{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IOO2J7GWYQPU26JIXSKN2SZRNI","short_pith_number":"pith:IOO2J7GW","canonical_record":{"source":{"id":"2503.23368","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-30T09:03:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c6aecad14a08dec0611180806685fa85a9ebf6c8c508b90f3b0b1a29dc7f739a","abstract_canon_sha256":"bbdf2e938eec70eb11509b048dbd84ea8aa019370d94729ade3e560757ed2d53"},"schema_version":"1.0"},"canonical_sha256":"439da4fcd6c41f4d7928bc94dd4b316a041b9f9dc02933026a864aa1e3c12f56","source":{"kind":"arxiv","id":"2503.23368","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23368","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23368v3","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23368","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"IOO2J7GWYQPU","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"pith_short_16","alias_value":"IOO2J7GWYQPU26JI","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"pith_short_8","alias_value":"IOO2J7GW","created_at":"2026-07-05T10:44:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IOO2J7GWYQPU26JIXSKN2SZRNI","target":"record","payload":{"canonical_record":{"source":{"id":"2503.23368","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-30T09:03:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c6aecad14a08dec0611180806685fa85a9ebf6c8c508b90f3b0b1a29dc7f739a","abstract_canon_sha256":"bbdf2e938eec70eb11509b048dbd84ea8aa019370d94729ade3e560757ed2d53"},"schema_version":"1.0"},"canonical_sha256":"439da4fcd6c41f4d7928bc94dd4b316a041b9f9dc02933026a864aa1e3c12f56","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:23.455782Z","signature_b64":"y1fySgxBXy0HlxQ2yKGT7/bt6TQGZLRoGbqD3N7gJYOh39Iec4AZQnwJbUWx/3vA8PKwfsHrrlY5mqfMG+CWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"439da4fcd6c41f4d7928bc94dd4b316a041b9f9dc02933026a864aa1e3c12f56","last_reissued_at":"2026-07-05T10:44:23.455299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:23.455299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.23368","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hZVvvxC8JVVmFQDBEz+sYC0lM5AOsbYXsyxJsKeQd+C9tlChgLouCDtRpaM9OnAct4J2KKHdAwVZp5nFo+JrAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:28:25.109726Z"},"content_sha256":"db7b2271923758566ebfe665ef73c99da167710838c4ce3f7988bf1fec6590ca","schema_version":"1.0","event_id":"sha256:db7b2271923758566ebfe665ef73c99da167710838c4ce3f7988bf1fec6590ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IOO2J7GWYQPU26JIXSKN2SZRNI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baolu Li, Huchuan Lu, Jianfei Cai, Lei Bai, Liqian Ma, Tien-Tsin Wong, Xindi Yang, Xu Jia, Yiming Zhang, Zhenfei Yin, Zhiyong Wang","submitted_at":"2025-03-30T09:03:09Z","abstract_excerpt":"Video diffusion models (VDMs) have advanced significantly in recent years, enabling the generation of highly realistic videos and drawing the attention of the community in their potential as world simulators. However, despite their capabilities, VDMs often fail to produce physically plausible videos due to an inherent lack of understanding of physics, resulting in incorrect dynamics and event sequences. To address this limitation, we propose a novel two-stage image-to-video generation framework that explicitly incorporates physics with vision and language informed physical prior. In the first "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23368","kind":"arxiv","version":3},"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/2503.23368/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VKM7iXC1d8lwxgK1x/58JGbe3JOQXSL7CtQ9r/OU32fx6aLCzlPcyhTm0B6RRSjQKzObv7lCT4Mr/Ih2/+FyBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:28:25.110407Z"},"content_sha256":"5c443811f8d999465aad3806936cd2b2f6b1f3116cb8f7ca29c83d3cc98a9882","schema_version":"1.0","event_id":"sha256:5c443811f8d999465aad3806936cd2b2f6b1f3116cb8f7ca29c83d3cc98a9882"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IOO2J7GWYQPU26JIXSKN2SZRNI/bundle.json","state_url":"https://pith.science/pith/IOO2J7GWYQPU26JIXSKN2SZRNI