{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MEYMV52WB5ZJLJWB2PGHVWAO7G","short_pith_number":"pith:MEYMV52W","schema_version":"1.0","canonical_sha256":"6130caf7560f7295a6c1d3cc7ad80ef9aa3abc017d46ef2eb4340e59887bee9a","source":{"kind":"arxiv","id":"2604.23282","version":2},"attestation_state":"computed","paper":{"title":"Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A two-stage cascade filters candidates by skeletal pose then verifies semantics with a multi-agent squad to bridge the gap where different actions share similar structures.","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chuxin Wang, Guijin Luo, Sihang Cai, Tao Jin, Yixuan Tang, Zequn Xie, Zhou Zhao","submitted_at":"2026-04-25T12:53:15Z","abstract_excerpt":"Text-based person anomaly search retrieves specific behavioral events from surveillance archives using natural-language queries. Although recent pose-aware methods align geometric structures well, they face a fundamental Pose-Semantic Gap: semantically different actions can share similar skeletal geometries. While Multimodal Large Language Models (MLLMs) can reduce this ambiguity, using them for large-scale retrieval is computationally prohibitive. We propose the Structure-Semantic Decoupled Cascade (SSDC) framework, which decouples retrieval into two stages: (1) Structure-Aware Coarse Retriev"},"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":"2604.23282","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-25T12:53:15Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"1635911ff6033b54975f20a72325427826b0434d0bf5343535c9457f432b9507","abstract_canon_sha256":"19158958884ff097ad978dc1cc87b02c6c62db770879be4303c007a6def39835"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:12.419731Z","signature_b64":"cJ6nUn1PO+YzGcH1af7+d0easWljBQg9BxN2ZRDkPDrfYxgswylHGElwsNbcPgsJt6g2sOiv0cWAtvYZYUiNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6130caf7560f7295a6c1d3cc7ad80ef9aa3abc017d46ef2eb4340e59887bee9a","last_reissued_at":"2026-05-28T01:05:12.419147Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:12.419147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A two-stage cascade filters candidates by skeletal pose then verifies semantics with a multi-agent squad to bridge the gap where different actions share similar structures.","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chuxin Wang, Guijin Luo, Sihang Cai, Tao Jin, Yixuan Tang, Zequn Xie, Zhou Zhao","submitted_at":"2026-04-25T12:53:15Z","abstract_excerpt":"Text-based person anomaly search retrieves specific behavioral events from surveillance archives using natural-language queries. Although recent pose-aware methods align geometric structures well, they face a fundamental Pose-Semantic Gap: semantically different actions can share similar skeletal geometries. While Multimodal Large Language Models (MLLMs) can reduce this ambiguity, using them for large-scale retrieval is computationally prohibitive. We propose the Structure-Semantic Decoupled Cascade (SSDC) framework, which decouples retrieval into two stages: (1) Structure-Aware Coarse Retriev"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We propose the Structure-Semantic Decoupled Cascade (SSDC) framework, which decouples retrieval into two stages: (1) Structure-Aware Coarse Retrieval... and (2) Detective Squad Interaction... Experiments on the PAB benchmark show that SSDC achieves state-of-the-art performance by balancing efficiency and semantic reasoning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That skeletal geometry provides a sufficiently reliable coarse filter for semantically distinct actions and that the multi-agent LLM verification stage can resolve remaining ambiguities accurately without introducing new errors or prohibitive latency.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SSDC is a two-stage cascade that first filters by skeletal similarity then applies a multi-agent LLM squad for semantic verification, achieving SOTA on the PAB benchmark for text-based person anomaly search.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A two-stage cascade filters candidates by skeletal pose then verifies semantics with a multi-agent squad to bridge the gap where different actions share similar structures.