{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4SEVKLP74Z2MCTVD33GESV53W2","short_pith_number":"pith:4SEVKLP7","schema_version":"1.0","canonical_sha256":"e489552dffe674c14ea3decc4957bbb6bd9b742fcc29335bd15be1fd7a5b8ac9","source":{"kind":"arxiv","id":"2505.02847","version":3},"attestation_state":"computed","paper":{"title":"Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","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","submitted_at":"2025-05-01T19:06:10Z","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"},"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":"2505.02847","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-01T19:06:10Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"43c2c2033672195a45a2bcc7db206a29a827b2649b9bcb1d8e43170ffafebfe9","abstract_canon_sha256":"ce50230ee108cfbed874a504d753ed3cc0ea59bc85e23b918550b41b9018ecb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:31.492835Z","signature_b64":"cXEZBP8LWYDBQmwZ6lSHzH2AnzKWg7OFM21tIHdd0IOSlrfBGsFQQO7oVo8D8PQg9udUfqIOukNaBDPdd14EAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e489552dffe674c14ea3decc4957bbb6bd9b742fcc29335bd15be1fd7a5b8ac9","last_reissued_at":"2026-07-05T11:06:31.492286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:31.492286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","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","submitted_at":"2025-05-01T19:06:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02847","kind":"arxiv","version":3},"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/2505.02847/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":"2505.02847","created_at":"2026-07-05T11:06:31.492360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02847v3","created_at":"2026-07-05T11:06:31.492360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02847","created_at":"2026-07-05T11:06:31.492360+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SEVKLP74Z2M","created_at":"2026-07-05T11:06:31.492360+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SEVKLP74Z2MCTVD","created_at":"2026-07-05T11:06:31.492360+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SEVKLP7","created_at":"2026-07-05T11:06:31.492360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":203,"is_internal_anchor":false},{"citing_arxiv_id":"2603.06194","citing_title":"MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07138","citing_title":"Can You Break RLVER? Probing Adversarial Robustness of RL-Trained Empathetic Agents","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02913","citing_title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","ref_index":164,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4SEVKLP74Z2MCTVD33GESV53W2","json":"https://pith.science/pith/4SEVKLP74Z2MCTVD33GESV53W2.json","graph_json":"https://pith.science/api/pith-number/4SEVKLP74Z2MCTVD33GESV53W2/graph.json","events_json":"https://pith.science/api/pith-number/4SEVKLP74Z2MCTVD33GESV53W2/events.json","paper":"https://pith.science/paper/4SEVKLP7"},"agent_actions":{"view_html":"https://pith.science/pith/4SEVKLP74Z2MCTVD33GESV53W2","download_json":"https://pith.science/pith/4SEVKLP74Z2MCTVD33GESV53W2.json","view_paper":"https://pith.science/paper/4SEVKLP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02847&json=true","fetch_graph":"https://pith.science/api/pith-number/4SEVKLP74Z2MCTVD33GESV53W2/graph.json","fetch_events":"https://pith.science/api/pith-number/4SEVKLP74Z2MCTVD33GESV53W2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SEVKLP74Z2MCTVD33GESV53W2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SEVKLP74Z2MCTVD33GESV53W2/action/storage_attestation","attest_author":"https://pith.science/pith/4SEVKLP74Z2MCTVD33GESV53W2/action/author_attestation","sign_citation":"https://pith.science/pith/4SEVKLP74Z2MCTVD33GESV53W2/action/citation_signature","submit_replication":"https://pith.science/pith/4SEVKLP74Z2MCTVD33GESV53W2/action/replication_record"}},"created_at":"2026-07-05T11:06:31.492360+00:00","updated_at":"2026-07-05T11:06:31.492360+00:00"}