{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GY4R3R7WKQ5BTL3LHFP5XT3XPM","short_pith_number":"pith:GY4R3R7W","schema_version":"1.0","canonical_sha256":"36391dc7f6543a19af6b395fdbcf777b33452562890370dfa25de7324af22cb2","source":{"kind":"arxiv","id":"2509.04504","version":1},"attestation_state":"computed","paper":{"title":"Behavioral Fingerprinting of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bei Yu, Hui-Ling Zhen, Mingxuan Yuan, Xianzhi Yu, Xing Li, Ying Zhang, Zehua Pei, Zhiyuan Yang","submitted_at":"2025-09-02T07:03:20Z","abstract_excerpt":"Current benchmarks for Large Language Models (LLMs) primarily focus on performance metrics, often failing to capture the nuanced behavioral characteristics that differentiate them. This paper introduces a novel ``Behavioral Fingerprinting'' framework designed to move beyond traditional evaluation by creating a multi-faceted profile of a model's intrinsic cognitive and interactive styles. Using a curated \\textit{Diagnostic Prompt Suite} and an innovative, automated evaluation pipeline where a powerful LLM acts as an impartial judge, we analyze eighteen models across capability tiers. Our result"},"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":"2509.04504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T07:03:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8136517a1324090fb83e564153b78f9b5038e4662d2ff33c00177922e201e3e2","abstract_canon_sha256":"4f11ac1fb1ae3dd0f35008262d21b4cb8b751776011546d236ba7652f8e3f2fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:24.181187Z","signature_b64":"bNE/sJ2GXZyaaZL7C+d1+SI/23ZJVmyZfY0HvzSe61W+aGPSGpFTNJnrZUFGYSUtDxWPpeQk1GqVr7ULV4GgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36391dc7f6543a19af6b395fdbcf777b33452562890370dfa25de7324af22cb2","last_reissued_at":"2026-07-05T12:05:24.180548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:24.180548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Behavioral Fingerprinting of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bei Yu, Hui-Ling Zhen, Mingxuan Yuan, Xianzhi Yu, Xing Li, Ying Zhang, Zehua Pei, Zhiyuan Yang","submitted_at":"2025-09-02T07:03:20Z","abstract_excerpt":"Current benchmarks for Large Language Models (LLMs) primarily focus on performance metrics, often failing to capture the nuanced behavioral characteristics that differentiate them. This paper introduces a novel ``Behavioral Fingerprinting'' framework designed to move beyond traditional evaluation by creating a multi-faceted profile of a model's intrinsic cognitive and interactive styles. Using a curated \\textit{Diagnostic Prompt Suite} and an innovative, automated evaluation pipeline where a powerful LLM acts as an impartial judge, we analyze eighteen models across capability tiers. Our result"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04504","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/2509.04504/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":"2509.04504","created_at":"2026-07-05T12:05:24.180630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04504v1","created_at":"2026-07-05T12:05:24.180630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04504","created_at":"2026-07-05T12:05:24.180630+00:00"},{"alias_kind":"pith_short_12","alias_value":"GY4R3R7WKQ5B","created_at":"2026-07-05T12:05:24.180630+00:00"},{"alias_kind":"pith_short_16","alias_value":"GY4R3R7WKQ5BTL3L","created_at":"2026-07-05T12:05:24.180630+00:00"},{"alias_kind":"pith_short_8","alias_value":"GY4R3R7W","created_at":"2026-07-05T12:05:24.180630+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30169","citing_title":"Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms","ref_index":100,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GY4R3R7WKQ5BTL3LHFP5XT3XPM","json":"https://pith.science/pith/GY4R3R7WKQ5BTL3LHFP5XT3XPM.json","graph_json":"https://pith.science/api/pith-number/GY4R3R7WKQ5BTL3LHFP5XT3XPM/graph.json","events_json":"https://pith.science/api/pith-number/GY4R3R7WKQ5BTL3LHFP5XT3XPM/events.json","paper":"https://pith.science/paper/GY4R3R7W"},"agent_actions":{"view_html":"https://pith.science/pith/GY4R3R7WKQ5BTL3LHFP5XT3XPM","download_json":"https://pith.science/pith/GY4R3R7WKQ5BTL3LHFP5XT3XPM.json","view_paper":"https://pith.science/paper/GY4R3R7W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04504&json=true","fetch_graph":"https://pith.science/api/pith-number/GY4R3R7WKQ5BTL3LHFP5XT3XPM/graph.json","fetch_events":"https://pith.science/api/pith-number/GY4R3R7WKQ5BTL3LHFP5XT3XPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GY4R3R7WKQ5BTL3LHFP5XT3XPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GY4R3R7WKQ5BTL3LHFP5XT3XPM/action/storage_attestation","attest_author":"https://pith.science/pith/GY4R3R7WKQ5BTL3LHFP5XT3XPM/action/author_attestation","sign_citation":"https://pith.science/pith/GY4R3R7WKQ5BTL3LHFP5XT3XPM/action/citation_signature","submit_replication":"https://pith.science/pith/GY4R3R7WKQ5BTL3LHFP5XT3XPM/action/replication_record"}},"created_at":"2026-07-05T12:05:24.180630+00:00","updated_at":"2026-07-05T12:05:24.180630+00:00"}