{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZX7OBZDZ5QF5A6JGECEK3Z5NKR","short_pith_number":"pith:ZX7OBZDZ","canonical_record":{"source":{"id":"2503.11513","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T15:36:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3257e60997f2f11bf4da1155a88e1e700d9c5b2b5097feee8aa59e4ffb9ad4c1","abstract_canon_sha256":"38759b5a78640abd7cf4851efa1ab6088b2f98c0dcd53e52a14bbcdfadb0b6a9"},"schema_version":"1.0"},"canonical_sha256":"cdfee0e479ec0bd079262088ade7ad54637aa3579af4ea8a041168e9c62ab28c","source":{"kind":"arxiv","id":"2503.11513","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.11513","created_at":"2026-07-05T10:31:33Z"},{"alias_kind":"arxiv_version","alias_value":"2503.11513v1","created_at":"2026-07-05T10:31:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11513","created_at":"2026-07-05T10:31:33Z"},{"alias_kind":"pith_short_12","alias_value":"ZX7OBZDZ5QF5","created_at":"2026-07-05T10:31:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZX7OBZDZ5QF5A6JG","created_at":"2026-07-05T10:31:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZX7OBZDZ","created_at":"2026-07-05T10:31:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZX7OBZDZ5QF5A6JGECEK3Z5NKR","target":"record","payload":{"canonical_record":{"source":{"id":"2503.11513","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T15:36:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3257e60997f2f11bf4da1155a88e1e700d9c5b2b5097feee8aa59e4ffb9ad4c1","abstract_canon_sha256":"38759b5a78640abd7cf4851efa1ab6088b2f98c0dcd53e52a14bbcdfadb0b6a9"},"schema_version":"1.0"},"canonical_sha256":"cdfee0e479ec0bd079262088ade7ad54637aa3579af4ea8a041168e9c62ab28c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:33.338749Z","signature_b64":"xhe/jI+TsKajKpdAcjIzNlgGoJ9sFHAgIbUgaPyiGDxUTRt4NP/tC5l614GJAJnMuTEWd8bRCC9F37NjhWfPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdfee0e479ec0bd079262088ade7ad54637aa3579af4ea8a041168e9c62ab28c","last_reissued_at":"2026-07-05T10:31:33.338247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:33.338247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.11513","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":"2026-07-05T10:31:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZM9Y83WYQp+cInvpDpjv51JHY1z7Ud31h5KQhh+Aq+FglsaipALWYOTFohxQUcjkECc8ZLp73bBAtQoFy+grAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:41:46.573019Z"},"content_sha256":"9cce750f8e6c65b6a5db934b8b2936db7136520cfa62f1a08cc44a1401f7e3f0","schema_version":"1.0","event_id":"sha256:9cce750f8e6c65b6a5db934b8b2936db7136520cfa62f1a08cc44a1401f7e3f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZX7OBZDZ5QF5A6JGECEK3Z5NKR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chong Luo, Houwen Peng, Kai Qiu, Lili Qiu, Lingqiao Liu, Qi Dai, Tianyu He, Yifan Yang, Yuqing Yang, Ziqin Zhou","submitted_at":"2025-03-14T15:36:39Z","abstract_excerpt":"Text-to-video generation poses significant challenges due to the inherent complexity of video data, which spans both temporal and spatial dimensions. It introduces additional redundancy, abrupt variations, and a domain gap between language and vision tokens while generation. Addressing these challenges requires an effective video tokenizer that can efficiently encode video data while preserving essential semantic and spatiotemporal information, serving as a critical bridge between text and vision. Inspired by the observation in VQ-VAE-2 and workflows of traditional animation, we propose HiTVid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11513","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/2503.11513/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":"2026-07-05T10:31:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y90mlq93I3tsiovQNARQOLETKVecgfEeKDDr0A46VieJz4uuWe5vsLfaQCynrBf5h5wlWkU+y/DiQzasq2tVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:41:46.573509Z"},"content_sha256":"e6023b3d81a08054c5b3d755571bd2708fbe82f54ffa85851816e95dd5e1d9e5","schema_version":"1.0","event_id":"sha256:e6023b3d81a08054c5b3d755571bd2708fbe82f54ffa85851816e95dd5e1d9e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZX7OBZDZ5QF5A6JGECEK3Z5NKR/bundle.json","state_url":"https://pith.science/pith/ZX7OBZDZ5QF5A6JGECEK3Z5NKR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZX7OBZDZ5QF5A6JGECEK3Z5NKR/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":"2026-08-06T16:41:46Z","links":{"resolver":"https://pith.science/pith/ZX7OBZDZ5QF5A6JGECEK3Z5NKR","bundle":"https://pith.science/pith/ZX7OBZDZ5QF5A6JGECEK3Z5NKR/bundle.json","state":"https://pith.science/pith/ZX7OBZDZ5QF5A6JGECEK3Z5NKR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZX7OBZDZ5QF5A6JGECEK3Z5NKR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZX7OBZDZ5QF5A6JGECEK3Z5NKR","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":"38759b5a78640abd7cf4851efa1ab6088b2f98c0dcd53e52a14bbcdfadb0b6a9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T15:36:39Z","title_canon_sha256":"3257e60997f2f11bf4da1155a88e1e700d9c5b2b5097feee8aa59e4ffb9ad4c1"},"schema_version":"1.0","source":{"id":"2503.11513","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.11513","created_at":"2026-07-05T10:31:33Z"},{"alias_kind":"arxiv_version","alias_value":"2503.11513v1","created_at":"2026-07-05T10:31:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11513","created_at":"2026-07-05T10:31:33Z"},{"alias_kind":"pith_short_12","alias_value":"ZX7OBZDZ5QF5","created_at":"2026-07-05T10:31:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZX7OBZDZ5QF5A6JG","created_at":"2026-07-05T10:31:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZX7OBZDZ","created_at":"2026-07-05T10:31:33Z"}],"graph_snapshots":[{"event_id":"sha256:e6023b3d81a08054c5b3d755571bd2708fbe82f54ffa85851816e95dd5e1d9e5","target":"graph","created_at":"2026-07-05T10:31:33Z","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/2503.11513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-video generation poses significant challenges due to the inherent complexity of video data, which spans both temporal and spatial dimensions. It introduces additional redundancy, abrupt variations, and a domain gap between language and vision tokens while generation. Addressing these challenges requires an effective video tokenizer that can efficiently encode video data while preserving essential semantic and spatiotemporal information, serving as a critical bridge between text and vision. Inspired by the observation in VQ-VAE-2 and workflows of traditional animation, we propose HiTVid","authors_text":"Chong Luo, Houwen Peng, Kai Qiu, Lili Qiu, Lingqiao Liu, Qi Dai, Tianyu He, Yifan Yang, Yuqing Yang, Ziqin Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T15:36:39Z","title":"HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11513","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":"sha256:9cce750f8e6c65b6a5db934b8b2936db7136520cfa62f1a08cc44a1401f7e3f0","target":"record","created_at":"2026-07-05T10:31:33Z","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":"38759b5a78640abd7cf4851efa1ab6088b2f98c0dcd53e52a14bbcdfadb0b6a9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T15:36:39Z","title_canon_sha256":"3257e60997f2f11bf4da1155a88e1e700d9c5b2b5097feee8aa59e4ffb9ad4c1"},"schema_version":"1.0","source":{"id":"2503.11513","kind":"arxiv","version":1}},"canonical_sha256":"cdfee0e479ec0bd079262088ade7ad54637aa3579af4ea8a041168e9c62ab28c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdfee0e479ec0bd079262088ade7ad54637aa3579af4ea8a041168e9c62ab28c","first_computed_at":"2026-07-05T10:31:33.338247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:33.338247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xhe/jI+TsKajKpdAcjIzNlgGoJ9sFHAgIbUgaPyiGDxUTRt4NP/tC5l614GJAJnMuTEWd8bRCC9F37NjhWfPDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:33.338749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.11513","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cce750f8e6c65b6a5db934b8b2936db7136520cfa62f1a08cc44a1401f7e3f0","sha256:e6023b3d81a08054c5b3d755571bd2708fbe82f54ffa85851816e95dd5e1d9e5"],"state_sha256":"a5a2cd7ef1beebc5185f808caa34069b31e7aadc18f19473b51392f25444841f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T+EOBEyoEJX/Aou9kNasCsS7aOU65qecd9qB2yRJkNYrwtc1cRLywFBFNEefczE/DfnccaXJDYQIDtS+pBGNAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:41:46.576797Z","bundle_sha256":"de6ff04db77dfa737629f76a3b84fa6b77d0b500233d2e630b7c8262b5d26fd2"}}