{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NXJEKJX4PVZSXZXJ6C57K22QES","short_pith_number":"pith:NXJEKJX4","schema_version":"1.0","canonical_sha256":"6dd24526fc7d732be6e9f0bbf56b50249f8c5bb3aa83189af8d48e1d5c9f1314","source":{"kind":"arxiv","id":"2502.18180","version":2},"attestation_state":"computed","paper":{"title":"ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Jenq-Neng Hwang, Jiaang Li, Jianhao Wang, Lei Li, Sen Jia, Serge Belongie, Zhaochong An","submitted_at":"2025-02-25T13:12:55Z","abstract_excerpt":"Advancements in Multimodal Large Language Models (MLLMs) have improved human motion understanding. However, these models remain constrained by their \"instruct-only\" nature, lacking interactivity and adaptability for diverse analytical perspectives. To address these challenges, we introduce ChatMotion, a multimodal multi-agent framework for human motion analysis. ChatMotion dynamically interprets user intent, decomposes complex tasks into meta-tasks, and activates specialized function modules for motion comprehension. It integrates multiple specialized modules, such as the MotionCore, to analyz"},"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":"2502.18180","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-25T13:12:55Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"61e0c970c4cf25c30c1de47415905d0d65f53ac41af20ea7d9ca04945b2a4c3a","abstract_canon_sha256":"a95dacc24ba2ec165908c4f03e0bd283e33c932a5f67a78c0c1cb04100e89344"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:07.847571Z","signature_b64":"bMxa709RoW3PkuDTdv+aRMQJc2BymNkAVPnjEHUb4nemY0dPbneY1RHPLA/JlF9dJOtmlDmdKrCWd46avRzTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dd24526fc7d732be6e9f0bbf56b50249f8c5bb3aa83189af8d48e1d5c9f1314","last_reissued_at":"2026-07-05T10:21:07.847101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:07.847101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Jenq-Neng Hwang, Jiaang Li, Jianhao Wang, Lei Li, Sen Jia, Serge Belongie, Zhaochong An","submitted_at":"2025-02-25T13:12:55Z","abstract_excerpt":"Advancements in Multimodal Large Language Models (MLLMs) have improved human motion understanding. However, these models remain constrained by their \"instruct-only\" nature, lacking interactivity and adaptability for diverse analytical perspectives. To address these challenges, we introduce ChatMotion, a multimodal multi-agent framework for human motion analysis. ChatMotion dynamically interprets user intent, decomposes complex tasks into meta-tasks, and activates specialized function modules for motion comprehension. It integrates multiple specialized modules, such as the MotionCore, to analyz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18180","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/2502.18180/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":"2502.18180","created_at":"2026-07-05T10:21:07.847167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18180v2","created_at":"2026-07-05T10:21:07.847167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18180","created_at":"2026-07-05T10:21:07.847167+00:00"},{"alias_kind":"pith_short_12","alias_value":"NXJEKJX4PVZS","created_at":"2026-07-05T10:21:07.847167+00:00"},{"alias_kind":"pith_short_16","alias_value":"NXJEKJX4PVZSXZXJ","created_at":"2026-07-05T10:21:07.847167+00:00"},{"alias_kind":"pith_short_8","alias_value":"NXJEKJX4","created_at":"2026-07-05T10:21:07.847167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20888","citing_title":"Fine-grained Human Motion Understanding with Language Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18620","citing_title":"BCL: Bayesian In-Context Learning Framework for Information Extraction","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18861","citing_title":"URDF Synthesis from RGB-D Sequences via Differentiable Joint Inference and Energy-Consistent Verification","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19929","citing_title":"RAM: Recover Any 3D Human Motion in-the-Wild","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17898","citing_title":"ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18051","citing_title":"INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18037","citing_title":"HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NXJEKJX4PVZSXZXJ6C57K22QES","json":"https://pith.science/pith/NXJEKJX4PVZSXZXJ6C57K22QES.json","graph_json":"https://pith.science/api/pith-number/NXJEKJX4PVZSXZXJ6C57K22QES/graph.json","events_json":"https://pith.science/api/pith-number/NXJEKJX4PVZSXZXJ6C57K22QES/events.json","paper":"https://pith.science/paper/NXJEKJX4"},"agent_actions":{"view_html":"https://pith.science/pith/NXJEKJX4PVZSXZXJ6C57K22QES","download_json":"https://pith.science/pith/NXJEKJX4PVZSXZXJ6C57K22QES.json","view_paper":"https://pith.science/paper/NXJEKJX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18180&json=true","fetch_graph":"https://pith.science/api/pith-number/NXJEKJX4PVZSXZXJ6C57K22QES/graph.json","fetch_events":"https://pith.science/api/pith-number/NXJEKJX4PVZSXZXJ6C57K22QES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NXJEKJX4PVZSXZXJ6C57K22QES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NXJEKJX4PVZSXZXJ6C57K22QES/action/storage_attestation","attest_author":"https://pith.science/pith/NXJEKJX4PVZSXZXJ6C57K22QES/action/author_attestation","sign_citation":"https://pith.science/pith/NXJEKJX4PVZSXZXJ6C57K22QES/action/citation_signature","submit_replication":"https://pith.science/pith/NXJEKJX4PVZSXZXJ6C57K22QES/action/replication_record"}},"created_at":"2026-07-05T10:21:07.847167+00:00","updated_at":"2026-07-05T10:21:07.847167+00:00"}