{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CFGRQ7U55QVZ2JR4HOWM37KTPW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"687e051a7284996a7367f639decc3ba94ae87c89093b6093c9768a2a4c38d00c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-08T20:35:06Z","title_canon_sha256":"23cd939941b65b5ef926cab9b8b7159e870f6a0390d205cba1a800ac7195dbc1"},"schema_version":"1.0","source":{"id":"2402.06044","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.06044","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"arxiv_version","alias_value":"2402.06044v3","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06044","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"pith_short_12","alias_value":"CFGRQ7U55QVZ","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"pith_short_16","alias_value":"CFGRQ7U55QVZ2JR4","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"pith_short_8","alias_value":"CFGRQ7U5","created_at":"2026-07-05T08:26:19Z"}],"graph_snapshots":[{"event_id":"sha256:c6808968afee6b4d72bcd79792e6d65aac59a09f13606922791af70488cbda47","target":"graph","created_at":"2026-07-05T08:26:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.06044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural Theory-of-Mind (N-ToM), machine's ability to understand and keep track of the mental states of others, is pivotal in developing socially intelligent agents. However, prevalent N-ToM benchmarks have several shortcomings, including the presence of ambiguous and artificial narratives, absence of personality traits and preferences, a lack of questions addressing characters' psychological mental states, and limited diversity in the questions posed. In response to these issues, we construct OpenToM, a new benchmark for assessing N-ToM with (1) longer and clearer narrative stories, (2) charact","authors_text":"Hainiu Xu, Jinhua Du, Lixing Zhu, Runcong Zhao, Yulan He","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-08T20:35:06Z","title":"OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06044","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9a549d7ae1adb4df7b8f602c93c595819586352d107d6297162ea4602648006d","target":"record","created_at":"2026-07-05T08:26:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"687e051a7284996a7367f639decc3ba94ae87c89093b6093c9768a2a4c38d00c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-08T20:35:06Z","title_canon_sha256":"23cd939941b65b5ef926cab9b8b7159e870f6a0390d205cba1a800ac7195dbc1"},"schema_version":"1.0","source":{"id":"2402.06044","kind":"arxiv","version":3}},"canonical_sha256":"114d187e9dec2b9d263c3baccdfd537dbf0cb0063e722777fe9b7af451b36e9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"114d187e9dec2b9d263c3baccdfd537dbf0cb0063e722777fe9b7af451b36e9b","first_computed_at":"2026-07-05T08:26:19.159753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:19.159753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V3REaTH2C5Ev5Al5y/onQrG+5LwYJCyJfkOE/yTtDcOx7AWJD8kD1fIZDe9w1OkPy5MOnDFWTAKxxhottxzOBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:19.160251Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.06044","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a549d7ae1adb4df7b8f602c93c595819586352d107d6297162ea4602648006d","sha256:c6808968afee6b4d72bcd79792e6d65aac59a09f13606922791af70488cbda47"],"state_sha256":"7148edde424c15e7c6a0f32e7cb3f9aed5dbb631c71bba1ccf3e321a754c551b"}