{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:EFYJR63LYOJSFXZBHR5HYV7JAM","short_pith_number":"pith:EFYJR63L","canonical_record":{"source":{"id":"2107.09240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-20T03:08:39Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"524c01cad764c24b7c9393d8ab189a21afc8e03bdec694d22e5166443644a92b","abstract_canon_sha256":"21a50a02fe9db862e63cc3229a779768ab4c8a4c56321475a520cb13149a00ab"},"schema_version":"1.0"},"canonical_sha256":"217098fb6bc39322df213c7a7c57e9030de2799d579b9a8026676e34149c24c6","source":{"kind":"arxiv","id":"2107.09240","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.09240","created_at":"2026-07-05T02:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"2107.09240v1","created_at":"2026-07-05T02:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09240","created_at":"2026-07-05T02:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"EFYJR63LYOJS","created_at":"2026-07-05T02:59:27Z"},{"alias_kind":"pith_short_16","alias_value":"EFYJR63LYOJSFXZB","created_at":"2026-07-05T02:59:27Z"},{"alias_kind":"pith_short_8","alias_value":"EFYJR63L","created_at":"2026-07-05T02:59:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:EFYJR63LYOJSFXZBHR5HYV7JAM","target":"record","payload":{"canonical_record":{"source":{"id":"2107.09240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-20T03:08:39Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"524c01cad764c24b7c9393d8ab189a21afc8e03bdec694d22e5166443644a92b","abstract_canon_sha256":"21a50a02fe9db862e63cc3229a779768ab4c8a4c56321475a520cb13149a00ab"},"schema_version":"1.0"},"canonical_sha256":"217098fb6bc39322df213c7a7c57e9030de2799d579b9a8026676e34149c24c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:27.729058Z","signature_b64":"uJoGlVDtqnzTy3GdB0VBwI0ssu2ccxi7NLQz5B49BqRgm9MzdBSK2osoN8+7xvTpzxPDaU7UFvCWjNi7ZkU0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"217098fb6bc39322df213c7a7c57e9030de2799d579b9a8026676e34149c24c6","last_reissued_at":"2026-07-05T02:59:27.728623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:27.728623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.09240","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:59:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9P/ZKi7z19ZhFUdq5taru/kM4KIP8og5mkcwcvSgilDKzgj7rXeudl1THBXnauxbmTu1+mtR/o8GJPy8xDLYBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T19:17:13.540694Z"},"content_sha256":"03c8a7a6daf30f8f95257cf1e084e0123d326556544dbe3da15ac45b38adc52b","schema_version":"1.0","event_id":"sha256:03c8a7a6daf30f8f95257cf1e084e0123d326556544dbe3da15ac45b38adc52b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:EFYJR63LYOJSFXZBHR5HYV7JAM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Video Transformer: Can Objects be the Words?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Jaesik Yoon, Sungjin Ahn, Yi-Fu Wu","submitted_at":"2021-07-20T03:08:39Z","abstract_excerpt":"Transformers have been successful for many natural language processing tasks. However, applying transformers to the video domain for tasks such as long-term video generation and scene understanding has remained elusive due to the high computational complexity and the lack of natural tokenization. In this paper, we propose the Object-Centric Video Transformer (OCVT) which utilizes an object-centric approach for decomposing scenes into tokens suitable for use in a generative video transformer. By factoring the video into objects, our fully unsupervised model is able to learn complex spatio-tempo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09240","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/2107.09240/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":"2026-07-05T02:59:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FbokDOkEPKCH0L7BrjZKjJ2iUYypn7odlT/mb6+nFQ+mLNYMSwk7P0FeL8QhzD/efYIaP3nd2aV5clHSCPZoDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T19:17:13.541075Z"},"content_sha256":"5df3db5df13076e9a5b9406468bb9e83c94669343e2cc60d1aa9813cbcede7c0","schema_version":"1.0","event_id":"sha256:5df3db5df13076e9a5b9406468bb9e83c94669343e2cc60d1aa9813cbcede7c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EFYJR63LYOJSFXZBHR5HYV7JAM/bundle.json","state_url":"https://pith.science/pith/EFYJR63LYOJSFXZBHR5HYV7JAM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EFYJR63LYOJSFXZBHR5HYV7JAM/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":"2026-07-19T19:17:13Z","links":{"resolver":"https://pith.science/pith/EFYJR63LYOJSFXZBHR5HYV7JAM","bundle":"https://pith.science/pith/EFYJR63LYOJSFXZBHR5HYV7JAM/bundle.json","state":"https://pith.science/pith/EFYJR63LYOJSFXZBHR5HYV7JAM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EFYJR63LYOJSFXZBHR5HYV7JAM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EFYJR63LYOJSFXZBHR5HYV7JAM","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":"21a50a02fe9db862e63cc3229a779768ab4c8a4c56321475a520cb13149a00ab","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-20T03:08:39Z","title_canon_sha256":"524c01cad764c24b7c9393d8ab189a21afc8e03bdec694d22e5166443644a92b"},"schema_version":"1.0","source":{"id":"2107.09240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.09240","created_at":"2026-07-05T02:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"2107.09240v1","created_at":"2026-07-05T02:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09240","created_at":"2026-07-05T02:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"EFYJR63LYOJS","created_at":"2026-07-05T02:59:27Z"},{"alias_kind":"pith_short_16","alias_value":"EFYJR63LYOJSFXZB","created_at":"2026-07-05T02:59:27Z"},{"alias_kind":"pith_short_8","alias_value":"EFYJR63L","created_at":"2026-07-05T02:59:27Z"}],"graph_snapshots":[{"event_id":"sha256:5df3db5df13076e9a5b9406468bb9e83c94669343e2cc60d1aa9813cbcede7c0","target":"graph","created_at":"2026-07-05T02:59:27Z","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/2107.09240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformers have been successful for many natural language processing tasks. However, applying transformers to the video domain for tasks such as long-term video generation and scene understanding has remained elusive due to the high computational complexity and the lack of natural tokenization. In this paper, we propose the Object-Centric Video Transformer (OCVT) which utilizes an object-centric approach for decomposing scenes into tokens suitable for use in a generative video transformer. By factoring the video into objects, our fully unsupervised model is able to learn complex spatio-tempo","authors_text":"Jaesik Yoon, Sungjin Ahn, Yi-Fu Wu","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-20T03:08:39Z","title":"Generative Video Transformer: Can Objects be the Words?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09240","kind":"arxiv","version":1},"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":"sha256:03c8a7a6daf30f8f95257cf1e084e0123d326556544dbe3da15ac45b38adc52b","target":"record","created_at":"2026-07-05T02:59:27Z","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":"21a50a02fe9db862e63cc3229a779768ab4c8a4c56321475a520cb13149a00ab","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-20T03:08:39Z","title_canon_sha256":"524c01cad764c24b7c9393d8ab189a21afc8e03bdec694d22e5166443644a92b"},"schema_version":"1.0","source":{"id":"2107.09240","kind":"arxiv","version":1}},"canonical_sha256":"217098fb6bc39322df213c7a7c57e9030de2799d579b9a8026676e34149c24c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"217098fb6bc39322df213c7a7c57e9030de2799d579b9a8026676e34149c24c6","first_computed_at":"2026-07-05T02:59:27.728623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:59:27.728623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uJoGlVDtqnzTy3GdB0VBwI0ssu2ccxi7NLQz5B49BqRgm9MzdBSK2osoN8+7xvTpzxPDaU7UFvCWjNi7ZkU0CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:59:27.729058Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.09240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03c8a7a6daf30f8f95257cf1e084e0123d326556544dbe3da15ac45b38adc52b","sha256:5df3db5df13076e9a5b9406468bb9e83c94669343e2cc60d1aa9813cbcede7c0"],"state_sha256":"83d37e3a48cc3216bc0334050a6d5795aeb79d204cdc9d6a59fea6f816545345"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SSckmaW5mfYZepFpmJ6LO9J5NIOjcGTKd8hYfx4rf2aaQejpQNXKnNslkRI1l4JhFJMtCSOtFD45XUwsFf9yCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T19:17:13.543853Z","bundle_sha256":"b7cf753c1b6d00254bf5235b4fc4f11d375f09d9985d54a440186d23d8abaa85"}}