{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DZTSDMW345FDSC476OA3MBEQPN","short_pith_number":"pith:DZTSDMW3","canonical_record":{"source":{"id":"2303.03684","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-07T06:54:48Z","cross_cats_sorted":[],"title_canon_sha256":"a1d908557709ef7e125d640c0ce99c3c22aa8362ea0f63680040d215e774710a","abstract_canon_sha256":"aa839f7e4ef64c3eeb83eefaf3ed3c22437af7070425c5915edafdab633842a6"},"schema_version":"1.0"},"canonical_sha256":"1e6721b2dbe74a390b9ff381b604907b475fbfbddacd4a684851ab2219679bb4","source":{"kind":"arxiv","id":"2303.03684","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.03684","created_at":"2026-07-05T05:51:45Z"},{"alias_kind":"arxiv_version","alias_value":"2303.03684v2","created_at":"2026-07-05T05:51:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03684","created_at":"2026-07-05T05:51:45Z"},{"alias_kind":"pith_short_12","alias_value":"DZTSDMW345FD","created_at":"2026-07-05T05:51:45Z"},{"alias_kind":"pith_short_16","alias_value":"DZTSDMW345FDSC47","created_at":"2026-07-05T05:51:45Z"},{"alias_kind":"pith_short_8","alias_value":"DZTSDMW3","created_at":"2026-07-05T05:51:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DZTSDMW345FDSC476OA3MBEQPN","target":"record","payload":{"canonical_record":{"source":{"id":"2303.03684","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-07T06:54:48Z","cross_cats_sorted":[],"title_canon_sha256":"a1d908557709ef7e125d640c0ce99c3c22aa8362ea0f63680040d215e774710a","abstract_canon_sha256":"aa839f7e4ef64c3eeb83eefaf3ed3c22437af7070425c5915edafdab633842a6"},"schema_version":"1.0"},"canonical_sha256":"1e6721b2dbe74a390b9ff381b604907b475fbfbddacd4a684851ab2219679bb4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:45.339129Z","signature_b64":"5AZ1SvoVjasKS6kWpXrkjXVSBjRIppbIsZpSppiMBoHTsSBFdtoJtnoXn2IR5mukpBf5MIGsnu0bSfZfTBDeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e6721b2dbe74a390b9ff381b604907b475fbfbddacd4a684851ab2219679bb4","last_reissued_at":"2026-07-05T05:51:45.338745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:45.338745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.03684","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:51:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V6PZGUUMv/59oAxkj4Rwyv+1bc/ca7KQsbTIN3/o2J87bBTdVbS25cMV8CqGSMdKqgg6ehWjJw7YgrG4boLQCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:46:28.729576Z"},"content_sha256":"27766439fd407dbc5a85a4c196e9377f2845e06b3156521d33b87d43e801cc9f","schema_version":"1.0","event_id":"sha256:27766439fd407dbc5a85a4c196e9377f2845e06b3156521d33b87d43e801cc9f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DZTSDMW345FDSC476OA3MBEQPN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MOSO: Decomposing MOtion, Scene and Object for Video Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Liu, Mingzhen Sun, Weining Wang, Xinxin Zhu","submitted_at":"2023-03-07T06:54:48Z","abstract_excerpt":"Motion, scene and object are three primary visual components of a video. In particular, objects represent the foreground, scenes represent the background, and motion traces their dynamics. Based on this insight, we propose a two-stage MOtion, Scene and Object decomposition framework (MOSO) for video prediction, consisting of MOSO-VQVAE and MOSO-Transformer. In the first stage, MOSO-VQVAE decomposes a previous video clip into the motion, scene and object components, and represents them as distinct groups of discrete tokens. Then, in the second stage, MOSO-Transformer predicts the object and sce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03684","kind":"arxiv","version":2},"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/2303.03684/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":"2026-07-05T05:51:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CButFGf9fmt0x78Wt0gt2v3ibH6C6snh/InzA0NmRsF6BX9Yb2ZzHZNrYtA5+rf3yRMyKQDU5gQuzjHZWclbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:46:28.730074Z"},"content_sha256":"06192831f67af8454560331e20ca42455e116b67e2255e101c674fd328c37dae","schema_version":"1.0","event_id":"sha256:06192831f67af8454560331e20ca42455e116b67e2255e101c674fd328c37dae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DZTSDMW345FDSC476OA3MBEQPN/bundle.json","state_url":"https://pith.science/pith/DZTSDMW345FDSC476OA3MBEQPN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DZTSDMW345FDSC476OA3MBEQPN/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":"2026-08-11T15:46:28Z","links":{"resolver":"https://pith.science/pith/DZTSDMW345FDSC476OA3MBEQPN","bundle":"https://pith.science/pith/DZTSDMW345FDSC476OA3MBEQPN/bundle.json","state":"https://pith.science/pith/DZTSDMW345FDSC476OA3MBEQPN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DZTSDMW345FDSC476OA3MBEQPN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DZTSDMW345FDSC476OA3MBEQPN","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":"aa839f7e4ef64c3eeb83eefaf3ed3c22437af7070425c5915edafdab633842a6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-07T06:54:48Z","title_canon_sha256":"a1d908557709ef7e125d640c0ce99c3c22aa8362ea0f63680040d215e774710a"},"schema_version":"1.0","source":{"id":"2303.03684","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.03684","created_at":"2026-07-05T05:51:45Z"},{"alias_kind":"arxiv_version","alias_value":"2303.03684v2","created_at":"2026-07-05T05:51:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03684","created_at":"2026-07-05T05:51:45Z"},{"alias_kind":"pith_short_12","alias_value":"DZTSDMW345FD","created_at":"2026-07-05T05:51:45Z"},{"alias_kind":"pith_short_16","alias_value":"DZTSDMW345FDSC47","created_at":"2026-07-05T05:51:45Z"},{"alias_kind":"pith_short_8","alias_value":"DZTSDMW3","created_at":"2026-07-05T05:51:45Z"}],"graph_snapshots":[{"event_id":"sha256:06192831f67af8454560331e20ca42455e116b67e2255e101c674fd328c37dae","target":"graph","created_at":"2026-07-05T05:51:45Z","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/2303.03684/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motion, scene and object are three primary visual components of a video. In particular, objects represent the foreground, scenes represent the background, and motion traces their dynamics. Based on this insight, we propose a two-stage MOtion, Scene and Object decomposition framework (MOSO) for video prediction, consisting of MOSO-VQVAE and MOSO-Transformer. In the first stage, MOSO-VQVAE decomposes a previous video clip into the motion, scene and object components, and represents them as distinct groups of discrete tokens. Then, in the second stage, MOSO-Transformer predicts the object and sce","authors_text":"Jing Liu, Mingzhen Sun, Weining Wang, Xinxin Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-07T06:54:48Z","title":"MOSO: Decomposing MOtion, Scene and Object for Video Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03684","kind":"arxiv","version":2},"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":"sha256:27766439fd407dbc5a85a4c196e9377f2845e06b3156521d33b87d43e801cc9f","target":"record","created_at":"2026-07-05T05:51:45Z","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":"aa839f7e4ef64c3eeb83eefaf3ed3c22437af7070425c5915edafdab633842a6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-07T06:54:48Z","title_canon_sha256":"a1d908557709ef7e125d640c0ce99c3c22aa8362ea0f63680040d215e774710a"},"schema_version":"1.0","source":{"id":"2303.03684","kind":"arxiv","version":2}},"canonical_sha256":"1e6721b2dbe74a390b9ff381b604907b475fbfbddacd4a684851ab2219679bb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e6721b2dbe74a390b9ff381b604907b475fbfbddacd4a684851ab2219679bb4","first_computed_at":"2026-07-05T05:51:45.338745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:51:45.338745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5AZ1SvoVjasKS6kWpXrkjXVSBjRIppbIsZpSppiMBoHTsSBFdtoJtnoXn2IR5mukpBf5MIGsnu0bSfZfTBDeCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:51:45.339129Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.03684","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27766439fd407dbc5a85a4c196e9377f2845e06b3156521d33b87d43e801cc9f","sha256:06192831f67af8454560331e20ca42455e116b67e2255e101c674fd328c37dae"],"state_sha256":"12d82f5af24ec77ff5a2fe8704cc997b6d5e0311057ca64bba86badf77c6b6f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DyxvJwkGJwnzu2b0S+LKR7xnP27LYUz+eeQ3UO3pQhLMwyQ58tcnLqqFHmhPZLJ6+37OSILrDBKNqkRbqkRTAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T15:46:28.735267Z","bundle_sha256":"a9cf59759d5b69ee327c36a00de68c640e7b53c7b91cb9856373458b31501868"}}