{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7GPQ4VJ3TSVRTZSTMQPQYOQYJ5","short_pith_number":"pith:7GPQ4VJ3","schema_version":"1.0","canonical_sha256":"f99f0e553b9cab19e653641f0c3a184f6be7fb115a540d0dba075a515b5e73a9","source":{"kind":"arxiv","id":"2506.01119","version":1},"attestation_state":"computed","paper":{"title":"MOOSE: Pay Attention to Temporal Dynamics for Video Understanding via Optical Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dung Tran, Hieu Hoang, Hong Nguyen, Phong Nguyen, Shrikanth Narayanan","submitted_at":"2025-06-01T18:53:27Z","abstract_excerpt":"Many motion-centric video analysis tasks, such as atomic actions, detecting atypical motor behavior in individuals with autism, or analyzing articulatory motion in real-time MRI of human speech, require efficient and interpretable temporal modeling. Capturing temporal dynamics is a central challenge in video analysis, often requiring significant computational resources and fine-grained annotations that are not widely available. This paper presents MOOSE (Motion Flow Over Spatial Space), a novel temporally-centric video encoder explicitly integrating optical flow with spatial embeddings to mode"},"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":"2506.01119","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T18:53:27Z","cross_cats_sorted":[],"title_canon_sha256":"4d0b191c042429031bc953e3bee8d4ba3c29ecaab72da28a03d75abecffd90f5","abstract_canon_sha256":"3b2dcc9c6677607a564c058965326b722b31c92c9591b211d29941fb305b6fea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:46.832924Z","signature_b64":"jsaMy4RHO5rsh6lKz7FMwjzp+cSKOd+6LssuvzyFDsh0GBGKJy+jbhhVD4+2BIrGBpP5ZD7wiojGStMHxe6+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f99f0e553b9cab19e653641f0c3a184f6be7fb115a540d0dba075a515b5e73a9","last_reissued_at":"2026-07-05T11:13:46.832406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:46.832406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOOSE: Pay Attention to Temporal Dynamics for Video Understanding via Optical Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dung Tran, Hieu Hoang, Hong Nguyen, Phong Nguyen, Shrikanth Narayanan","submitted_at":"2025-06-01T18:53:27Z","abstract_excerpt":"Many motion-centric video analysis tasks, such as atomic actions, detecting atypical motor behavior in individuals with autism, or analyzing articulatory motion in real-time MRI of human speech, require efficient and interpretable temporal modeling. Capturing temporal dynamics is a central challenge in video analysis, often requiring significant computational resources and fine-grained annotations that are not widely available. This paper presents MOOSE (Motion Flow Over Spatial Space), a novel temporally-centric video encoder explicitly integrating optical flow with spatial embeddings to mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01119","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/2506.01119/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":"2506.01119","created_at":"2026-07-05T11:13:46.832479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01119v1","created_at":"2026-07-05T11:13:46.832479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01119","created_at":"2026-07-05T11:13:46.832479+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GPQ4VJ3TSVR","created_at":"2026-07-05T11:13:46.832479+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GPQ4VJ3TSVRTZST","created_at":"2026-07-05T11:13:46.832479+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GPQ4VJ3","created_at":"2026-07-05T11:13:46.832479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22823","citing_title":"Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7GPQ4VJ3TSVRTZSTMQPQYOQYJ5","json":"https://pith.science/pith/7GPQ4VJ3TSVRTZSTMQPQYOQYJ5.json","graph_json":"https://pith.science/api/pith-number/7GPQ4VJ3TSVRTZSTMQPQYOQYJ5/graph.json","events_json":"https://pith.science/api/pith-number/7GPQ4VJ3TSVRTZSTMQPQYOQYJ5/events.json","paper":"https://pith.science/paper/7GPQ4VJ3"},"agent_actions":{"view_html":"https://pith.science/pith/7GPQ4VJ3TSVRTZSTMQPQYOQYJ5","download_json":"https://pith.science/pith/7GPQ4VJ3TSVRTZSTMQPQYOQYJ5.json","view_paper":"https://pith.science/paper/7GPQ4VJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01119&json=true","fetch_graph":"https://pith.science/api/pith-number/7GPQ4VJ3TSVRTZSTMQPQYOQYJ5/graph.json","fetch_events":"https://pith.science/api/pith-number/7GPQ4VJ3TSVRTZSTMQPQYOQYJ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GPQ4VJ3TSVRTZSTMQPQYOQYJ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GPQ4VJ3TSVRTZSTMQPQYOQYJ5/action/storage_attestation","attest_author":"https://pith.science/pith/7GPQ4VJ3TSVRTZSTMQPQYOQYJ5/action/author_attestation","sign_citation":"https://pith.science/pith/7GPQ4VJ3TSVRTZSTMQPQYOQYJ5/action/citation_signature","submit_replication":"https://pith.science/pith/7GPQ4VJ3TSVRTZSTMQPQYOQYJ5/action/replication_record"}},"created_at":"2026-07-05T11:13:46.832479+00:00","updated_at":"2026-07-05T11:13:46.832479+00:00"}