{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HAIKJAYG3YF7AOJVXJI3S3VXQ4","short_pith_number":"pith:HAIKJAYG","canonical_record":{"source":{"id":"2412.04432","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T18:53:04Z","cross_cats_sorted":[],"title_canon_sha256":"0fe437eb28d84fe983fecef6a26f9f633b9869faf5b021d90c2ff5b063dc68ad","abstract_canon_sha256":"63146f2f5d0be3a0a2e2d61e98de41993d03a7444c05e16b848aba7613d0f31a"},"schema_version":"1.0"},"canonical_sha256":"3810a48306de0bf03935ba51b96eb7870164b39ee2d06b83c9214888f17a196e","source":{"kind":"arxiv","id":"2412.04432","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04432","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04432v1","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04432","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"pith_short_12","alias_value":"HAIKJAYG3YF7","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"pith_short_16","alias_value":"HAIKJAYG3YF7AOJV","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"pith_short_8","alias_value":"HAIKJAYG","created_at":"2026-07-05T09:45:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HAIKJAYG3YF7AOJVXJI3S3VXQ4","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04432","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T18:53:04Z","cross_cats_sorted":[],"title_canon_sha256":"0fe437eb28d84fe983fecef6a26f9f633b9869faf5b021d90c2ff5b063dc68ad","abstract_canon_sha256":"63146f2f5d0be3a0a2e2d61e98de41993d03a7444c05e16b848aba7613d0f31a"},"schema_version":"1.0"},"canonical_sha256":"3810a48306de0bf03935ba51b96eb7870164b39ee2d06b83c9214888f17a196e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:03.837470Z","signature_b64":"mr9nMPYiHGAX+Ty1pNsrpDUM1CPW7Rxvy7L9MEGX+dGMw6R+vtmo+gjVOVLsbq+lU9FxcK1ma9vXSeu6xJ2EAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3810a48306de0bf03935ba51b96eb7870164b39ee2d06b83c9214888f17a196e","last_reissued_at":"2026-07-05T09:45:03.837012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:03.837012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04432","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":"2026-07-05T09:45:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vymG/EPRPivOZvweyWG250SM2RHJiu0bIt99fboN/FYQ9UsQX2sQGg6aNbhpZsXoNq0Mrh7iNpjt9bi9asgBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:02:55.191009Z"},"content_sha256":"a594ff036d0c5eb54aeed6d993b8e038ea59ecc3d915ae819d5b2ab16a6dd5ae","schema_version":"1.0","event_id":"sha256:a594ff036d0c5eb54aeed6d993b8e038ea59ecc3d915ae819d5b2ab16a6dd5ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HAIKJAYG3YF7AOJVXJI3S3VXQ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ying Shan, Yixiao Ge, Yizhuo Li, Yuying Ge","submitted_at":"2024-12-05T18:53:04Z","abstract_excerpt":"In recent years, there has been a significant surge of interest in unifying image comprehension and generation within Large Language Models (LLMs). This growing interest has prompted us to explore extending this unification to videos. The core challenge lies in developing a versatile video tokenizer that captures both the spatial characteristics and temporal dynamics of videos to obtain representations for LLMs, and the representations can be further decoded into realistic video clips to enable video generation. In this work, we introduce Divot, a Diffusion-Powered Video Tokenizer, which lever"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04432","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/2412.04432/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":"2026-07-05T09:45:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FXl24I9/eBF4dPxwp9B+J00HvQ81dTvKWXhG6sTbsl5bz1qfY91zAJpHgisDfeJ7JJTZIb20V1JvwsqYOFQ2Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:02:55.191626Z"},"content_sha256":"ea96119c7fdd122aef1a43182373f15aadae5c9e75b26cf168f78144ae3ec449","schema_version":"1.0","event_id":"sha256:ea96119c7fdd122aef1a43182373f15aadae5c9e75b26cf168f78144ae3ec449"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HAIKJAYG3YF7AOJVXJI3S3VXQ4/bundle.json","state_url":"https://pith.science/pith/HAIKJAYG3YF