2025 · paper
Temporal fingerprints for identity matching across fully encrypted domains
Develops a temporal-activity representation for matching accounts across encrypted domains without relying on message content.[65]
Network intelligence and temporal modeling
Shahar Somin
שחר סומין
Identity: verifiedThe BIU Network Intelligence Lab page uses Shahar Somin and matches the roster; the publication record also uses the same identity. [64][65]
Documented foundation
Research & experience
Somin’s laboratory studies structural and temporal signals in complex networks, including encrypted or partially observed systems.[64][65]
graph analysistemporal fingerprintsAI for hidden coordinationcyber and financial networks
CV and official profile
The institutional lab profile and publication page were inspected; no standalone CV was verified.[64]
Selected work
Representative records, not a complete publication list. Metadata confirms attribution; it does not independently replicate a result.
Patent evidence
1 catalogued patent record · 1 identified family
Coverage: Partial inventor search
Network-stabilization family attributed through exact name, topic and co-inventor Yaniv Altshuler. Inspected US20150040248A1 (Encryption-resistant watermarking; NDS/Cisco metadata; Itsik Mantin and Shahar Somin) remains withheld: no independent career bridge resolved this same-name corporate attribution. An inaccessible MIT biography is not negative evidence.
Systems and methods for network stabilization prediction
US11323334B2 · Published 2022-05-03
Published patent document inspected
Publication assignee: Netz Forecasts Ltd
Named inventor Shahar Somin; network research and co-inventor Altshuler corroborated by institutional publications. Assignee is the captured publication metadata, not a current-ownership determination.[250][293]
Original report snapshot
Original evidence: not verified
No attributable patent record was verified in the bounded search.
Records are counted separately from identified families. Author-reported entries are labelled and may still need publication verification. Inventorship, publication-time applicant and current ownership are different facts. No legal-status, patentability or freedom-to-operate conclusion is made.
Scores prioritize research fit from 1–10; they are not probabilities.
Review: Reviewed with limitations
Proposed capability matches, not confirmed relationships. Scores are analyst judgments with low forecast confidence; researcher interests, capacity and feasibility need confirmation.
Internal connections
11 candidates
Connection 1
Orr Levy
Proposal hypothesis: Levy's failure coupling in biological networks and Somin's temporal graph analysis share a question about early warning before coordinated failure.[5][6][64][65]
First test and score details
First test
Proposed first test: Generate networks with known failure cascades and compare temporal fingerprints with static coupling estimates on warning time and false alarms.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 3
Why this rank
Rank 1/11; fit 9/10 (3 topic overlap + 3 complementarity + 3 feasible first test). New pairing outside the frozen portfolio co-member graph. Temporal identity-matching methods are a transferable modelling idea, not evidence of biological mechanism. Equal scores use existing-first, then stable researcher ID.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work.
Connection 2
Mor Weiss
Proposal hypothesis: Somin's temporal fingerprinting identifies a concrete leakage risk for Mor Weiss's secure distributed protocols.[64][65][123]
First test and score details
First test
Proposed first test: Generate synthetic encrypted-message timings and compare coordination inference before and after a specified padding schedule, reporting leakage and overhead.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 3
Why this rank
Rank 2/11; fit 9/10 (3 topic overlap + 3 complementarity + 3 feasible first test). New pairing outside the frozen portfolio co-member graph. Encryption alone does not hide metadata; no real-person identity matching is proposed. Equal scores use existing-first, then stable researcher ID.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work.
Connection 3
Gonen Singer
Original proposal
Proposal hypothesis: Somin can derive temporal coordination features and Singer can test whether those features improve a stochastic resource-allocation decision.[64][65][79][80]
First test and score details
First test
Proposed first test: Inject known demand bursts into a synthetic service network and compare feature-informed allocation with a rate-only controller on unmet demand and false interventions.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 2
Why this rank
Rank 3/11; fit 8/10 (2 topic overlap + 3 complementarity + 3 feasible first test). Preserved original co-membership proposal in o03. An added candidate, Orr Levy (9/10), ranks above this original because its stated pair-specific roles and first test score higher; this original is limited as follows: Correlation in event timing is not a causal intervention target; retain the simpler controller if decision quality does not improve. No automatic score boost for original membership. Equal scores use existing-first, then stable researcher ID.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work. Original initiative conditions remain: o03 Shahar Somin: Conditional later role: test temporal network signals only if approved event-network data adds value beyond the queueing baseline.
