{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:N2DILE5BPN4AQU6WHLH4JZBIGW","short_pith_number":"pith:N2DILE5B","canonical_record":{"source":{"id":"2406.07686","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T20:05:58Z","cross_cats_sorted":[],"title_canon_sha256":"8c39a9e51db1b16a3b4ceedbb8cb049f39c8ab1eda733e4dfff8f11d216b83fa","abstract_canon_sha256":"bd2732ca39156e2d2ba0fcd39f9f5cd5d5514c7d7b0f910acf8c7a8c89007371"},"schema_version":"1.0"},"canonical_sha256":"6e868593a17b780853d63acfc4e42835bf80dbf05649a02969631264d2c56470","source":{"kind":"arxiv","id":"2406.07686","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07686","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07686v1","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07686","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"pith_short_12","alias_value":"N2DILE5BPN4A","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"N2DILE5BPN4AQU6W","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"N2DILE5B","created_at":"2026-07-05T08:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:N2DILE5BPN4AQU6WHLH4JZBIGW","target":"record","payload":{"canonical_record":{"source":{"id":"2406.07686","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T20:05:58Z","cross_cats_sorted":[],"title_canon_sha256":"8c39a9e51db1b16a3b4ceedbb8cb049f39c8ab1eda733e4dfff8f11d216b83fa","abstract_canon_sha256":"bd2732ca39156e2d2ba0fcd39f9f5cd5d5514c7d7b0f910acf8c7a8c89007371"},"schema_version":"1.0"},"canonical_sha256":"6e868593a17b780853d63acfc4e42835bf80dbf05649a02969631264d2c56470","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:36.754499Z","signature_b64":"A+TsZPtWIDTnAVfysMOF6CeGWt48MPwIBc/ngNDLwbOWeQ7YjFwZ6Bdgf30aeyXsSbT3KYgP4Y7ykQEoRvFrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e868593a17b780853d63acfc4e42835bf80dbf05649a02969631264d2c56470","last_reissued_at":"2026-07-05T08:30:36.753947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:36.753947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.07686","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":"2026-07-05T08:30:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MsSlyHxvcBnn/W8JksIAUcC0ncHqAvIeMwIlQ91fWbYRuaMrZ6+JZWV3JUBliWkthW4FdIHAb07qVoSHtSoJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T15:13:36.195998Z"},"content_sha256":"d6aa4d82ac8b581a9e7a7d20349501fc34c0595523f44a2ce7e4d944f0fcc369","schema_version":"1.0","event_id":"sha256:d6aa4d82ac8b581a9e7a7d20349501fc34c0595523f44a2ce7e4d944f0fcc369"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:N2DILE5BPN4AQU6WHLH4JZBIGW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitrios Hatzinakos, Jing Shi, Kai Wang, Shijian Deng, Yapeng Tian","submitted_at":"2024-06-11T20:05:58Z","abstract_excerpt":"Recent Diffusion Transformers (DiTs) have shown impressive capabilities in generating high-quality single-modality content, including images, videos, and audio. However, it is still under-explored whether the transformer-based diffuser can efficiently denoise the Gaussian noises towards superb multimodal content creation. To bridge this gap, we introduce AV-DiT, a novel and efficient audio-visual diffusion transformer designed to generate high-quality, realistic videos with both visual and audio tracks. To minimize model complexity and computational costs, AV-DiT utilizes a shared DiT backbone"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07686","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/2406.07686/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":"2026-07-05T08:30:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lxR8Urq3pf1ITDnkpjctp6A9/Ael8ekszpF8XeqCs8EHHMUNQrAgY7LIfWz4nEKQAjXzvgpRKN0U5cWoR+AZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T15:13:36.196567Z"},"content_sha256":"63a1d1761ca167726fc9ff13a3a3316a57a3700b05225daf69ac445e25184dd3","schema_version":"1.0","event_id":"sha256:63a1d1761ca167726fc9ff13a3a3316a57a3700b05225daf69ac445e25184dd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N2DILE5BPN4AQU6WHLH4JZBIGW/bundle.json","state_url":"https://pith.science/pith/N2DILE5BPN