{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N7VIFVWIV3DLW6XGGRSQOW22YG","short_pith_number":"pith:N7VIFVWI","schema_version":"1.0","canonical_sha256":"6fea82d6c8aec6bb7ae63465075b5ac18deeca3f26f931937de9a70c3446da09","source":{"kind":"arxiv","id":"2607.04653","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Video Physical Consistency via Role-aware Joint Training and Modality-decoupled Denoising","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangting Zheng, Haojing Chen, Hao Li, Jingtao Zhang, Shaofeng Zhang, Xiaosong Jia, Xue Yang, Yanyong Zhang, Zhen Yang","submitted_at":"2026-07-06T04:18:28Z","abstract_excerpt":"While modern video diffusion models excel in visual fidelity, maintaining long-range physical consistency remains a formidable challenge. Conventional pixel-reconstruction objectives mainly focus on appearance details and often fail to capture the underlying dynamics of a scene. To mitigate this, recent efforts have integrated auxiliary modalities (e.g., optical flow) to introduce physics priors via joint training with video appearance. However, these methods have three main limitations: (1) they do not distinguish the different motion patterns of different entity types; (2) joint modeling of "},"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":"2607.04653","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-06T04:18:28Z","cross_cats_sorted":[],"title_canon_sha256":"fa12d1ab0cfbe10f3f8b96e87f5413886e7701ee84b95867e98c28bc6d4862e5","abstract_canon_sha256":"c81fc7611809d5b756a47e539cc79d72c3840ce33f17aea998a33490cdb623c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:29.704303Z","signature_b64":"cxtKjgF61fX4VWoOejM3JZuZf8w9mhSSbf5GBf6LQiD/kfi1SaV9RJu3cPrFR1FEz8d4gclPtlUU4NuzfIexDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fea82d6c8aec6bb7ae63465075b5ac18deeca3f26f931937de9a70c3446da09","last_reissued_at":"2026-07-07T02:19:29.703641Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:29.703641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Video Physical Consistency via Role-aware Joint Training and Modality-decoupled Denoising","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangting Zheng, Haojing Chen, Hao Li, Jingtao Zhang, Shaofeng Zhang, Xiaosong Jia, Xue Yang, Yanyong Zhang, Zhen Yang","submitted_at":"2026-07-06T04:18:28Z","abstract_excerpt":"While modern video diffusion models excel in visual fidelity, maintaining long-range physical consistency remains a formidable challenge. Conventional pixel-reconstruction objectives mainly focus on appearance details and often fail to capture the underlying dynamics of a scene. To mitigate this, recent efforts have integrated auxiliary modalities (e.g., optical flow) to introduce physics priors via joint training with video appearance. However, these methods have three main limitations: (1) they do not distinguish the different motion patterns of different entity types; (2) joint modeling of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04653","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/2607.04653/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":"2607.04653","created_at":"2026-07-07T02:19:29.703741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04653v1","created_at":"2026-07-07T02:19:29.703741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04653","created_at":"2026-07-07T02:19:29.703741+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7VIFVWIV3DL","created_at":"2026-07-07T02:19:29.703741+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7VIFVWIV3DLW6XG","created_at":"2026-07-07T02:19:29.703741+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7VIFVWI","created_at":"2026-07-07T02:19:29.703741+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/N7VIFVWIV3DLW6XGGRSQOW22YG","json":"https://pith.science/pith/N7VIFVWIV3DLW6XGGRSQOW22YG.json","graph_json":"https://pith.science/api/pith-number/N7VIFVWIV3DLW6XGGRSQOW22YG/graph.json","events_json":"https://pith.science/api/pith-number/N7VIFVWIV3DLW6XGGRSQOW22YG/events.json","paper":"https://pith.science/paper/N7VIFVWI"},"agent_actions":{"view_html":"https://pith.science/pith/N7VIFVWIV3DLW6XGGRSQOW22YG","download_json":"https://pith.science/pith/N7VIFVWIV3DLW6XGGRSQOW22YG.json","view_paper":"https://pith.science/paper/N7VIFVWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04653&json=true","fetch_graph":"https://pith.science/api/pith-number/N7VIFVWIV3DLW6XGGRSQOW22YG/graph.json","fetch_events":"https://pith.science/api/pith-number/N7VIFVWIV3DLW6XGGRSQOW22YG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7VIFVWIV3DLW6XGGRSQOW22YG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7VIFVWIV3DLW6XGGRSQOW22YG/action/storage_attestation","attest_author":"https://pith.science/pith/N7VIFVWIV3DLW6XGGRSQOW22YG/action/author_attestation","sign_citation":"https://pith.science/pith/N7VIFVWIV3DLW6XGGRSQOW22YG/action/citation_signature","submit_replication":"https://pith.science/pith/N7VIFVWIV3DLW6XGGRSQOW22YG/action/replication_record"}},"created_at":"2026-07-07T02:19:29.703741+00:00","updated_at":"2026-07-07T02:19:29.703741+00:00"}