{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DZPZFGHGPX7R6YJMCG3CUCQJCP","short_pith_number":"pith:DZPZFGHG","canonical_record":{"source":{"id":"2403.14368","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T12:50:15Z","cross_cats_sorted":[],"title_canon_sha256":"0126e20c459552faae74a4df8eb3333f42526746ace88892b1e0556b1a338aad","abstract_canon_sha256":"42027fd1b3916da0c3da4bbc062b24adc74eddf962026ee6a0a72ff1c11bdb8d"},"schema_version":"1.0"},"canonical_sha256":"1e5f9298e67dff1f612c11b62a0a0913de439b72466dfc0b9618ab00cd8a78df","source":{"kind":"arxiv","id":"2403.14368","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14368","created_at":"2026-07-05T10:38:19Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14368v2","created_at":"2026-07-05T10:38:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14368","created_at":"2026-07-05T10:38:19Z"},{"alias_kind":"pith_short_12","alias_value":"DZPZFGHGPX7R","created_at":"2026-07-05T10:38:19Z"},{"alias_kind":"pith_short_16","alias_value":"DZPZFGHGPX7R6YJM","created_at":"2026-07-05T10:38:19Z"},{"alias_kind":"pith_short_8","alias_value":"DZPZFGHG","created_at":"2026-07-05T10:38:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DZPZFGHGPX7R6YJMCG3CUCQJCP","target":"record","payload":{"canonical_record":{"source":{"id":"2403.14368","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T12:50:15Z","cross_cats_sorted":[],"title_canon_sha256":"0126e20c459552faae74a4df8eb3333f42526746ace88892b1e0556b1a338aad","abstract_canon_sha256":"42027fd1b3916da0c3da4bbc062b24adc74eddf962026ee6a0a72ff1c11bdb8d"},"schema_version":"1.0"},"canonical_sha256":"1e5f9298e67dff1f612c11b62a0a0913de439b72466dfc0b9618ab00cd8a78df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:19.945977Z","signature_b64":"/rONck6BV2IP05108JiyAxhCxzn06c90cBwsP24FqE7Mx5IHTodesntlbnpVFmtYsf0+ZSe9+7gjnhsTgXESCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e5f9298e67dff1f612c11b62a0a0913de439b72466dfc0b9618ab00cd8a78df","last_reissued_at":"2026-07-05T10:38:19.945483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:19.945483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.14368","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":"2026-07-05T10:38:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X214dMoB5LZaEFfDwknhNnRaOubjfaixHB3q5dsiLvBfJsPNU+Y+g+P12pgWaiIVEvXHeQdOzWPkwqAO23NYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:17:27.025485Z"},"content_sha256":"4c7c4e1c8e0a33592f85350b60f772b29c238475b22d92dc91b2f1fe3b933b9b","schema_version":"1.0","event_id":"sha256:4c7c4e1c8e0a33592f85350b60f772b29c238475b22d92dc91b2f1fe3b933b9b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DZPZFGHGPX7R6YJMCG3CUCQJCP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aram Davtyan, Bj\\\"orn Ommer, Paolo Favaro, Sepehr Sameni","submitted_at":"2024-03-21T12:50:15Z","abstract_excerpt":"The field of video generation has expanded significantly in recent years, with controllable and compositional video generation garnering considerable interest. Most methods rely on leveraging annotations such as text, objects' bounding boxes, and motion cues, which require substantial human effort and thus limit their scalability. In contrast, we address the challenge of controllable and compositional video generation without any annotations by introducing a novel unsupervised approach. Our model is trained from scratch on a dataset of unannotated videos. At inference time, it can compose plau"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14368","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/2403.14368/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":"2026-07-05T10:38:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aPCe6h7XzKPDrGape2FpLvJjd2fTae36fYjorSelq2EdoLSeiB4aquPJdq4DVx3ZjIwwk0lJy6eaA+0dWdfXBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:17:27.026091Z"},"content_sha256":"b3aa02decba4f0c2941fdee7a1e4e0746ebb702a5d05891ac2c6d7647b02f090","schema_version":"1.0","event_id":"sha256:b3aa02decba4f0c2941fdee7a1e4e0746ebb702a5d05891ac2c6d7647b02f090"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DZPZFGHGPX7R6YJMCG3CUCQJCP/bundle.json","state_url":"https://pith.science/pith/DZPZFGHGPX7R6