{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6PEGRZIUOYUK3SM56PRTLRJWNB","short_pith_number":"pith:6PEGRZIU","schema_version":"1.0","canonical_sha256":"f3c868e5147628adc99df3e335c5366855161cbaadc4d7d7754a1faef588eea4","source":{"kind":"arxiv","id":"2501.05442","version":2},"attestation_state":"computed","paper":{"title":"Progressive Growing of Video Tokenizers for Temporally Compact Latent Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.IV"],"primary_cat":"cs.CV","authors_text":"Aniruddha Mahapatra, David Bourgin, Feng Liu, Long Mai, Yitian Zhang","submitted_at":"2025-01-09T18:55:15Z","abstract_excerpt":"Video tokenizers are essential for latent video diffusion models, converting raw video data into spatiotemporally compressed latent spaces for efficient training. However, extending state-of-the-art video tokenizers to achieve a temporal compression ratio beyond 4x without increasing channel capacity poses significant challenges. In this work, we propose an alternative approach to enhance temporal compression. We find that the reconstruction quality of temporally subsampled videos from a low-compression encoder surpasses that of high-compression encoders applied to original videos. This indica"},"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":"2501.05442","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T18:55:15Z","cross_cats_sorted":["cs.AI","eess.IV"],"title_canon_sha256":"2a841e10dcbc7664aae877fe7a56d147f2c5826c87e80b4c9cefd35c935b83f1","abstract_canon_sha256":"9a588583c1acf024223e7c7f835fa714c7c9ecd845da3ced90f316636814ead0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:17.362661Z","signature_b64":"9nrnDs7tAsIGWw5u4en3EkZVpvdj9185Nv6xEzR5HqPSO5u2mTcD21QVFxtRsWqAVgvPgx0pB/LgRIExo/lvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3c868e5147628adc99df3e335c5366855161cbaadc4d7d7754a1faef588eea4","last_reissued_at":"2026-07-05T11:47:17.362228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:17.362228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progressive Growing of Video Tokenizers for Temporally Compact Latent Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.IV"],"primary_cat":"cs.CV","authors_text":"Aniruddha Mahapatra, David Bourgin, Feng Liu, Long Mai, Yitian Zhang","submitted_at":"2025-01-09T18:55:15Z","abstract_excerpt":"Video tokenizers are essential for latent video diffusion models, converting raw video data into spatiotemporally compressed latent spaces for efficient training. However, extending state-of-the-art video tokenizers to achieve a temporal compression ratio beyond 4x without increasing channel capacity poses significant challenges. In this work, we propose an alternative approach to enhance temporal compression. We find that the reconstruction quality of temporally subsampled videos from a low-compression encoder surpasses that of high-compression encoders applied to original videos. This indica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05442","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/2501.05442/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":"2501.05442","created_at":"2026-07-05T11:47:17.362286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05442v2","created_at":"2026-07-05T11:47:17.362286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05442","created_at":"2026-07-05T11:47:17.362286+00:00"},{"alias_kind":"pith_short_12","alias_value":"6PEGRZIUOYUK","created_at":"2026-07-05T11:47:17.362286+00:00"},{"alias_kind":"pith_short_16","alias_value":"6PEGRZIUOYUK3SM5","created_at":"2026-07-05T11:47:17.362286+00:00"},{"alias_kind":"pith_short_8","alias_value":"6PEGRZIU","created_at":"2026-07-05T11:47:17.362286+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6PEGRZIUOYUK3SM56PRTLRJWNB","json":"https://pith.science/pith/6PEGRZIUOYUK3SM56PRTLRJWNB.json","graph_json":"https://pith.science/api/pith-number/6PEGRZIUOYUK3SM56PRTLRJWNB/graph.json","events_json":"https://pith.science/api/pith-number/6PEGRZIUOYUK3SM56PRTLRJWNB/events.json","paper":"https://pith.science/paper/6PEGRZIU"},"agent_actions":{"view_html":"https://pith.science/pith/6PEGRZIUOYUK3SM56PRTLRJWNB","download_json":"https://pith.science/pith/6PEGRZIUOYUK3SM56PRTLRJWNB.json","view_paper":"https://pith.science/paper/6PEGRZIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05442&json=true","fetch_graph":"https://pith.science/api/pith-number/6PEGRZIUOYUK3SM56PRTLRJWNB/graph.json","fetch_events":"https://pith.science/api/pith-number/6PEGRZIUOYUK3SM56PRTLRJWNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6PEGRZIUOYUK3SM56PRTLRJWNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6PEGRZIUOYUK3SM56PRTLRJWNB/action/storage_attestation","attest_author":"https://pith.science/pith/6PEGRZIUOYUK3SM56PRTLRJWNB/action/author_attestation","sign_citation":"https://pith.science/pith/6PEGRZIUOYUK3SM56PRTLRJWNB/action/citation_signature","submit_replication":"https://pith.science/pith/6PEGRZIUOYUK3SM56PRTLRJWNB/action/replication_record"}},"created_at":"2026-07-05T11:47:17.362286+00:00","updated_at":"2026-07-05T11:47:17.362286+00:00"}