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1499d35b1977e6d0d6e1d63ef7e5217b7be59dc48420a8d8fde366dbd62da02d"},"source":{"id":"2604.23282","kind":"arxiv","version":2},"verdict":{"id":"7a6fe0ff-1d84-4ad9-a15b-ec4b2e4e5ba1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T08:24:13.323832Z","strongest_claim":"We propose the Structure-Semantic Decoupled Cascade (SSDC) framework, which decouples retrieval into two stages: (1) Structure-Aware Coarse Retrieval... and (2) Detective Squad Interaction... Experiments on the PAB benchmark show that SSDC achieves state-of-the-art performance by balancing efficiency and semantic reasoning.","one_line_summary":"SSDC is a two-stage cascade that first filters by skeletal similarity then applies a multi-agent LLM squad for semantic verification, achieving SOTA on the PAB benchmark for text-based person anomaly search.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That skeletal geometry provides a sufficiently reliable coarse filter for semantically distinct actions and that the multi-agent LLM verification stage can resolve remaining ambiguities accurately without introducing new errors or prohibitive latency.","pith_extraction_headline":"A two-stage cascade filters candidates by skeletal pose then verifies semantics with a multi-agent squad to bridge the gap where different actions share similar structures."},"integrity":{"clean":false,"summary":{"advisory":1,"critical":0,"by_detector":{"doi_compliance":{"total":1,"advisory":1,"critical":0,"informational":0}},"informational":0},"endpoint":"/pith/2604.23282/integrity.json","findings":[{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.23919/cje.2025.00.215Towards) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detector":"doi_compliance","severity":"advisory","ref_index":9,"audited_at":"2026-05-19T23:16:39.952796Z","detected_doi":"10.23919/cje.2025.00.215Towards","finding_type":"recoverable_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null}],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T09:36:08.064601Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T23:16:39.952796Z","status":"completed","version":"1.0.0","findings_count":1}],"snapshot_sha256":"ce7d2ea1dc2a6dc90b2212a582a296c570bab740de27697c4d494b03bbcf1ed7"},"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":"2604.23282","created_at":"2026-05-28T01:05:12.419205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.23282v2","created_at":"2026-05-28T01:05:12.419205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.23282","created_at":"2026-05-28T01:05:12.419205+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEYMV52WB5ZJ","created_at":"2026-05-28T01:05:12.419205+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEYMV52WB5ZJLJWB","created_at":"2026-05-28T01:05:12.419205+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEYMV52W","created_at":"2026-05-28T01:05:12.419205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MEYMV52WB5ZJLJWB2PGHVWAO7G","json":"https://pith.science/pith/MEYMV52WB5ZJLJWB2PGHVWAO7G.json","graph_json":"https://pith.science/api/pith-number/MEYMV52WB5ZJLJWB2PGHVWAO7G/graph.json","events_json":"https://pith.science/api/pith-number/MEYMV52WB5ZJLJWB2PGHVWAO7G/events.json","paper":"https://pith.science/paper/MEYMV52W"},"agent_actions":{"view_html":"https://pith.science/pith/MEYMV52WB5ZJLJWB2PGHVWAO7G","download_json":"https://pith.science/pith/MEYMV52WB5ZJLJWB2PGHVWAO7G.json","view_paper":"https://pith.science/paper/MEYMV52W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.23282&json=true","fetch_graph":"https://pith.science/api/pith-number/MEYMV52WB5ZJLJWB2PGHVWAO7G/graph.json","fetch_events":"https://pith.science/api/pith-number/MEYMV52WB5ZJLJWB2PGHVWAO7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEYMV52WB5ZJLJWB2PGHVWAO7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEYMV52WB5ZJLJWB2PGHVWAO7G/action/storage_attestation","attest_author":"https://pith.science/pith/MEYMV52WB5ZJLJWB2PGHVWAO7G/action/author_attestation","sign_citation":"https://pith.science/pith/MEYMV52WB5ZJLJWB2PGHVWAO7G/action/citation_signature","submit_replication":"https://pith.science/pith/MEYMV52WB5ZJLJWB2PGHVWAO7G/action/replication_record"}},"created_at":"2026-05-28T01:05:12.419205+00:00","updated_at":"2026-05-28T01:05:12.419205+00:00"}