{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KCBB774Q3QXMQSTBREWO3QTOU5","short_pith_number":"pith:KCBB774Q","canonical_record":{"source":{"id":"2507.22913","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T15:32:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1618a0535d503c712294e9c54734a9bab2de0f81b2198a98ef710f76f39331d1","abstract_canon_sha256":"7790f236289109f835ba52d9f15cba493916cd7f9babe012f1cac26083f5a87e"},"schema_version":"1.0"},"canonical_sha256":"50821fff90dc2ec84a61892cedc26ea764aebe7b875b88438b12f6c353bfe27f","source":{"kind":"arxiv","id":"2507.22913","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22913","created_at":"2026-07-05T11:46:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22913v1","created_at":"2026-07-05T11:46:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22913","created_at":"2026-07-05T11:46:01Z"},{"alias_kind":"pith_short_12","alias_value":"KCBB774Q3QXM","created_at":"2026-07-05T11:46:01Z"},{"alias_kind":"pith_short_16","alias_value":"KCBB774Q3QXMQSTB","created_at":"2026-07-05T11:46:01Z"},{"alias_kind":"pith_short_8","alias_value":"KCBB774Q","created_at":"2026-07-05T11:46:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KCBB774Q3QXMQSTBREWO3QTOU5","target":"record","payload":{"canonical_record":{"source":{"id":"2507.22913","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T15:32:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1618a0535d503c712294e9c54734a9bab2de0f81b2198a98ef710f76f39331d1","abstract_canon_sha256":"7790f236289109f835ba52d9f15cba493916cd7f9babe012f1cac26083f5a87e"},"schema_version":"1.0"},"canonical_sha256":"50821fff90dc2ec84a61892cedc26ea764aebe7b875b88438b12f6c353bfe27f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:01.519612Z","signature_b64":"ygsKodhpb3keMTCD7tmf/m3wHLrZag+Iz1Yn/Zesllm+WGBej9CJcFDBYsbyutSU7A5Z1hoOZb0WaLo6+NtgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50821fff90dc2ec84a61892cedc26ea764aebe7b875b88438b12f6c353bfe27f","last_reissued_at":"2026-07-05T11:46:01.519013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:01.519013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.22913","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:46:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g8wOva4vsEkg+gdaPweqo0UyxvD5hKDO+mOBBGZtXiCBMz14iL45HGCQwXUCnzCO3e9qKlRoUSqig4IXOAFPDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:45:40.356326Z"},"content_sha256":"cb67d543c2d710883a97a80fa6ea3aef5c0d14ecf79d8797ac02357fde715a59","schema_version":"1.0","event_id":"sha256:cb67d543c2d710883a97a80fa6ea3aef5c0d14ecf79d8797ac02357fde715a59"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KCBB774Q3QXMQSTBREWO3QTOU5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Hybrid Framework for Subject Analysis: Integrating Embedding-Based Regression Models with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daqing He, Diana Zhang, Jason Thomale, Jinyu Liu, Lingzi Hong, Xiaoying Song","submitted_at":"2025-07-19T15:32:46Z","abstract_excerpt":"Providing subject access to information resources is an essential function of any library management system. Large language models (LLMs) have been widely used in classification and summarization tasks, but their capability to perform subject analysis is underexplored. Multi-label classification with traditional machine learning (ML) models has been used for subject analysis but struggles with unseen cases. LLMs offer an alternative but often over-generate and hallucinate. Therefore, we propose a hybrid framework that integrates embedding-based ML models with LLMs. This approach uses ML models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22913","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/2507.22913/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:46:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QU/QiadNVbcSqeH5mPuntv1bxYlDQsL6ewZDBv6ubKeC6a2FDEI88AyBOmzUSIJhyC2YvkSjx+NW52Qxs1ZIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:45:40.356731Z"},"content_sha256":"c97296c5a2de43f3b83eb90b0a03d04c44e3ddb4c13bd0b68dc0489eb1f210da","schema_version":"1.0","event_id":"sha256:c97296c5a2de43f3b83eb90b0a03d04c44e3ddb4c13bd0b68dc0489eb1f210da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KCBB774Q3QXMQSTBREWO3QTOU5/bundle.json","state_url":"https://pith.science/pith/KCBB