{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YAW2XI3EWVCPCGMG5II2RXAUKG","short_pith_number":"pith:YAW2XI3E","canonical_record":{"source":{"id":"2206.04003","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-08T16:29:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"072bdd56f46f3df4bdeafe1cf5bad7a1ef246965176e1c913c84f56d0887d518","abstract_canon_sha256":"d2b850f17514ceb00749a9401c49e004577d899d6ceb423ed031a2aaf5dd8386"},"schema_version":"1.0"},"canonical_sha256":"c02daba364b544f11986ea11a8dc1451a97f01534f62d065f50fd0ae5325cb28","source":{"kind":"arxiv","id":"2206.04003","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.04003","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"arxiv_version","alias_value":"2206.04003v2","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04003","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_12","alias_value":"YAW2XI3EWVCP","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_16","alias_value":"YAW2XI3EWVCPCGMG","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_8","alias_value":"YAW2XI3E","created_at":"2026-07-05T04:33:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YAW2XI3EWVCPCGMG5II2RXAUKG","target":"record","payload":{"canonical_record":{"source":{"id":"2206.04003","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-08T16:29:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"072bdd56f46f3df4bdeafe1cf5bad7a1ef246965176e1c913c84f56d0887d518","abstract_canon_sha256":"d2b850f17514ceb00749a9401c49e004577d899d6ceb423ed031a2aaf5dd8386"},"schema_version":"1.0"},"canonical_sha256":"c02daba364b544f11986ea11a8dc1451a97f01534f62d065f50fd0ae5325cb28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:00.692221Z","signature_b64":"lojSKzxGZ8EOK7b2HNFuZZa2r8qbDKCsTGkkLBtf9dttEY6M0f5Ar0e14KMQmaBI+sobljX3bgyMa3Rqk6CzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c02daba364b544f11986ea11a8dc1451a97f01534f62d065f50fd0ae5325cb28","last_reissued_at":"2026-07-05T04:33:00.691223Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:00.691223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.04003","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":"2026-07-05T04:33:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vw4P8CtnfAmacZmKUxDGwfVxnGUVe7xRVKOGfeLosl8/Z5SIWvC1A+cYMb9IF7JfXURKGyJUNVPeu6Su2OhGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:04:20.149280Z"},"content_sha256":"e14b81215e6317adcace01f3959c40ce26967264695a580d2b06b2cb79b7ed7f","schema_version":"1.0","event_id":"sha256:e14b81215e6317adcace01f3959c40ce26967264695a580d2b06b2cb79b7ed7f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YAW2XI3EWVCPCGMG5II2RXAUKG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Patch-based Object-centric Transformers for Efficient Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Pieter Abbeel, Ryo Okumura, Stephen James, Wilson Yan","submitted_at":"2022-06-08T16:29:59Z","abstract_excerpt":"In this work, we present Patch-based Object-centric Video Transformer (POVT), a novel region-based video generation architecture that leverages object-centric information to efficiently model temporal dynamics in videos. We build upon prior work in video prediction via an autoregressive transformer over the discrete latent space of compressed videos, with an added modification to model object-centric information via bounding boxes. Due to better compressibility of object-centric representations, we can improve training efficiency by allowing the model to only access object information for long"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04003","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/2206.04003/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":"2026-07-05T04:33:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FaV94bQDCZqdMBsd+1l2c2uRWvOZy18ToCHQqOiTUASeUwJKzylXqeMXUCQyBxlr2QHL7Gm4rvOko+a3dDm5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:04:20.149874Z"},"content_sha256":"dfdb713b0beeaee652aa7b752e0d81c32b327a3a1ac2db493fbf50358635e3ad","schema_version":"1.0","event_id":"sha256:dfdb713b0beeaee652aa7b752e0d81c32b327a3a1ac2db493fbf50358635e3ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YAW2XI3EWVCPCGMG5II2RXAUKG/bundle.json","state_url":"https://