{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AOVNECR7CKP5NIF2DQB7LKWNAN","short_pith_number":"pith:AOVNECR7","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"},"canonical_sha256":"03aad20a3f129fd6a0ba1c03f5aacd0366db916473646fedb9c89069eae65de2","source":{"kind":"arxiv","id":"2606.30811","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30811","created_at":"2026-07-01T00:17:18Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30811v1","created_at":"2026-07-01T00:17:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30811","created_at":"2026-07-01T00:17:18Z"},{"alias_kind":"pith_short_12","alias_value":"AOVNECR7CKP5","created_at":"2026-07-01T00:17:18Z"},{"alias_kind":"pith_short_16","alias_value":"AOVNECR7CKP5NIF2","created_at":"2026-07-01T00:17:18Z"},{"alias_kind":"pith_short_8","alias_value":"AOVNECR7","created_at":"2026-07-01T00:17:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AOVNECR7CKP5NIF2DQB7LKWNAN","target":"record","payload":{"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"},"canonical_sha256":"03aad20a3f129fd6a0ba1c03f5aacd0366db916473646fedb9c89069eae65de2","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"},"source_kind":"arxiv","source_id":"2606.30811","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":"2026-07-01T00:17:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"emIem9iBaT5i4Cn4t+HiEE+NEr7cJR9234QNtCWy5kzIGEpfV9cMZn64djqeU/94urG80vdsdHUQg8G0Z8F8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T19:15:38.731492Z"},"content_sha256":"22cc88af6ebc42fca574cc689ff791737b1ad661d4c31be344e8381a417ec57c","schema_version":"1.0","event_id":"sha256:22cc88af6ebc42fca574cc689ff791737b1ad661d4c31be344e8381a417ec57c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AOVNECR7CKP5NIF2DQB7LKWNAN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-01T00:17:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lOI5RiUIwvH0kmOTuj5Jr+/hljxdPSiCAAERWd/gHOLCVigqaiukAGqQGJnTWEEcFQ2KvasBTWN5rl8ABG35Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T19:15:38.731872Z"},"content_sha256":"183340d699ae541fd3a82141fa881cc6f06403dfb4ea4d61899a41cd4a252799","schema_version":"1.0","event_id":"sha256:183340d699ae541fd3a82141fa881cc6f06403dfb4ea4d61899a41cd4a252799"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AOVNECR7CKP5NIF2DQB7LKWNAN/bundle.json","state_url":"https://pith.science/pith/AOVNECR7CKP5NIF2DQB7LKWNAN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AOVNECR7CKP5NIF2DQB7LKWNAN/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":"2026-07-01T19:15:38Z","links":{"resolver":"https://pith.science/pith/AOVNECR7CKP5NIF2DQB7LKWNAN","bundle":"https://pith.science/pith/AOVNECR7CKP5NIF2DQB7LKWNAN/bundle.json","state":"https://pith.science/pith/AOVNECR7CKP5NIF2DQB7LKWNAN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AOVNECR7CKP5NIF2DQB7LKWNAN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AOVNECR7CKP5NIF2DQB7LKWNAN","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":"87e5495b171db84a4fec674990ad2da88d4b4e4d6747cd8e10f9ad18181ca02c","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T18:35:17Z","title_canon_sha256":"f171f5fec913f7a7961f60c185e1cea5712f3bbf3244c872c2f3758ee075fd04"},"schema_version":"1.0","source":{"id":"2606.30811","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30811","created_at":"2026-07-01T00:17:18Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30811v1","created_at":"2026-07-01T00:17:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30811","created_at":"2026-07-01T00:17:18Z"},{"alias_kind":"pith_short_12","alias_value":"AOVNECR7CKP5","created_at":"2026-07-01T00:17:18Z"},{"alias_kind":"pith_short_16","alias_value":"AOVNECR7CKP5NIF2","created_at":"2026-07-01T00:17:18Z"},{"alias_kind":"pith_short_8","alias_value":"AOVNECR7","created_at":"2026-07-01T00:17:18Z"}],"graph_snapshots":[{"event_id":"sha256:183340d699ae541fd3a82141fa881cc6f06403dfb4ea4d61899a41cd4a252799","target":"graph","created_at":"2026-07-01T00:17:18Z","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/2606.30811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"I Chieh Chen, Kien T. Pham, Long Chen, Qifeng Chen","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T18:35:17Z","title":"AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30811","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":"sha256:22cc88af6ebc42fca574cc689ff791737b1ad661d4c31be344e8381a417ec57c","target":"record","created_at":"2026-07-01T00:17:18Z","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":"87e5495b171db84a4fec674990ad2da88d4b4e4d6747cd8e10f9ad18181ca02c","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T18:35:17Z","title_canon_sha256":"f171f5fec913f7a7961f60c185e1cea5712f3bbf3244c872c2f3758ee075fd04"},"schema_version":"1.0","source":{"id":"2606.30811","kind":"arxiv","version":1}},"canonical_sha256":"03aad20a3f129fd6a0ba1c03f5aacd0366db916473646fedb9c89069eae65de2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03aad20a3f129fd6a0ba1c03f5aacd0366db916473646fedb9c89069eae65de2","first_computed_at":"2026-07-01T00:17:18.256066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T00:17:18.256066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EEiJOQPnONJ0W6M2RhKiZJZGtEHWzjGJQ5aFSYWe5cFEyZT+912mTwe/ZAsDjYGsRcuIylHDDfT3ZMiI8kVODw==","signature_status":"signed_v1","signed_at":"2026-07-01T00:17:18.256463Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30811","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22cc88af6ebc42fca574cc689ff791737b1ad661d4c31be344e8381a417ec57c","sha256:183340d699ae541fd3a82141fa881cc6f06403dfb4ea4d61899a41cd4a252799"],"state_sha256":"8f2937bb3454c78f29a0bad45ad2cd4cd5d5e68a88e7879037cb3e733ebec8fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dolYyNHPUZXnkHCIKnpVzgscB7gzOIJ9wl6zjyWjgD2/IG/QRErMhaKKV7g/Cx0qLvKiRI2pi71kD1N0O2BwBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T19:15:38.733868Z","bundle_sha256":"3c68b2f720e0ba127c349c9a0858162132e504e8bdb3678e9e86caa34d724893"}}