YJMCG3CUCQJCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DZPZFGHGPX7R6YJMCG3CUCQJCP/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":"2026-08-15T18:17:27Z","links":{"resolver":"https://pith.science/pith/DZPZFGHGPX7R6YJMCG3CUCQJCP","bundle":"https://pith.science/pith/DZPZFGHGPX7R6YJMCG3CUCQJCP/bundle.json","state":"https://pith.science/pith/DZPZFGHGPX7R6YJMCG3CUCQJCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DZPZFGHGPX7R6YJMCG3CUCQJCP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DZPZFGHGPX7R6YJMCG3CUCQJCP","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":"42027fd1b3916da0c3da4bbc062b24adc74eddf962026ee6a0a72ff1c11bdb8d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T12:50:15Z","title_canon_sha256":"0126e20c459552faae74a4df8eb3333f42526746ace88892b1e0556b1a338aad"},"schema_version":"1.0","source":{"id":"2403.14368","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14368","created_at":"2026-07-05T10:38:19Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14368v2","created_at":"2026-07-05T10:38:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14368","created_at":"2026-07-05T10:38:19Z"},{"alias_kind":"pith_short_12","alias_value":"DZPZFGHGPX7R","created_at":"2026-07-05T10:38:19Z"},{"alias_kind":"pith_short_16","alias_value":"DZPZFGHGPX7R6YJM","created_at":"2026-07-05T10:38:19Z"},{"alias_kind":"pith_short_8","alias_value":"DZPZFGHG","created_at":"2026-07-05T10:38:19Z"}],"graph_snapshots":[{"event_id":"sha256:b3aa02decba4f0c2941fdee7a1e4e0746ebb702a5d05891ac2c6d7647b02f090","target":"graph","created_at":"2026-07-05T10:38:19Z","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/2403.14368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The field of video generation has expanded significantly in recent years, with controllable and compositional video generation garnering considerable interest. Most methods rely on leveraging annotations such as text, objects' bounding boxes, and motion cues, which require substantial human effort and thus limit their scalability. In contrast, we address the challenge of controllable and compositional video generation without any annotations by introducing a novel unsupervised approach. Our model is trained from scratch on a dataset of unannotated videos. At inference time, it can compose plau","authors_text":"Aram Davtyan, Bj\\\"orn Ommer, Paolo Favaro, Sepehr Sameni","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T12:50:15Z","title":"CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14368","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":"sha256:4c7c4e1c8e0a33592f85350b60f772b29c238475b22d92dc91b2f1fe3b933b9b","target":"record","created_at":"2026-07-05T10:38:19Z","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":"42027fd1b3916da0c3da4bbc062b24adc74eddf962026ee6a0a72ff1c11bdb8d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T12:50:15Z","title_canon_sha256":"0126e20c459552faae74a4df8eb3333f42526746ace88892b1e0556b1a338aad"},"schema_version":"1.0","source":{"id":"2403.14368","kind":"arxiv","version":2}},"canonical_sha256":"1e5f9298e67dff1f612c11b62a0a0913de439b72466dfc0b9618ab00cd8a78df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e5f9298e67dff1f612c11b62a0a0913de439b72466dfc0b9618ab00cd8a78df","first_computed_at":"2026-07-05T10:38:19.945483Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:19.945483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/rONck6BV2IP05108JiyAxhCxzn06c90cBwsP24FqE7Mx5IHTodesntlbnpVFmtYsf0+ZSe9+7gjnhsTgXESCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:19.945977Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.14368","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c7c4e1c8e0a33592f85350b60f772b29c238475b22d92dc91b2f1fe3b933b9b","sha256:b3aa02decba4f0c2941fdee7a1e4e0746ebb702a5d05891ac2c6d7647b02f090"],"state_sha256":"e63f022a4583745a3bbb011dbca96204f21722d8d728d9d835032d253639758a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Co1AdaGo5/pGMQrX+56KOMMhSzZbgogjdAzw0QsiFUNAaxbtiAuXIULTZMkAOscvHx45Ib7H0ih4e7IUFNLBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T18:17:27.032494Z","bundle_sha256":"758181789126a8ed9ed9904f781b0adc5a52efc3fd17e0c83d9f603bd46d67ae"}}