{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N34MAQ6UFFAHZQV6LQB2JQFRYF","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":"695366520e789a2eebb984fb5d15d901053d7712e863b69d5d1c4f867bd2cc36","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:26Z","title_canon_sha256":"85ed6b8b174de2ed70cc47831dcd3da4ff4bd517fa3572a78271d4ad73a9501b"},"schema_version":"1.0","source":{"id":"2406.09399","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09399","created_at":"2026-07-05T08:31:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09399v1","created_at":"2026-07-05T08:31:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09399","created_at":"2026-07-05T08:31:32Z"},{"alias_kind":"pith_short_12","alias_value":"N34MAQ6UFFAH","created_at":"2026-07-05T08:31:32Z"},{"alias_kind":"pith_short_16","alias_value":"N34MAQ6UFFAHZQV6","created_at":"2026-07-05T08:31:32Z"},{"alias_kind":"pith_short_8","alias_value":"N34MAQ6U","created_at":"2026-07-05T08:31:32Z"}],"graph_snapshots":[{"event_id":"sha256:395d3f55d6ce5a8974ef28ba9c09942ed6c7bd12cfab5c0fbc9e9eb5a0d98ca1","target":"graph","created_at":"2026-07-05T08:31:32Z","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/2406.09399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenizer, serving as a translator to map the intricate visual data into a compact latent space, lies at the core of visual generative models. Based on the finding that existing tokenizers are tailored to image or video inputs, this paper presents OmniTokenizer, a transformer-based tokenizer for joint image and video tokenization. OmniTokenizer is designed with a spatial-temporal decoupled architecture, which integrates window and causal attention for spatial and temporal modeling. To exploit the complementary nature of image and video data, we further propose a progressive training strategy, ","authors_text":"Binyue Peng, Junke Wang, Yi Jiang, Yu-Gang Jiang, Zehuan Yuan, Zuxuan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:26Z","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09399","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:f0b23a69bd34f6ead84a7aa718ae3270b7acd3ac58b1259610d33834072ce422","target":"record","created_at":"2026-07-05T08:31:32Z","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":"695366520e789a2eebb984fb5d15d901053d7712e863b69d5d1c4f867bd2cc36","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:26Z","title_canon_sha256":"85ed6b8b174de2ed70cc47831dcd3da4ff4bd517fa3572a78271d4ad73a9501b"},"schema_version":"1.0","source":{"id":"2406.09399","kind":"arxiv","version":1}},"canonical_sha256":"6ef8c043d429407cc2be5c03a4c0b1c1628fb1366be54cc9784f8e91f0f15747","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ef8c043d429407cc2be5c03a4c0b1c1628fb1366be54cc9784f8e91f0f15747","first_computed_at":"2026-07-05T08:31:32.515197Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:32.515197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qQgW2/NSWhQp0DZbZGwvf0UFEYzOIJnTC64ZIZLUVrOSduZfNtgFJm3Wf5ezjekGrDWFKBOV5HzgYgetH81CBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:32.515753Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09399","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0b23a69bd34f6ead84a7aa718ae3270b7acd3ac58b1259610d33834072ce422","sha256:395d3f55d6ce5a8974ef28ba9c09942ed6c7bd12cfab5c0fbc9e9eb5a0d98ca1"],"state_sha256":"5fca78ee272379da3f5890904657284db0bee0f30aaeac52f230eeb3aa739682"}