774Q3QXMQSTBREWO3QTOU5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KCBB774Q3QXMQSTBREWO3QTOU5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T15:45:40Z","links":{"resolver":"https://pith.science/pith/KCBB774Q3QXMQSTBREWO3QTOU5","bundle":"https://pith.science/pith/KCBB774Q3QXMQSTBREWO3QTOU5/bundle.json","state":"https://pith.science/pith/KCBB774Q3QXMQSTBREWO3QTOU5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KCBB774Q3QXMQSTBREWO3QTOU5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KCBB774Q3QXMQSTBREWO3QTOU5","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":"7790f236289109f835ba52d9f15cba493916cd7f9babe012f1cac26083f5a87e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T15:32:46Z","title_canon_sha256":"1618a0535d503c712294e9c54734a9bab2de0f81b2198a98ef710f76f39331d1"},"schema_version":"1.0","source":{"id":"2507.22913","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22913","created_at":"2026-07-05T11:46:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22913v1","created_at":"2026-07-05T11:46:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22913","created_at":"2026-07-05T11:46:01Z"},{"alias_kind":"pith_short_12","alias_value":"KCBB774Q3QXM","created_at":"2026-07-05T11:46:01Z"},{"alias_kind":"pith_short_16","alias_value":"KCBB774Q3QXMQSTB","created_at":"2026-07-05T11:46:01Z"},{"alias_kind":"pith_short_8","alias_value":"KCBB774Q","created_at":"2026-07-05T11:46:01Z"}],"graph_snapshots":[{"event_id":"sha256:c97296c5a2de43f3b83eb90b0a03d04c44e3ddb4c13bd0b68dc0489eb1f210da","target":"graph","created_at":"2026-07-05T11:46:01Z","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/2507.22913/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Providing subject access to information resources is an essential function of any library management system. Large language models (LLMs) have been widely used in classification and summarization tasks, but their capability to perform subject analysis is underexplored. Multi-label classification with traditional machine learning (ML) models has been used for subject analysis but struggles with unseen cases. LLMs offer an alternative but often over-generate and hallucinate. Therefore, we propose a hybrid framework that integrates embedding-based ML models with LLMs. This approach uses ML models","authors_text":"Daqing He, Diana Zhang, Jason Thomale, Jinyu Liu, Lingzi Hong, Xiaoying Song","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T15:32:46Z","title":"A Hybrid Framework for Subject Analysis: Integrating Embedding-Based Regression Models with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22913","kind":"arxiv","version":1},"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:cb67d543c2d710883a97a80fa6ea3aef5c0d14ecf79d8797ac02357fde715a59","target":"record","created_at":"2026-07-05T11:46:01Z","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":"7790f236289109f835ba52d9f15cba493916cd7f9babe012f1cac26083f5a87e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T15:32:46Z","title_canon_sha256":"1618a0535d503c712294e9c54734a9bab2de0f81b2198a98ef710f76f39331d1"},"schema_version":"1.0","source":{"id":"2507.22913","kind":"arxiv","version":1}},"canonical_sha256":"50821fff90dc2ec84a61892cedc26ea764aebe7b875b88438b12f6c353bfe27f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50821fff90dc2ec84a61892cedc26ea764aebe7b875b88438b12f6c353bfe27f","first_computed_at":"2026-07-05T11:46:01.519013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:01.519013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ygsKodhpb3keMTCD7tmf/m3wHLrZag+Iz1Yn/Zesllm+WGBej9CJcFDBYsbyutSU7A5Z1hoOZb0WaLo6+NtgCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:01.519612Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22913","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb67d543c2d710883a97a80fa6ea3aef5c0d14ecf79d8797ac02357fde715a59","sha256:c97296c5a2de43f3b83eb90b0a03d04c44e3ddb4c13bd0b68dc0489eb1f210da"],"state_sha256":"c4ba338688b439979e1f4d7a437bb939bf0f31e2086b77eacfda58e40a557d59"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E+1PxO95hIXLJ55LrtqdLAK2G1ehLIyNNUR6q1AyO6ndpt3zTGkr8+plE0n/KrduOympvYiL+fLMrSenV+KWDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:45:40.373615Z","bundle_sha256":"2adbdfae56cc7b7372ead8318c9780d56a79c1c7f97f00d98392cac0eb0d0b3a"}}