{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YI26ZHKSVEG5XQDF6755CQ6LS4","short_pith_number":"pith:YI26ZHKS","schema_version":"1.0","canonical_sha256":"c235ec9d52a90ddbc065f7fbd143cb9701f05d417bfe29ce32005dd1f422dea4","source":{"kind":"arxiv","id":"2607.18664","version":1},"attestation_state":"computed","paper":{"title":"DeforM: Reasoning-Guided Physics-Aware Video Generation via Spatial-Temporal Masking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xinyuan Chen, Yaohui Wang, Yunyi Li, Yu Qiao","submitted_at":"2026-07-21T03:23:52Z","abstract_excerpt":"Video generation models achieve high visual quality but often struggle to generate physics-aware videos. Unlike rigid-body motion, which can be described by explicit trajectories or formulas, complex deformation dynamics remain challenging to synthesize. We observe that a lack of physical reasoning for localizing dynamic areas allows irrelevant regions to dilute the model's attention, leading to generation failure. In this paper, we propose DeforM, a reasoning-guided image-to-video generation framework that directs the model's focus toward physics-critical regions. To reason about and localize"},"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":"2607.18664","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T03:23:52Z","cross_cats_sorted":[],"title_canon_sha256":"2ef006408cc7f4fe76fa401372e880cc1e727c8b84cb08c8cbe33f934b66dc5c","abstract_canon_sha256":"4f2416c7355f2aeb307559c711f72f575736a647475de880b931c5dbdaa8eb37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:59.281201Z","signature_b64":"AG5FQMH9LTxeYx2ccfDdb15ePKIVh1mkfoGHFKYABieiBnn8zYxPNoaU6nWnhVIXa08xs2z3BwPzHoZohk2pAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c235ec9d52a90ddbc065f7fbd143cb9701f05d417bfe29ce32005dd1f422dea4","last_reissued_at":"2026-07-22T00:22:59.280366Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:59.280366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeforM: Reasoning-Guided Physics-Aware Video Generation via Spatial-Temporal Masking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xinyuan Chen, Yaohui Wang, Yunyi Li, Yu Qiao","submitted_at":"2026-07-21T03:23:52Z","abstract_excerpt":"Video generation models achieve high visual quality but often struggle to generate physics-aware videos. Unlike rigid-body motion, which can be described by explicit trajectories or formulas, complex deformation dynamics remain challenging to synthesize. We observe that a lack of physical reasoning for localizing dynamic areas allows irrelevant regions to dilute the model's attention, leading to generation failure. In this paper, we propose DeforM, a reasoning-guided image-to-video generation framework that directs the model's focus toward physics-critical regions. To reason about and localize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18664","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/2607.18664/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":"2607.18664","created_at":"2026-07-22T00:22:59.280797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18664v1","created_at":"2026-07-22T00:22:59.280797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18664","created_at":"2026-07-22T00:22:59.280797+00:00"},{"alias_kind":"pith_short_12","alias_value":"YI26ZHKSVEG5","created_at":"2026-07-22T00:22:59.280797+00:00"},{"alias_kind":"pith_short_16","alias_value":"YI26ZHKSVEG5XQDF","created_at":"2026-07-22T00:22:59.280797+00:00"},{"alias_kind":"pith_short_8","alias_value":"YI26ZHKS","created_at":"2026-07-22T00:22:59.280797+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/YI26ZHKSVEG5XQDF6755CQ6LS4","json":"https://pith.science/pith/YI26ZHKSVEG5XQDF6755CQ6LS4.json","graph_json":"https://pith.science/api/pith-number/YI26ZHKSVEG5XQDF6755CQ6LS4/graph.json","events_json":"https://pith.science/api/pith-number/YI26ZHKSVEG5XQDF6755CQ6LS4/events.json","paper":"https://pith.science/paper/YI26ZHKS"},"agent_actions":{"view_html":"https://pith.science/pith/YI26ZHKSVEG5XQDF6755CQ6LS4","download_json":"https://pith.science/pith/YI26ZHKSVEG5XQDF6755CQ6LS4.json","view_paper":"https://pith.science/paper/YI26ZHKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18664&json=true","fetch_graph":"https://pith.science/api/pith-number/YI26ZHKSVEG5XQDF6755CQ6LS4/graph.json","fetch_events":"https://pith.science/api/pith-number/YI26ZHKSVEG5XQDF6755CQ6LS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YI26ZHKSVEG5XQDF6755CQ6LS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YI26ZHKSVEG5XQDF6755CQ6LS4/action/storage_attestation","attest_author":"https://pith.science/pith/YI26ZHKSVEG5XQDF6755CQ6LS4/action/author_attestation","sign_citation":"https://pith.science/pith/YI26ZHKSVEG5XQDF6755CQ6LS4/action/citation_signature","submit_replication":"https://pith.science/pith/YI26ZHKSVEG5XQDF6755CQ6LS4/action/replication_record"}},"created_at":"2026-07-22T00:22:59.280797+00:00","updated_at":"2026-07-22T00:22:59.280797+00:00"}