{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IQHMJQDLMZ2IV36PEEOU37WXRM","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":"3253bdf1daec287a318186f92404cd6fc84585bf6e9e79b8a97781cd06340d19","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-21T11:51:13Z","title_canon_sha256":"4f46db1c6fce239f4818602ac3e5a75458b5dfe42fdde5a8eaf043a35338de42"},"schema_version":"1.0","source":{"id":"2404.13627","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.13627","created_at":"2026-07-05T09:16:14Z"},{"alias_kind":"arxiv_version","alias_value":"2404.13627v3","created_at":"2026-07-05T09:16:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13627","created_at":"2026-07-05T09:16:14Z"},{"alias_kind":"pith_short_12","alias_value":"IQHMJQDLMZ2I","created_at":"2026-07-05T09:16:14Z"},{"alias_kind":"pith_short_16","alias_value":"IQHMJQDLMZ2IV36P","created_at":"2026-07-05T09:16:14Z"},{"alias_kind":"pith_short_8","alias_value":"IQHMJQDL","created_at":"2026-07-05T09:16:14Z"}],"graph_snapshots":[{"event_id":"sha256:981818b8ae8e97243f1cf1046c46e2f1a83105c80daec5c42cf9b107ce32a4f0","target":"graph","created_at":"2026-07-05T09:16:14Z","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/2404.13627/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have sparked substantial interest and debate concerning their potential emergence of Theory of Mind (ToM) ability. Theory of mind evaluations currently focuses on testing models using machine-generated data or game settings prone to shortcuts and spurious correlations, which lacks evaluation of machine ToM ability in real-world human interaction scenarios. This poses a pressing demand to develop new real-world scenario benchmarks. We introduce NegotiationToM, a new benchmark designed to stress-test machine ToM in real-world negotiation surrounding covered multi-dim","authors_text":"Cheng Jiayang, Chunkit Chan, Haoran Li, Hongming Zhang, Wei Fan, Weiqi Wang, Xin Liu, Yangqiu Song, Yauwai Yim, Zheye Deng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-21T11:51:13Z","title":"NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13627","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:d8c80599f5bee9a95ee3f342b9a82ba9ce87d46b59d86f801aef3919c1ca03d9","target":"record","created_at":"2026-07-05T09:16:14Z","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":"3253bdf1daec287a318186f92404cd6fc84585bf6e9e79b8a97781cd06340d19","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-21T11:51:13Z","title_canon_sha256":"4f46db1c6fce239f4818602ac3e5a75458b5dfe42fdde5a8eaf043a35338de42"},"schema_version":"1.0","source":{"id":"2404.13627","kind":"arxiv","version":3}},"canonical_sha256":"440ec4c06b66748aefcf211d4dfed78b055a6acb6e2deb78205ce65bd3f74fa8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"440ec4c06b66748aefcf211d4dfed78b055a6acb6e2deb78205ce65bd3f74fa8","first_computed_at":"2026-07-05T09:16:14.586581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:14.586581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jZtoU1xkhfCTCqlO8Cq0CmaGmvJmr18bejWmWmP6RAXNRQ2pQXC5BoEyapZBK/BuWzuzA7VoBZa08ygLluWxCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:14.587132Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.13627","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8c80599f5bee9a95ee3f342b9a82ba9ce87d46b59d86f801aef3919c1ca03d9","sha256:981818b8ae8e97243f1cf1046c46e2f1a83105c80daec5c42cf9b107ce32a4f0"],"state_sha256":"bbe635663ff765ee8506eb9e3cd89f2bece63df2c0f9c0b1a8032d4b18b6d22e"}