{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NRTEEOZE7X5HT4JFUDXEP7IBEO","short_pith_number":"pith:NRTEEOZE","schema_version":"1.0","canonical_sha256":"6c66423b24fdfa79f125a0ee47fd0123aa6ce58318a7ee312df3d636df130abf","source":{"kind":"arxiv","id":"2412.13061","version":1},"attestation_state":"computed","paper":{"title":"VidTok: A Versatile and Open-Source Video Tokenizer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anni Tang, Jiang Bian, Junliang Guo, Li Song, Tianyu He, Xinle Cheng","submitted_at":"2024-12-17T16:27:11Z","abstract_excerpt":"Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations. Consequently, there is a growing demand for high-performance, open-source video tokenizers as video-centric research gains prominence. We introduce VidTok, a versatile video tokenizer that delivers state-of-the-art performance in both continuous and discrete tokenizations. VidTok incorporates several key advancements over existing approaches: 1) model architecture such as convolutional layers"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.13061","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T16:27:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3021b1ab0fe222384c770655477d5742134ead81e2e4d9f0a2dd0b845d730a9b","abstract_canon_sha256":"c06d6efeaeecd77ce32e69c2e41c54d5e78dc871fd61a1fa3e404d07eb8004bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:39.751391Z","signature_b64":"+a69aeyuysqoFPDMOHuSDsXyJ3cjfS4vgKeidPn1+d+cPwHDKbI/FinmqhP7gt2mCchmCLqXqnWpm46U5tIjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c66423b24fdfa79f125a0ee47fd0123aa6ce58318a7ee312df3d636df130abf","last_reissued_at":"2026-07-05T09:50:39.750875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:39.750875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VidTok: A Versatile and Open-Source Video Tokenizer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anni Tang, Jiang Bian, Junliang Guo, Li Song, Tianyu He, Xinle Cheng","submitted_at":"2024-12-17T16:27:11Z","abstract_excerpt":"Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations. Consequently, there is a growing demand for high-performance, open-source video tokenizers as video-centric research gains prominence. We introduce VidTok, a versatile video tokenizer that delivers state-of-the-art performance in both continuous and discrete tokenizations. VidTok incorporates several key advancements over existing approaches: 1) model architecture such as convolutional layers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13061","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/2412.13061/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.13061","created_at":"2026-07-05T09:50:39.750930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13061v1","created_at":"2026-07-05T09:50:39.750930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13061","created_at":"2026-07-05T09:50:39.750930+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRTEEOZE7X5H","created_at":"2026-07-05T09:50:39.750930+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRTEEOZE7X5HT4JF","created_at":"2026-07-05T09:50:39.750930+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRTEEOZE","created_at":"2026-07-05T09:50:39.750930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17590","citing_title":"TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30811","citing_title":"AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2506.00433","citing_title":"Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NRTEEOZE7X5HT4JFUDXEP7IBEO","json":"https://pith.science/pith/NRTEEOZE7X5HT4JFUDXEP7IBEO.json","graph_json":"https://pith.science/api/pith-number/NRTEEOZE7X5HT4JFUDXEP7IBEO/graph.json","events_json":"https://pith.science/api/pith-number/NRTEEOZE7X5HT4JFUDXEP7IBEO/events.json","paper":"https://pith.science/paper/NRTEEOZE"},"agent_actions":{"view_html":"https://pith.science/pith/NRTEEOZE7X5HT4JFUDXEP7IBEO","download_json":"https://pith.science/pith/NRTEEOZE7X5HT4JFUDXEP7IBEO.json","view_paper":"https://pith.science/paper/NRTEEOZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13061&json=true","fetch_graph":"https://pith.science/api/pith-number/NRTEEOZE7X5HT4JFUDXEP7IBEO/graph.json","fetch_events":"https://pith.science/api/pith-number/NRTEEOZE7X5HT4JFUDXEP7IBEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRTEEOZE7X5HT4JFUDXEP7IBEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRTEEOZE7X5HT4JFUDXEP7IBEO/action/storage_attestation","attest_author":"https://pith.science/pith/NRTEEOZE7X5HT4JFUDXEP7IBEO/action/author_attestation","sign_citation":"https://pith.science/pith/NRTEEOZE7X5HT4JFUDXEP7IBEO/action/citation_signature","submit_replication":"https://pith.science/pith/NRTEEOZE7X5HT4JFUDXEP7IBEO/action/replication_record"}},"created_at":"2026-07-05T09:50:39.750930+00:00","updated_at":"2026-07-05T09:50:39.750930+00:00"}