{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AOVNECR7CKP5NIF2DQB7LKWNAN","short_pith_number":"pith:AOVNECR7","schema_version":"1.0","canonical_sha256":"03aad20a3f129fd6a0ba1c03f5aacd0366db916473646fedb9c89069eae65de2","source":{"kind":"arxiv","id":"2606.30811","version":1},"attestation_state":"computed","paper":{"title":"AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"I Chieh Chen, Kien T. Pham, Long Chen, Qifeng Chen","submitted_at":"2026-06-29T18:35:17Z","abstract_excerpt":"Audio-video generation has recently gained unprecedented research attention, aiming to synthesize high-quality sounding video content with fine-grained synchronization and semantic alignment between the auditory and visual components. The preceding methods predominantly adopt a dual-branch design with separate tokenization and generation modules per modality, neglecting the representation gap while necessitating intensive computational resources for proper training. Inspired by recent advancements in one-dimensional visual tokenization, we present \\textbf{AVTok}, a novel unified tokenizer desi"},"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":"2606.30811","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T18:35:17Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"f171f5fec913f7a7961f60c185e1cea5712f3bbf3244c872c2f3758ee075fd04","abstract_canon_sha256":"87e5495b171db84a4fec674990ad2da88d4b4e4d6747cd8e10f9ad18181ca02c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:18.256463Z","signature_b64":"EEiJOQPnONJ0W6M2RhKiZJZGtEHWzjGJQ5aFSYWe5cFEyZT+912mTwe/ZAsDjYGsRcuIylHDDfT3ZMiI8kVODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03aad20a3f129fd6a0ba1c03f5aacd0366db916473646fedb9c89069eae65de2","last_reissued_at":"2026-07-01T00:17:18.256066Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:18.256066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"I Chieh Chen, Kien T. Pham, Long Chen, Qifeng Chen","submitted_at":"2026-06-29T18:35:17Z","abstract_excerpt":"Audio-video generation has recently gained unprecedented research attention, aiming to synthesize high-quality sounding video content with fine-grained synchronization and semantic alignment between the auditory and visual components. The preceding methods predominantly adopt a dual-branch design with separate tokenization and generation modules per modality, neglecting the representation gap while necessitating intensive computational resources for proper training. Inspired by recent advancements in one-dimensional visual tokenization, we present \\textbf{AVTok}, a novel unified tokenizer desi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30811","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/2606.30811/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":"2606.30811","created_at":"2026-07-01T00:17:18.256118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30811v1","created_at":"2026-07-01T00:17:18.256118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30811","created_at":"2026-07-01T00:17:18.256118+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOVNECR7CKP5","created_at":"2026-07-01T00:17:18.256118+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOVNECR7CKP5NIF2","created_at":"2026-07-01T00:17:18.256118+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOVNECR7","created_at":"2026-07-01T00:17:18.256118+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/AOVNECR7CKP5NIF2DQB7LKWNAN","json":"https://pith.science/pith/AOVNECR7CKP5NIF2DQB7LKWNAN.json","graph_json":"https://pith.science/api/pith-number/AOVNECR7CKP5NIF2DQB7LKWNAN/graph.json","events_json":"https://pith.science/api/pith-number/AOVNECR7CKP5NIF2DQB7LKWNAN/events.json","paper":"https://pith.science/paper/AOVNECR7"},"agent_actions":{"view_html":"https://pith.science/pith/AOVNECR7CKP5NIF2DQB7LKWNAN","download_json":"https://pith.science/pith/AOVNECR7CKP5NIF2DQB7LKWNAN.json","view_paper":"https://pith.science/paper/AOVNECR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30811&json=true","fetch_graph":"https://pith.science/api/pith-number/AOVNECR7CKP5NIF2DQB7LKWNAN/graph.json","fetch_events":"https://pith.science/api/pith-number/AOVNECR7CKP5NIF2DQB7LKWNAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOVNECR7CKP5NIF2DQB7LKWNAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOVNECR7CKP5NIF2DQB7LKWNAN/action/storage_attestation","attest_author":"https://pith.science/pith/AOVNECR7CKP5NIF2DQB7LKWNAN/action/author_attestation","sign_citation":"https://pith.science/pith/AOVNECR7CKP5NIF2DQB7LKWNAN/action/citation_signature","submit_replication":"https://pith.science/pith/AOVNECR7CKP5NIF2DQB7LKWNAN/action/replication_record"}},"created_at":"2026-07-01T00:17:18.256118+00:00","updated_at":"2026-07-01T00:17:18.256118+00:00"}