Show 8 moreShow fewer internal connections
Connection 4
Izack Cohen
Original proposal
Proposal hypothesis: Somin's temporal network signals could identify coordination patterns that Izack Cohen's queueing model misses in a service workflow.[64][65][97][98]
First test and score details
First test
Proposed first test: Generate event logs with known bottlenecks and compare a queue-only detector with a temporal-network feature extension on false alarms and detection delay.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 2
Why this rank
Rank 4/11; fit 8/10 (2 topic overlap + 3 complementarity + 3 feasible first test). Preserved original co-membership proposal in o03. An added candidate, Orr Levy (9/10), ranks above this original because its stated pair-specific roles and first test score higher; this original is limited as follows: Synthetic signals must beat the simpler process baseline before requesting governed real event-network data. No automatic score boost for original membership. Equal scores use existing-first, then stable researcher ID.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work. Original initiative conditions remain: o03 Shahar Somin: Conditional later role: test temporal network signals only if approved event-network data adds value beyond the queueing baseline.
Connection 5
Ilan Reuven Cohen
Original proposal
Proposal hypothesis: Somin's temporal models can forecast short-lived load changes while Ilan Cohen's online algorithms decide allocations before future arrivals are known.[64][65][119][120]
First test and score details
First test
Proposed first test: Compare a forecast-assisted online scheduler with a forecast-free rule under synthetic coordination shocks; report regret when forecasts are wrong.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 2
Why this rank
Rank 5/11; fit 8/10 (2 topic overlap + 3 complementarity + 3 feasible first test). Preserved original co-membership proposal in o03. An added candidate, Orr Levy (9/10), ranks above this original because its stated pair-specific roles and first test score higher; this original is limited as follows: Only add temporal forecasting if it improves the chosen allocation task under misspecification. No automatic score boost for original membership. Equal scores use existing-first, then stable researcher ID.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work. Original initiative conditions remain: o03 Ilan Reuven Cohen: Conditional later role: add online/fair-allocation rules if the chosen service decision requires them. o03 Shahar Somin: Conditional later role: test temporal network signals only if approved event-network data adds value beyond the queueing baseline.
Connection 6
Ran Gelles
Proposal hypothesis: Somin's temporal network signals could identify communication-failure patterns that Gelles's interactive protocols need to tolerate.[57][58][64][65]
First test and score details
First test
Proposed first test: Generate synthetic coordinated packet-loss bursts and compare a fixed redundancy rule with a pattern-aware rule on failure and overhead.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 2
Why this rank
Rank 6/11; fit 8/10 (2 topic overlap + 3 complementarity + 3 feasible first test). New pairing outside the frozen portfolio co-member graph. Pattern detection must not be used as an unsupported identity or malicious-intent inference. Equal scores use existing-first, then stable researcher ID.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work.
Connection 7
Ori Ernst
Proposal hypothesis: Somin can identify temporal event structure and Ernst can preserve source support when summarizing network incidents.[64][65][93][94][95]
First test and score details
First test
Proposed first test: Create a synthetic timestamped incident corpus and compare event-grounded summaries with ordinary summaries on ordering errors and unsupported links.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 2
Why this rank
Rank 7/11; fit 8/10 (2 topic overlap + 3 complementarity + 3 feasible first test). New pairing outside the frozen portfolio co-member graph. Temporal association must not be rewritten as causal coordination or malicious intent. Equal scores use existing-first, then stable researcher ID.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work.
Connection 8
Benjamin M. Zaidel
Proposal hypothesis: Somin's temporal network analysis could identify bursty coordination that changes Zaidel's multiuser interference assumptions.[64][65][102]
First test and score details
First test
Proposed first test: Generate synchronized and independent user activity with equal mean load; compare throughput prediction with and without temporal features.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 2
Why this rank
Rank 8/11; fit 8/10 (2 topic overlap + 3 complementarity + 3 feasible first test). New pairing outside the frozen portfolio co-member graph. Activity patterns do not reveal identities or intent, and their value must exceed a simple burst model. Equal scores use existing-first, then stable researcher ID.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work.
Connection 9
Yair Noam
Proposal hypothesis: Somin's temporal patterns can be tested as early indicators of interference changes in Noam's spectrum-management models.[64][65][130][131]
First test and score details
First test
Proposed first test: Generate matched-mean stationary and burst-coordinated interferers; compare temporal prediction with a power-only estimator on outage warning.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 2
Why this rank
Rank 9/11; fit 8/10 (2 topic overlap + 3 complementarity + 3 feasible first test). New pairing outside the frozen portfolio co-member graph. No source establishes Somin as a radio hardware specialist; the contribution is temporal modelling. Equal scores use existing-first, then stable researcher ID.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work.