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IOO2J7GWYQPU26JIXSKN2SZRNI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T18:28:25Z","links":{"resolver":"https://pith.science/pith/IOO2J7GWYQPU26JIXSKN2SZRNI","bundle":"https://pith.science/pith/IOO2J7GWYQPU26JIXSKN2SZRNI/bundle.json","state":"https://pith.science/pith/IOO2J7GWYQPU26JIXSKN2SZRNI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IOO2J7GWYQPU26JIXSKN2SZRNI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IOO2J7GWYQPU26JIXSKN2SZRNI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bbdf2e938eec70eb11509b048dbd84ea8aa019370d94729ade3e560757ed2d53","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-30T09:03:09Z","title_canon_sha256":"c6aecad14a08dec0611180806685fa85a9ebf6c8c508b90f3b0b1a29dc7f739a"},"schema_version":"1.0","source":{"id":"2503.23368","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23368","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23368v3","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23368","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"IOO2J7GWYQPU","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"pith_short_16","alias_value":"IOO2J7GWYQPU26JI","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"pith_short_8","alias_value":"IOO2J7GW","created_at":"2026-07-05T10:44:23Z"}],"graph_snapshots":[{"event_id":"sha256:5c443811f8d999465aad3806936cd2b2f6b1f3116cb8f7ca29c83d3cc98a9882","target":"graph","created_at":"2026-07-05T10:44:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.23368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video diffusion models (VDMs) have advanced significantly in recent years, enabling the generation of highly realistic videos and drawing the attention of the community in their potential as world simulators. However, despite their capabilities, VDMs often fail to produce physically plausible videos due to an inherent lack of understanding of physics, resulting in incorrect dynamics and event sequences. To address this limitation, we propose a novel two-stage image-to-video generation framework that explicitly incorporates physics with vision and language informed physical prior. In the first ","authors_text":"Baolu Li, Huchuan Lu, Jianfei Cai, Lei Bai, Liqian Ma, Tien-Tsin Wong, Xindi Yang, Xu Jia, Yiming Zhang, Zhenfei Yin, Zhiyong Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-30T09:03:09Z","title":"VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23368","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:db7b2271923758566ebfe665ef73c99da167710838c4ce3f7988bf1fec6590ca","target":"record","created_at":"2026-07-05T10:44:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bbdf2e938eec70eb11509b048dbd84ea8aa019370d94729ade3e560757ed2d53","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-30T09:03:09Z","title_canon_sha256":"c6aecad14a08dec0611180806685fa85a9ebf6c8c508b90f3b0b1a29dc7f739a"},"schema_version":"1.0","source":{"id":"2503.23368","kind":"arxiv","version":3}},"canonical_sha256":"439da4fcd6c41f4d7928bc94dd4b316a041b9f9dc02933026a864aa1e3c12f56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"439da4fcd6c41f4d7928bc94dd4b316a041b9f9dc02933026a864aa1e3c12f56","first_computed_at":"2026-07-05T10:44:23.455299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:23.455299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y1fySgxBXy0HlxQ2yKGT7/bt6TQGZLRoGbqD3N7gJYOh39Iec4AZQnwJbUWx/3vA8PKwfsHrrlY5mqfMG+CWDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:23.455782Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.23368","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db7b2271923758566ebfe665ef73c99da167710838c4ce3f7988bf1fec6590ca","sha256:5c443811f8d999465aad3806936cd2b2f6b1f3116cb8f7ca29c83d3cc98a9882"],"state_sha256":"4eacdfa080db2a905b210ec2d4820529068e6a0c9466032c5a6fa7fc9e329e75"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"amV0ir7K8jS/U5MVYQBBbg2hTVBDOOy2jsE4DC11PAgVIQdS+VG/ccT1kZjOSsQnbsI/+22Q3wiIyy7u7xvkCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:28:25.115885Z","bundle_sha256":"c43a4df8863f435271cd0b841f6fd18561d97ecb8a80fcdf2c137726a5f4603a"}}