{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EBA2Y6UAZS4APD74XLY4JVJBQJ","short_pith_number":"pith:EBA2Y6UA","schema_version":"1.0","canonical_sha256":"2041ac7a80ccb8078ffcbaf1c4d521824e207caaa0253e38b2f1202a19604015","source":{"kind":"arxiv","id":"2606.29531","version":1},"attestation_state":"computed","paper":{"title":"MotionAtlas: Detailed Region Captioning for Motion-Centric Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anna Wang, Haochen Wang, Jacky Mai, Jason Li, Kuan Gao, Weisong Liu, Yanwei Li, Yikang Zhou, Yuhao Wang, Zhaoxiang Zhang, Zhongwei Ren","submitted_at":"2026-06-28T17:54:55Z","abstract_excerpt":"We propose MotionAtlas, a system for detailed captioning of motion-centric videos, comprising (1) a dedicated human-annotated benchmark, (2) a scalable, high-quality pipeline to construct training samples, and (3) a family of powerful Video-MLLMs. Unlike conventional global motion captioning datasets, we focus on region-aware motion captioning: given a video and a spatiotemporal mask, the model generates precise descriptions of motion within the target region, thereby alleviating visual clutter and motion entanglement and enabling reliable, quantifiable evaluation. Concretely, we first build M"},"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":"2606.29531","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T17:54:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d5b5daeb3d391aa367878bfb538d1f07adacb024a768f8226c33f46ef4192f01","abstract_canon_sha256":"08f6fad1e37c35857cf88fd0b7ee6f0d6df082f55eac57a781000812a789f51d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:10.583989Z","signature_b64":"eslLhNHf90o8zBNBiYjBF2nzSI5WC59oC0AKW7HrTIjUuEriE8rchFmGvNh3l3ncafb93mcJ93lKjTWL3qheDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2041ac7a80ccb8078ffcbaf1c4d521824e207caaa0253e38b2f1202a19604015","last_reissued_at":"2026-06-30T01:18:10.583276Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:10.583276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MotionAtlas: Detailed Region Captioning for Motion-Centric Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anna Wang, Haochen Wang, Jacky Mai, Jason Li, Kuan Gao, Weisong Liu, Yanwei Li, Yikang Zhou, Yuhao Wang, Zhaoxiang Zhang, Zhongwei Ren","submitted_at":"2026-06-28T17:54:55Z","abstract_excerpt":"We propose MotionAtlas, a system for detailed captioning of motion-centric videos, comprising (1) a dedicated human-annotated benchmark, (2) a scalable, high-quality pipeline to construct training samples, and (3) a family of powerful Video-MLLMs. Unlike conventional global motion captioning datasets, we focus on region-aware motion captioning: given a video and a spatiotemporal mask, the model generates precise descriptions of motion within the target region, thereby alleviating visual clutter and motion entanglement and enabling reliable, quantifiable evaluation. Concretely, we first build M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29531","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/2606.29531/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":"2606.29531","created_at":"2026-06-30T01:18:10.583381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29531v1","created_at":"2026-06-30T01:18:10.583381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29531","created_at":"2026-06-30T01:18:10.583381+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBA2Y6UAZS4A","created_at":"2026-06-30T01:18:10.583381+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBA2Y6UAZS4APD74","created_at":"2026-06-30T01:18:10.583381+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBA2Y6UA","created_at":"2026-06-30T01:18:10.583381+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/EBA2Y6UAZS4APD74XLY4JVJBQJ","json":"https://pith.science/pith/EBA2Y6UAZS4APD74XLY4JVJBQJ.json","graph_json":"https://pith.science/api/pith-number/EBA2Y6UAZS4APD74XLY4JVJBQJ/graph.json","events_json":"https://pith.science/api/pith-number/EBA2Y6UAZS4APD74XLY4JVJBQJ/events.json","paper":"https://pith.science/paper/EBA2Y6UA"},"agent_actions":{"view_html":"https://pith.science/pith/EBA2Y6UAZS4APD74XLY4JVJBQJ","download_json":"https://pith.science/pith/EBA2Y6UAZS4APD74XLY4JVJBQJ.json","view_paper":"https://pith.science/paper/EBA2Y6UA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29531&json=true","fetch_graph":"https://pith.science/api/pith-number/EBA2Y6UAZS4APD74XLY4JVJBQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/EBA2Y6UAZS4APD74XLY4JVJBQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBA2Y6UAZS4APD74XLY4JVJBQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBA2Y6UAZS4APD74XLY4JVJBQJ/action/storage_attestation","attest_author":"https://pith.science/pith/EBA2Y6UAZS4APD74XLY4JVJBQJ/action/author_attestation","sign_citation":"https://pith.science/pith/EBA2Y6UAZS4APD74XLY4JVJBQJ/action/citation_signature","submit_replication":"https://pith.science/pith/EBA2Y6UAZS4APD74XLY4JVJBQJ/action/replication_record"}},"created_at":"2026-06-30T01:18:10.583381+00:00","updated_at":"2026-06-30T01:18:10.583381+00:00"}