{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N4UC6HOZJIYVG3NTXVIUDEWUNP","short_pith_number":"pith:N4UC6HOZ","schema_version":"1.0","canonical_sha256":"6f282f1dd94a31536db3bd514192d46bc5a840e7b5f98e05c5588f5804d5abc9","source":{"kind":"arxiv","id":"2509.04376","version":2},"attestation_state":"computed","paper":{"title":"AnomalyLMM: Bridging Generative Knowledge and Discriminative Retrieval for Text-Based Person Anomaly Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Ju, Hu Zhang, Zhedong Zheng","submitted_at":"2025-09-04T16:34:46Z","abstract_excerpt":"With growing public safety demands, text-based person anomaly search has emerged as a critical task, aiming to retrieve individuals with abnormal behaviors via natural language descriptions. Unlike conventional person search, this task presents two unique challenges: (1) fine-grained cross-modal alignment between textual anomalies and visual behaviors, and (2) anomaly recognition under sparse real-world samples. While Large Multi-modal Models (LMMs) excel in multi-modal understanding, their potential for fine-grained anomaly retrieval remains underexplored, hindered by: (1) a domain gap betwee"},"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":"2509.04376","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T16:34:46Z","cross_cats_sorted":[],"title_canon_sha256":"26f640f53c29e12d8c17b64ffe095dfad9bd4b2deb78fc36e603827672808f59","abstract_canon_sha256":"e7ef1b39559b199400873a3fb755628a70f139889367b5a67eadf9ddadf3c6ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:23.082146Z","signature_b64":"qZ5PJZ6cQSk9lYobzZLIQT13TG0PkVvBA++yQncH9xXsS9kcJS2mRqmI+TaeAK842OJYIkegkYMa/A75W94oBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f282f1dd94a31536db3bd514192d46bc5a840e7b5f98e05c5588f5804d5abc9","last_reissued_at":"2026-07-05T12:05:23.081665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:23.081665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnomalyLMM: Bridging Generative Knowledge and Discriminative Retrieval for Text-Based Person Anomaly Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Ju, Hu Zhang, Zhedong Zheng","submitted_at":"2025-09-04T16:34:46Z","abstract_excerpt":"With growing public safety demands, text-based person anomaly search has emerged as a critical task, aiming to retrieve individuals with abnormal behaviors via natural language descriptions. Unlike conventional person search, this task presents two unique challenges: (1) fine-grained cross-modal alignment between textual anomalies and visual behaviors, and (2) anomaly recognition under sparse real-world samples. While Large Multi-modal Models (LMMs) excel in multi-modal understanding, their potential for fine-grained anomaly retrieval remains underexplored, hindered by: (1) a domain gap betwee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04376","kind":"arxiv","version":2},"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/2509.04376/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":"2509.04376","created_at":"2026-07-05T12:05:23.081725+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04376v2","created_at":"2026-07-05T12:05:23.081725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04376","created_at":"2026-07-05T12:05:23.081725+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4UC6HOZJIYV","created_at":"2026-07-05T12:05:23.081725+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4UC6HOZJIYVG3NT","created_at":"2026-07-05T12:05:23.081725+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4UC6HOZ","created_at":"2026-07-05T12:05:23.081725+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.09474","citing_title":"FaLCon: Facet-Anchored Retrieval with Late Consensus for Sim2Real Text-Based Person Anomaly Search","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N4UC6HOZJIYVG3NTXVIUDEWUNP","json":"https://pith.science/pith/N4UC6HOZJIYVG3NTXVIUDEWUNP.json","graph_json":"https://pith.science/api/pith-number/N4UC6HOZJIYVG3NTXVIUDEWUNP/graph.json","events_json":"https://pith.science/api/pith-number/N4UC6HOZJIYVG3NTXVIUDEWUNP/events.json","paper":"https://pith.science/paper/N4UC6HOZ"},"agent_actions":{"view_html":"https://pith.science/pith/N4UC6HOZJIYVG3NTXVIUDEWUNP","download_json":"https://pith.science/pith/N4UC6HOZJIYVG3NTXVIUDEWUNP.json","view_paper":"https://pith.science/paper/N4UC6HOZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04376&json=true","fetch_graph":"https://pith.science/api/pith-number/N4UC6HOZJIYVG3NTXVIUDEWUNP/graph.json","fetch_events":"https://pith.science/api/pith-number/N4UC6HOZJIYVG3NTXVIUDEWUNP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4UC6HOZJIYVG3NTXVIUDEWUNP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4UC6HOZJIYVG3NTXVIUDEWUNP/action/storage_attestation","attest_author":"https://pith.science/pith/N4UC6HOZJIYVG3NTXVIUDEWUNP/action/author_attestation","sign_citation":"https://pith.science/pith/N4UC6HOZJIYVG3NTXVIUDEWUNP/action/citation_signature","submit_replication":"https://pith.science/pith/N4UC6HOZJIYVG3NTXVIUDEWUNP/action/replication_record"}},"created_at":"2026-07-05T12:05:23.081725+00:00","updated_at":"2026-07-05T12:05:23.081725+00:00"}