Connection 10
Hila Chalutz-Ben Gal
Original proposal
Proposal hypothesis: Chalutz-Ben Gal's workforce-network questions and Somin's temporal graph methods could test coordination changes using consented aggregate activity patterns.[22][23][64][65]
First test and score details
First test
Proposed first test: Construct synthetic team-event graphs with known handoff failures and compare temporal motifs with static network features on detection accuracy.
Score components
- complementarity
- 3
- feasible first test
- 2
- topic overlap
- 2
Why this rank
Rank 10/11; fit 7/10 (2 topic overlap + 3 complementarity + 2 feasible first test). Preserved original co-membership proposal in o03. An added candidate, Orr Levy (9/10), ranks above this original because its stated pair-specific roles and first test score higher; this original is limited as follows: Do not infer worker identity, performance or willingness from temporal fingerprints; governed access and a non-surveillance purpose are required. No automatic score boost for original membership. Equal scores use existing-first, then stable researcher ID.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work. Original initiative conditions remain: o03 Shahar Somin: Conditional later role: test temporal network signals only if approved event-network data adds value beyond the queueing baseline.
Connection 11
Alexandra Simonovsky
Identity check needed: Conditional proposal: confirm the researcher identity and research interests before assessing this match.
Proposal hypothesis: Conditional on confirmation, Simonovsky could coordinate a synthetic event-analysis challenge while Somin supplies the temporal-network task and evaluation.[16][17][64][65]
First test and score details
First test
Conditional proposed first test: After identity confirmation, package artificial coordination and non-coordination traces and pilot the clarity of labels and submission requirements.
Score components
- complementarity
- 2
- feasible first test
- 1
- topic overlap
- 1
Why this rank
Rank 11/11; fit 4/10 (1 topic overlap + 2 complementarity + 1 feasible first test). New pairing outside the frozen portfolio co-member graph. No real identity matching or inferred network-science expertise for Simonovsky is proposed. Equal scores use existing-first, then stable researcher ID.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work. Conditional: confirm Alexandra Simonovsky identity and current role before any team assignment. Evidence supports AI-agent event coordination only; research appointment, teaching role and technical research expertise are not verified. Excluded from confirmed-team claims.
External connections
10 candidates
Connection 1
Kathleen M. Carley
Carnegie Mellon University
Original proposal
Her dynamic-network-analysis and social-cybersecurity program could complement behavioral validation and governance; no willingness is asserted.[64][65][66][445]
First test and score details
First test
Evaluate on a synthetic and one de-identified event stream with predefined latency and false-alarm thresholds.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 4
Why this rank
Rank 1/10 after semantic revision; analyst score 10 = max(1, 4+3+3): topic overlap 4/4, complementarity 3/3, feasible first test 3/3. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked. Original remains first under these components; original status breaks equal-score ties only, without a prestige bonus.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified.
Connection 2
Michael Bronstein
University of Oxford
Proposed capability match: Shahar Somin's graph analysis, temporal fingerprints can be paired with Michael Bronstein's documented geometric deep learning, graph neural networks for privacy-preserving early warning for coordinated failures. The specific contribution is geometric structure and graph representations; this transfer is an analyst hypothesis.[64][65][74][442]
First test and score details
First test
Compare a geometry/graph-aware model with a parameter-matched unstructured baseline under structural perturbations using a synthetic temporal coordination network with planted events and held-out activity regimes. Compare held-out error, symmetry consistency and robustness to altered graph topology with an activity-matched shuffled-network null.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 3
Why this rank
Rank 2/10 after semantic revision; analyst score 9 = max(1, 3+3+3): topic overlap 3/4, complementarity 3/3, feasible first test 3/3. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified. The refreshed Oxford profile also lists an Aithyra scientific-director role; the original Oxford institution string is preserved.
Connection 3
Matthew O. Jackson
Stanford University
Proposed capability match: Shahar Somin's graph analysis, temporal fingerprints can be paired with Matthew O. Jackson's documented network science and economics, economic modelling for privacy-preserving early warning for coordinated failures. The specific contribution is network structure and economic incentives; this transfer is an analyst hypothesis.[64][65][463]
First test and score details
First test
Compare allocation or diffusion on the measured graph with degree-preserving shuffled graphs using a synthetic temporal coordination network with planted events and held-out activity regimes. Compare distributional effects and sensitivity to network-position assumptions with an activity-matched shuffled-network null.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 3
Why this rank
Rank 3/10 after semantic revision; analyst score 9 = max(1, 3+3+3): topic overlap 3/4, complementarity 3/3, feasible first test 3/3. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified.
Show 7 moreShow fewer external connections
Connection 4
Yarin Gal
University of Oxford
Proposed capability match: Shahar Somin's graph analysis, temporal fingerprints can be paired with Yarin Gal's documented Bayesian deep learning, uncertainty estimation for privacy-preserving early warning for coordinated failures. The specific contribution is uncertainty and selective prediction; this transfer is an analyst hypothesis.[64][65][78][452]
First test and score details
First test
Compare uncertainty estimates with calibrated single-model and ensemble baselines under a predefined shift using a synthetic temporal coordination network with planted events and held-out activity regimes. Compare calibration error, risk-coverage and confident-error rate with an activity-matched shuffled-network null.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 2
Why this rank
Rank 4/10 after semantic revision; analyst score 8 = max(1, 2+3+3): topic overlap 2/4, complementarity 3/3, feasible first test 3/3. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified.
Connection 5
David Tse
Stanford University
Proposed capability match: Shahar Somin's graph analysis, temporal fingerprints can be paired with David Tse's documented information-theoretic methods, decentralized systems for privacy-preserving early warning for coordinated failures. The specific contribution is first-principles data and decentralized-system modelling; this transfer is an analyst hypothesis.[64][65][496]
First test and score details
First test
Compare a decentralized or information-constrained algorithm with a centralized reference on a small reproducible workload using a synthetic temporal coordination network with planted events and held-out activity regimes. Compare communication cost, correctness and sensitivity to missing participants with an activity-matched shuffled-network null.
Score components
- complementarity
- 2
- feasible first test
- 3
- topic overlap
- 3
Why this rank
Rank 5/10 after semantic revision; analyst score 8 = max(1, 3+2+3): topic overlap 3/4, complementarity 2/3, feasible first test 3/3. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified. His refreshed lab page describes wireless as a previous application and current work on decentralized systems; no active wireless project is assumed.
Connection 6
Gregory Wornell
Massachusetts Institute of Technology
Proposed capability match: Shahar Somin's graph analysis, temporal fingerprints can be paired with Gregory Wornell's documented signal processing, statistical inference for privacy-preserving early warning for coordinated failures. The specific contribution is joint statistical inference and information constraints; this transfer is an analyst hypothesis.[64][65][110][503]
First test and score details
First test
Compare full-data inference with task-specific compressed statistics at fixed communication or storage budget using a synthetic temporal coordination network with planted events and held-out activity regimes. Compare estimation error, calibration and bits per valid decision with an activity-matched shuffled-network null.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 2
Why this rank
Rank 6/10 after semantic revision; analyst score 8 = max(1, 2+3+3): topic overlap 2/4, complementarity 3/3, feasible first test 3/3. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified.
Connection 7
Susan Athey
Stanford University
Proposed capability match for Shahar Somin with Susan Athey: Causal analysis can complement coordination research once treatment, outcome and network-interference assumptions are explicit; planted coordination labels alone do not define a causal benefit.[64][65][433]
First test and score details
First test
Simulate a temporal communication network with treatment defined as randomized access to a coordination aid and outcome defined as handoff delay on planted collaborative tasks. Compare a stratified treatment-effect estimate with a simple randomized-arm difference against the simulator's planted effects; vary network interference explicitly. A shuffled graph is a separate topology check, not a treatment comparator.
Score components
- complementarity
- 2
- feasible first test
- 2
- topic overlap
- 3
Why this rank
Rank 7/10 after semantic revision; analyst score 7 = max(1, 3+2+2): topic overlap 3/4, complementarity 2/3, feasible first test 2/3. Causal analysis can complement coordination research once treatment, outcome and network-interference assumptions are explicit; planted coordination labels alone do not define a causal benefit. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified. Post-review scope: Causal analysis can complement coordination research once treatment, outcome and network-interference assumptions are explicit; planted coordination labels alone do not define a causal benefit. This revised proposal awaits independent targeted re-review; simulated outcomes would establish model behavior only, not biological, clinical or deployed benefit.