pith.science/pith/YAW2XI3EWVCPCGMG5II2RXAUKG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YAW2XI3EWVCPCGMG5II2RXAUKG/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":"2026-08-18T04:04:20Z","links":{"resolver":"https://pith.science/pith/YAW2XI3EWVCPCGMG5II2RXAUKG","bundle":"https://pith.science/pith/YAW2XI3EWVCPCGMG5II2RXAUKG/bundle.json","state":"https://pith.science/pith/YAW2XI3EWVCPCGMG5II2RXAUKG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YAW2XI3EWVCPCGMG5II2RXAUKG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YAW2XI3EWVCPCGMG5II2RXAUKG","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":"d2b850f17514ceb00749a9401c49e004577d899d6ceb423ed031a2aaf5dd8386","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-08T16:29:59Z","title_canon_sha256":"072bdd56f46f3df4bdeafe1cf5bad7a1ef246965176e1c913c84f56d0887d518"},"schema_version":"1.0","source":{"id":"2206.04003","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.04003","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"arxiv_version","alias_value":"2206.04003v2","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04003","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_12","alias_value":"YAW2XI3EWVCP","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_16","alias_value":"YAW2XI3EWVCPCGMG","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_8","alias_value":"YAW2XI3E","created_at":"2026-07-05T04:33:00Z"}],"graph_snapshots":[{"event_id":"sha256:dfdb713b0beeaee652aa7b752e0d81c32b327a3a1ac2db493fbf50358635e3ad","target":"graph","created_at":"2026-07-05T04:33:00Z","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/2206.04003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we present Patch-based Object-centric Video Transformer (POVT), a novel region-based video generation architecture that leverages object-centric information to efficiently model temporal dynamics in videos. We build upon prior work in video prediction via an autoregressive transformer over the discrete latent space of compressed videos, with an added modification to model object-centric information via bounding boxes. Due to better compressibility of object-centric representations, we can improve training efficiency by allowing the model to only access object information for long","authors_text":"Pieter Abbeel, Ryo Okumura, Stephen James, Wilson Yan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-08T16:29:59Z","title":"Patch-based Object-centric Transformers for Efficient Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04003","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:e14b81215e6317adcace01f3959c40ce26967264695a580d2b06b2cb79b7ed7f","target":"record","created_at":"2026-07-05T04:33:00Z","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":"d2b850f17514ceb00749a9401c49e004577d899d6ceb423ed031a2aaf5dd8386","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-08T16:29:59Z","title_canon_sha256":"072bdd56f46f3df4bdeafe1cf5bad7a1ef246965176e1c913c84f56d0887d518"},"schema_version":"1.0","source":{"id":"2206.04003","kind":"arxiv","version":2}},"canonical_sha256":"c02daba364b544f11986ea11a8dc1451a97f01534f62d065f50fd0ae5325cb28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c02daba364b544f11986ea11a8dc1451a97f01534f62d065f50fd0ae5325cb28","first_computed_at":"2026-07-05T04:33:00.691223Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:33:00.691223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lojSKzxGZ8EOK7b2HNFuZZa2r8qbDKCsTGkkLBtf9dttEY6M0f5Ar0e14KMQmaBI+sobljX3bgyMa3Rqk6CzDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:33:00.692221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.04003","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e14b81215e6317adcace01f3959c40ce26967264695a580d2b06b2cb79b7ed7f","sha256:dfdb713b0beeaee652aa7b752e0d81c32b327a3a1ac2db493fbf50358635e3ad"],"state_sha256":"1eb61c304fec6bcb20c74b227fea2c00a82f22aa119377ecec000c59f1693cb7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hsiGfUvlAU8UG2YB4FewU8G4VKpcfa/m533qu3MZK8zF9kPUsDZHQbkpoFmzaPuBzwxWbeEwh9LjVtM79GgTAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T04:04:20.154853Z","bundle_sha256":"e5c94d912969e6499ee2b60f80e5e0449af636b65111653332b8144f31eb4a88"}}