4AQU6WHLH4JZBIGW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N2DILE5BPN4AQU6WHLH4JZBIGW/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":"2026-08-20T15:13:36Z","links":{"resolver":"https://pith.science/pith/N2DILE5BPN4AQU6WHLH4JZBIGW","bundle":"https://pith.science/pith/N2DILE5BPN4AQU6WHLH4JZBIGW/bundle.json","state":"https://pith.science/pith/N2DILE5BPN4AQU6WHLH4JZBIGW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N2DILE5BPN4AQU6WHLH4JZBIGW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N2DILE5BPN4AQU6WHLH4JZBIGW","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":"bd2732ca39156e2d2ba0fcd39f9f5cd5d5514c7d7b0f910acf8c7a8c89007371","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T20:05:58Z","title_canon_sha256":"8c39a9e51db1b16a3b4ceedbb8cb049f39c8ab1eda733e4dfff8f11d216b83fa"},"schema_version":"1.0","source":{"id":"2406.07686","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07686","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07686v1","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07686","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"pith_short_12","alias_value":"N2DILE5BPN4A","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"N2DILE5BPN4AQU6W","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"N2DILE5B","created_at":"2026-07-05T08:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:63a1d1761ca167726fc9ff13a3a3316a57a3700b05225daf69ac445e25184dd3","target":"graph","created_at":"2026-07-05T08:30:36Z","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/2406.07686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Diffusion Transformers (DiTs) have shown impressive capabilities in generating high-quality single-modality content, including images, videos, and audio. However, it is still under-explored whether the transformer-based diffuser can efficiently denoise the Gaussian noises towards superb multimodal content creation. To bridge this gap, we introduce AV-DiT, a novel and efficient audio-visual diffusion transformer designed to generate high-quality, realistic videos with both visual and audio tracks. To minimize model complexity and computational costs, AV-DiT utilizes a shared DiT backbone","authors_text":"Dimitrios Hatzinakos, Jing Shi, Kai Wang, Shijian Deng, Yapeng Tian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T20:05:58Z","title":"AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07686","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:d6aa4d82ac8b581a9e7a7d20349501fc34c0595523f44a2ce7e4d944f0fcc369","target":"record","created_at":"2026-07-05T08:30:36Z","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":"bd2732ca39156e2d2ba0fcd39f9f5cd5d5514c7d7b0f910acf8c7a8c89007371","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T20:05:58Z","title_canon_sha256":"8c39a9e51db1b16a3b4ceedbb8cb049f39c8ab1eda733e4dfff8f11d216b83fa"},"schema_version":"1.0","source":{"id":"2406.07686","kind":"arxiv","version":1}},"canonical_sha256":"6e868593a17b780853d63acfc4e42835bf80dbf05649a02969631264d2c56470","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e868593a17b780853d63acfc4e42835bf80dbf05649a02969631264d2c56470","first_computed_at":"2026-07-05T08:30:36.753947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:36.753947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A+TsZPtWIDTnAVfysMOF6CeGWt48MPwIBc/ngNDLwbOWeQ7YjFwZ6Bdgf30aeyXsSbT3KYgP4Y7ykQEoRvFrAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:36.754499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07686","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6aa4d82ac8b581a9e7a7d20349501fc34c0595523f44a2ce7e4d944f0fcc369","sha256:63a1d1761ca167726fc9ff13a3a3316a57a3700b05225daf69ac445e25184dd3"],"state_sha256":"933e1a986908b981c51dbf589e964a85a2a55329c3ecc90af069d982f19d5e4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yiC10h6e+onmt4xy57J2XNnaDBU7WPg8wo0GFiZhRsfXqN+tAlF3DN9vLdjrVkU8NB3GBukr7zNO8dN504m5AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T15:13:36.201956Z","bundle_sha256":"513615203a75ea67d162c367a0b9b3dbd4cef026b4a7814cc34e5f2264f896e7"}}