Connection 8
Shafi Goldwasser
Massachusetts Institute of Technology
Proposed capability match: Shahar Somin's graph analysis, temporal fingerprints can be paired with Shafi Goldwasser's documented cryptography, proof systems for privacy-preserving early warning for coordinated failures. The specific contribution is formal privacy bounds on network alerts; this transfer is an analyst hypothesis.[64][65][126][457]
First test and score details
First test
Specify allowed leakage from an aggregate coordination alert and attack a toy release rule using a synthetic temporal coordination network with planted events and held-out activity regimes. Compare information disclosed and correctness of alert verification with an activity-matched shuffled-network null.
Score components
- complementarity
- 3
- feasible first test
- 2
- topic overlap
- 2
Why this rank
Rank 8/10 after semantic revision; analyst score 7 = max(1, 2+3+2): topic overlap 2/4, complementarity 3/3, feasible first test 2/3. The experiment, numerical inputs or identity/scope needs confirmation before execution.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified. Contribution is restricted to the scope stated in the first test.
Connection 9
Michael Mitzenmacher
Harvard University
Proposed capability match for Shahar Somin with Michael Mitzenmacher: Randomized algorithms address processing of network-event streams through an explicit resource problem; routing efficiency must be separated from identifying coordination.[64][65][101][478]
First test and score details
First test
Convert the synthetic network's timestamped messages into jobs with arrival times, processing demands and destinations. Compare randomized two-choice routing with uniform random routing on the same arrivals and server capacity; report tail queueing delay, dropped jobs and detection latency for identical planted events under the same downstream detector.
Score components
- complementarity
- 3
- feasible first test
- 2
- topic overlap
- 2
Why this rank
Rank 9/10 after semantic revision; analyst score 7 = max(1, 2+3+2): topic overlap 2/4, complementarity 3/3, feasible first test 2/3. Randomized algorithms address processing of network-event streams through an explicit resource problem; routing efficiency must be separated from identifying coordination. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified. Post-review scope: Randomized algorithms address processing of network-event streams through an explicit resource problem; routing efficiency must be separated from identifying coordination. This revised proposal awaits independent targeted re-review; simulated outcomes would establish model behavior only, not biological, clinical or deployed benefit.
Connection 10
Daron Acemoglu
Massachusetts Institute of Technology
Proposed capability match for Shahar Somin with Daron Acemoglu: Labour/task modelling is a conditional extension requiring new model objects, not an established interpretation of temporal coordination data.[64][65][430]
First test and score details
First test
Define a separate toy worker-task bipartite model with stipulated skill requirements, task demand and productivity. Compare two declared automation scenarios with the same initial workforce and demand; report model-implied reassignment and unmet tasks while sweeping substitution/complementarity assumptions. Do not infer labour outcomes from a generic communication graph.
Score components
- complementarity
- 2
- feasible first test
- 1
- topic overlap
- 1
Why this rank
Rank 10/10 after semantic revision; analyst score 4 = max(1, 1+2+1): topic overlap 1/4, complementarity 2/3, feasible first test 1/3. Labour/task modelling is a conditional extension requiring new model objects, not an established interpretation of temporal coordination data. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified. Post-review scope: Labour/task modelling is a conditional extension requiring new model objects, not an established interpretation of temporal coordination data. This revised proposal awaits independent targeted re-review; simulated outcomes would establish model behavior only, not biological, clinical or deployed benefit.
Evidence & open questions
- No standalone CV or attributable patent record was verified.
Inspect claim ratings and independent review
Shahar Somin has source-grounded capabilities in network intelligence and temporal modeling, represented here by graph analysis, temporal fingerprints, AI for hidden coordination. [64][65]
Moderate confidenceReview: reviewedThe sources establish public professional activity, not comparative quality, future performance, or willingness to participate.
Review record
- profiles_a: supports. Somin's official lab page directly describes graph theory, temporal modeling, AI, hidden coordination and resilience, and it lists the exact 2025 temporal-fingerprint work.
Hypothesis for 2027–2031: Shahar Somin could explore privacy-preserving early warning for coordinated failures through the bounded first test described in this profile. [64][65][66]
Low confidenceReview: reviewedIdentity leakage, distribution shift, and the legitimacy of operational use require independent review.
Review record
- profiles_a: supports. The hypothesis is grounded in temporal-activity matching and dynamic-network analysis; Carley's CMU profile directly supports social cybersecurity and coordinated-activity analysis. Operational legitimacy and privacy are unresolved as stated.