7AOJVXJI3S3VXQ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HAIKJAYG3YF7AOJVXJI3S3VXQ4/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":"2026-08-21T17:02:55Z","links":{"resolver":"https://pith.science/pith/HAIKJAYG3YF7AOJVXJI3S3VXQ4","bundle":"https://pith.science/pith/HAIKJAYG3YF7AOJVXJI3S3VXQ4/bundle.json","state":"https://pith.science/pith/HAIKJAYG3YF7AOJVXJI3S3VXQ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HAIKJAYG3YF7AOJVXJI3S3VXQ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HAIKJAYG3YF7AOJVXJI3S3VXQ4","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":"63146f2f5d0be3a0a2e2d61e98de41993d03a7444c05e16b848aba7613d0f31a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T18:53:04Z","title_canon_sha256":"0fe437eb28d84fe983fecef6a26f9f633b9869faf5b021d90c2ff5b063dc68ad"},"schema_version":"1.0","source":{"id":"2412.04432","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04432","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04432v1","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04432","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"pith_short_12","alias_value":"HAIKJAYG3YF7","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"pith_short_16","alias_value":"HAIKJAYG3YF7AOJV","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"pith_short_8","alias_value":"HAIKJAYG","created_at":"2026-07-05T09:45:03Z"}],"graph_snapshots":[{"event_id":"sha256:ea96119c7fdd122aef1a43182373f15aadae5c9e75b26cf168f78144ae3ec449","target":"graph","created_at":"2026-07-05T09:45:03Z","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/2412.04432/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, there has been a significant surge of interest in unifying image comprehension and generation within Large Language Models (LLMs). This growing interest has prompted us to explore extending this unification to videos. The core challenge lies in developing a versatile video tokenizer that captures both the spatial characteristics and temporal dynamics of videos to obtain representations for LLMs, and the representations can be further decoded into realistic video clips to enable video generation. In this work, we introduce Divot, a Diffusion-Powered Video Tokenizer, which lever","authors_text":"Ying Shan, Yixiao Ge, Yizhuo Li, Yuying Ge","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T18:53:04Z","title":"Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04432","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:a594ff036d0c5eb54aeed6d993b8e038ea59ecc3d915ae819d5b2ab16a6dd5ae","target":"record","created_at":"2026-07-05T09:45:03Z","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":"63146f2f5d0be3a0a2e2d61e98de41993d03a7444c05e16b848aba7613d0f31a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T18:53:04Z","title_canon_sha256":"0fe437eb28d84fe983fecef6a26f9f633b9869faf5b021d90c2ff5b063dc68ad"},"schema_version":"1.0","source":{"id":"2412.04432","kind":"arxiv","version":1}},"canonical_sha256":"3810a48306de0bf03935ba51b96eb7870164b39ee2d06b83c9214888f17a196e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3810a48306de0bf03935ba51b96eb7870164b39ee2d06b83c9214888f17a196e","first_computed_at":"2026-07-05T09:45:03.837012Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:03.837012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mr9nMPYiHGAX+Ty1pNsrpDUM1CPW7Rxvy7L9MEGX+dGMw6R+vtmo+gjVOVLsbq+lU9FxcK1ma9vXSeu6xJ2EAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:03.837470Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04432","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a594ff036d0c5eb54aeed6d993b8e038ea59ecc3d915ae819d5b2ab16a6dd5ae","sha256:ea96119c7fdd122aef1a43182373f15aadae5c9e75b26cf168f78144ae3ec449"],"state_sha256":"93a495073a1270d9c9d4546ae52d720a0c64c7a4642b2aa45dc2fc81bb071be7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bikdoz0M5eOqBqvnU2l/EztLuwYv6T3DwV1VQwrsvZ8htkB9L6IndlYWNXTVOjGHQMgZk0VafT2UHlAnNgjoBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T17:02:55.195614Z","bundle_sha256":"1316a42e56805b93943a6bfcc869a5ad1a754cb9a1f0b9927cccc3f950ef0f60"}}