{"schema_version":"papers/paper-detail-v1","title":"OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling","surface":"papers","opportunity_kernel":{"paper_id":"1d4724d6-4cd8-4e29-904c-bc3d31743d8a","title":"OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling","authors":["Adam Bawatneh","Sagar Sapkota","Amrit Singh Bedi","Santu Karmaker","Mubarak Shah"],"arxiv_id":"2605.26322v1","doi":null,"published_at":"2026-05-25T20:45:08.000Z","score_object":{"overall":{"value":7,"scale":"0-10","confidence":0.85,"confidence_reason":"Backfilled from persisted papers.viability_score.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-27T20:11:01.649Z","fresh_until":"2026-06-26T20:11:01.649Z","is_stale":false,"source_count":1,"missingness":[]},"technical":{"value":1.4,"scale":"0-10","confidence":0.55,"confidence_reason":"Backfilled from paper_extraction_scorecards.reconstruction_score.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-27T20:12:20.733Z","fresh_until":"2026-06-10T20:12:20.733Z","is_stale":false,"source_count":1,"missingness":["reproducibility_results.reproducibility_score","deployability_scores.score"]},"commercial":{"value":4,"scale":"0-10","confidence":0.75,"confidence_reason":"Backfilled from persisted commercial_flags and repo availability.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-27T20:11:01.649Z","fresh_until":"2026-06-26T20:11:01.649Z","is_stale":false,"source_count":1,"missingness":[]},"market":{"value":2,"scale":"0-10","confidence":0.45,"confidence_reason":"Heuristic market score materialized from paper metadata, repo availability, and deployability.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-27T20:31:53.275Z","fresh_until":"2026-06-10T20:31:53.275Z","is_stale":false,"source_count":1,"missingness":[]},"team":{"value":4.9,"scale":"0-10","confidence":0.42,"confidence_reason":"Heuristic fallback from paper author count and extracted affiliations.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-27T20:11:01.649Z","fresh_until":"2026-06-10T20:11:01.649Z","is_stale":false,"source_count":2,"missingness":[]},"methodology":{"value":3.9,"scale":"0-10","confidence":0.82,"confidence_reason":"Backfilled from paper_extraction_scorecards.total_score.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-27T20:12:20.733Z","fresh_until":"2026-06-26T20:12:20.733Z","is_stale":false,"source_count":2,"missingness":[]}},"evidence_receipt":{"freshness":"fresh","proof_status":"unverified","repo_status":"missing","references_count":0,"source_count":3,"coverage":0.5,"missingness":["repo_url","references","proof_status"],"unresolved_unknowns":["proof verification has not been recorded yet"],"last_verification_at":"2026-05-27T20:31:53.275Z"},"lineage_hash":"f33020e6568f7d7b7f4ae6029b16a70caf8ab606761da9b34e4fdaac1b0043f0"},"distribution":null,"replication_evidence":[],"author_dna":[]}