{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4SEVKLP74Z2MCTVD33GESV53W2","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":"ce50230ee108cfbed874a504d753ed3cc0ea59bc85e23b918550b41b9018ecb6","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-01T19:06:10Z","title_canon_sha256":"43c2c2033672195a45a2bcc7db206a29a827b2649b9bcb1d8e43170ffafebfe9"},"schema_version":"1.0","source":{"id":"2505.02847","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02847","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02847v3","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02847","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"4SEVKLP74Z2M","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"4SEVKLP74Z2MCTVD","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"4SEVKLP7","created_at":"2026-07-05T11:06:31Z"}],"graph_snapshots":[{"event_id":"sha256:9fe6907ad28cf2b2acefcc1a01fc9440cca56a7047eae2be4e3db47286505529","target":"graph","created_at":"2026-07-05T11:06:31Z","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/2505.02847/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Assessing how well a large language model (LLM) understands human, rather than merely text, remains an open challenge. To bridge the gap, we introduce Sentient Agent as a Judge (SAGE), an automated evaluation framework that measures an LLM's higher-order social cognition. SAGE instantiates a Sentient Agent that simulates human-like emotional changes and inner thoughts during interaction, providing a more realistic evaluation of the tested model in multi-turn conversations. At every turn, the agent reasons about (i) how its emotion changes, (ii) how it feels, and (iii) how it should reply, yiel","authors_text":"Bang Zhang, Fanghua Ye, Jian Li, Jiaqi Chen, Peisong Wang, Qingxuan Jiang, Ruotian Ma, Xiaolong Li, Xingyu Chen, Yifan Yang, Yue Wang, Zhaopeng Tu, Zheng Xie","cross_cats":["cs.AI","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-01T19:06:10Z","title":"Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02847","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":"sha256:226ec108ee9f38b6273e180741eed7a1e458c12e35d46ee2a9a8ab0ea75f5e6a","target":"record","created_at":"2026-07-05T11:06:31Z","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":"ce50230ee108cfbed874a504d753ed3cc0ea59bc85e23b918550b41b9018ecb6","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-01T19:06:10Z","title_canon_sha256":"43c2c2033672195a45a2bcc7db206a29a827b2649b9bcb1d8e43170ffafebfe9"},"schema_version":"1.0","source":{"id":"2505.02847","kind":"arxiv","version":3}},"canonical_sha256":"e489552dffe674c14ea3decc4957bbb6bd9b742fcc29335bd15be1fd7a5b8ac9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e489552dffe674c14ea3decc4957bbb6bd9b742fcc29335bd15be1fd7a5b8ac9","first_computed_at":"2026-07-05T11:06:31.492286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:31.492286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cXEZBP8LWYDBQmwZ6lSHzH2AnzKWg7OFM21tIHdd0IOSlrfBGsFQQO7oVo8D8PQg9udUfqIOukNaBDPdd14EAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:31.492835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02847","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:226ec108ee9f38b6273e180741eed7a1e458c12e35d46ee2a9a8ab0ea75f5e6a","sha256:9fe6907ad28cf2b2acefcc1a01fc9440cca56a7047eae2be4e3db47286505529"],"state_sha256":"75355cd0fc575f33faa29005278316260fdb19cd61bb76c5b9790a2b6df76f37"}