{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SWOHONJNQSBF32OXBWGIQ3RYDD","short_pith_number":"pith:SWOHONJN","schema_version":"1.0","canonical_sha256":"959c77352d84825de9d70d8c886e3818fa9c63ef63c84b24164c11601ec87bff","source":{"kind":"arxiv","id":"2605.26322","version":1},"attestation_state":"computed","paper":{"title":"OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adam Bawatneh, Amrit Singh Bedi, Mubarak Shah, Sagar Sapkota, Santu Karmaker","submitted_at":"2026-05-25T20:45:08Z","abstract_excerpt":"Theory of Mind (ToM), the ability to infer others' knowledge, intentions, and emotions, is commonly evaluated in large language models (LLMs) using end-point question answering, where performance is judged solely by the final answer to a social reasoning query. This paradigm obscures whether the model actually constructs the underlying mental-state representations required for robust reasoning, particularly in scenarios involving divergent, evolving, or mistaken beliefs. In order to address this research gap, we introduce OmniToM, a benchmark that directly evaluates these representations by re"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.26322","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-25T20:45:08Z","cross_cats_sorted":[],"title_canon_sha256":"e30486f4115a85a39e755503deb9c2ed58440eb68ac34e22a7f538f5deddd4de","abstract_canon_sha256":"6657b2240d64785486a42e2bc9061e1e8affe1311a4979b944af489e8f4a1e74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:11.979361Z","signature_b64":"ruEnkYwK8cDWu4ZRnmytOfx8mu18XtBG2xVFWtcQhzNAb6uLCbUJW6jqMbYN80J7+Xx6CceDRpI1Ztoin1oPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"959c77352d84825de9d70d8c886e3818fa9c63ef63c84b24164c11601ec87bff","last_reissued_at":"2026-05-27T01:05:11.978640Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:11.978640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adam Bawatneh, Amrit Singh Bedi, Mubarak Shah, Sagar Sapkota, Santu Karmaker","submitted_at":"2026-05-25T20:45:08Z","abstract_excerpt":"Theory of Mind (ToM), the ability to infer others' knowledge, intentions, and emotions, is commonly evaluated in large language models (LLMs) using end-point question answering, where performance is judged solely by the final answer to a social reasoning query. This paradigm obscures whether the model actually constructs the underlying mental-state representations required for robust reasoning, particularly in scenarios involving divergent, evolving, or mistaken beliefs. In order to address this research gap, we introduce OmniToM, a benchmark that directly evaluates these representations by re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26322","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.26322/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.26322","created_at":"2026-05-27T01:05:11.978757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26322v1","created_at":"2026-05-27T01:05:11.978757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26322","created_at":"2026-05-27T01:05:11.978757+00:00"},{"alias_kind":"pith_short_12","alias_value":"SWOHONJNQSBF","created_at":"2026-05-27T01:05:11.978757+00:00"},{"alias_kind":"pith_short_16","alias_value":"SWOHONJNQSBF32OX","created_at":"2026-05-27T01:05:11.978757+00:00"},{"alias_kind":"pith_short_8","alias_value":"SWOHONJN","created_at":"2026-05-27T01:05:11.978757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SWOHONJNQSBF32OXBWGIQ3RYDD","json":"https://pith.science/pith/SWOHONJNQSBF32OXBWGIQ3RYDD.json","graph_json":"https://pith.science/api/pith-number/SWOHONJNQSBF32OXBWGIQ3RYDD/graph.json","events_json":"https://pith.science/api/pith-number/SWOHONJNQSBF32OXBWGIQ3RYDD/events.json","paper":"https://pith.science/paper/SWOHONJN"},"agent_actions":{"view_html":"https://pith.science/pith/SWOHONJNQSBF32OXBWGIQ3RYDD","download_json":"https://pith.science/pith/SWOHONJNQSBF32OXBWGIQ3RYDD.json","view_paper":"https://pith.science/paper/SWOHONJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26322&json=true","fetch_graph":"https://pith.science/api/pith-number/SWOHONJNQSBF32OXBWGIQ3RYDD/graph.json","fetch_events":"https://pith.science/api/pith-number/SWOHONJNQSBF32OXBWGIQ3RYDD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SWOHONJNQSBF32OXBWGIQ3RYDD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SWOHONJNQSBF32OXBWGIQ3RYDD/action/storage_attestation","attest_author":"https://pith.science/pith/SWOHONJNQSBF32OXBWGIQ3RYDD/action/author_attestation","sign_citation":"https://pith.science/pith/SWOHONJNQSBF32OXBWGIQ3RYDD/action/citation_signature","submit_replication":"https://pith.science/pith/SWOHONJNQSBF32OXBWGIQ3RYDD/action/replication_record"}},"created_at":"2026-05-27T01:05:11.978757+00:00","updated_at":"2026-05-27T01:05:11.978757+00:00"}