{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:P2TDLSYZWBXY72BQ3AFZIAEPET","short_pith_number":"pith:P2TDLSYZ","canonical_record":{"source":{"id":"2306.17203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-29T12:39:58Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"738f6bd004be43b211f3ca083606e28b8845e72ee4701349c6ee5f2daee05b8b","abstract_canon_sha256":"5abb9bc6981dbad4a378869fdbf9a74bc54130277f2770be0ddb06e0929ac751"},"schema_version":"1.0"},"canonical_sha256":"7ea635cb19b06f8fe830d80b94008f24d0ed4711a907b633566564ed7b1d28ac","source":{"kind":"arxiv","id":"2306.17203","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17203","created_at":"2026-07-05T06:26:23Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17203v1","created_at":"2026-07-05T06:26:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17203","created_at":"2026-07-05T06:26:23Z"},{"alias_kind":"pith_short_12","alias_value":"P2TDLSYZWBXY","created_at":"2026-07-05T06:26:23Z"},{"alias_kind":"pith_short_16","alias_value":"P2TDLSYZWBXY72BQ","created_at":"2026-07-05T06:26:23Z"},{"alias_kind":"pith_short_8","alias_value":"P2TDLSYZ","created_at":"2026-07-05T06:26:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:P2TDLSYZWBXY72BQ3AFZIAEPET","target":"record","payload":{"canonical_record":{"source":{"id":"2306.17203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-29T12:39:58Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"738f6bd004be43b211f3ca083606e28b8845e72ee4701349c6ee5f2daee05b8b","abstract_canon_sha256":"5abb9bc6981dbad4a378869fdbf9a74bc54130277f2770be0ddb06e0929ac751"},"schema_version":"1.0"},"canonical_sha256":"7ea635cb19b06f8fe830d80b94008f24d0ed4711a907b633566564ed7b1d28ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:23.346485Z","signature_b64":"COgXOZb2BLlz32XFm0YLhvPsuu/URaE5HF8Bz8ofkiiCGJNlRQNp3UB8EikM3UXLkgSDuH9DCzQ5YUjZwZ3KCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ea635cb19b06f8fe830d80b94008f24d0ed4711a907b633566564ed7b1d28ac","last_reissued_at":"2026-07-05T06:26:23.345970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:23.345970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.17203","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":"2026-07-05T06:26:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aPMqPuwKvTRR5FJXkEHPOXM18Cv/6B+9/kMuAEkxnhhBScMwmh+u496qtbaYO2zjwxOBYWCyVucY/yGoTWkWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:24:09.766132Z"},"content_sha256":"1e980a5684b6a0981b31f558af95d316ffb53e811e22f963001053eac6565375","schema_version":"1.0","event_id":"sha256:1e980a5684b6a0981b31f558af95d316ffb53e811e22f963001053eac6565375"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:P2TDLSYZWBXY72BQ3AFZIAEPET","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenxu Hu, Chuanhao Yan, Hang Zhao, Simian Luo","submitted_at":"2023-06-29T12:39:58Z","abstract_excerpt":"The Video-to-Audio (V2A) model has recently gained attention for its practical application in generating audio directly from silent videos, particularly in video/film production. However, previous methods in V2A have limited generation quality in terms of temporal synchronization and audio-visual relevance. We present Diff-Foley, a synchronized Video-to-Audio synthesis method with a latent diffusion model (LDM) that generates high-quality audio with improved synchronization and audio-visual relevance. We adopt contrastive audio-visual pretraining (CAVP) to learn more temporally and semanticall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17203","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/2306.17203/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":"2026-07-05T06:26:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DMVJobxxXbYscG1dzsLtaAevhrqxtnzPNKRlvzFqIXM8DvyPZ7O0FKILVeJQQDJ3IJgu5jpUFwtrhWGBfiJoBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:24:09.766808Z"},"content_sha256":"0ddaf78884ae4289f4eb237880e4d0ff63bce92d24e937055d0fbc134a2ca2d7","schema_version":"1.0","event_id":"sha256:0ddaf78884ae4289f4eb237880e4d0ff63bce92d24e937055d0fbc134a2ca2d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P2TDLSYZWBXY72BQ3AFZIAEPET/bundle.json","state_url":"https://pith.science/pith/P2TDLSYZWBXY72BQ3AFZIAEPET/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P2TDLSYZWBXY72BQ3AFZIAEPET/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":"2026-07-07T05:24:09Z","links":{"resolver":"https://pith.science/pith/P2TDLSYZWBXY72BQ3AFZIAEPET","bundle":"https://pith.science/pith/P2TDLSYZWBXY72BQ3AFZIAEPET/bundle.json","state":"https://pith.science/pith/P2TDLSYZWBXY72BQ3AFZIAEPET/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P2TDLSYZWBXY72BQ3AFZIAEPET/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:P2TDLSYZWBXY72BQ3AFZIAEPET","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":"5abb9bc6981dbad4a378869fdbf9a74bc54130277f2770be0ddb06e0929ac751","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-29T12:39:58Z","title_canon_sha256":"738f6bd004be43b211f3ca083606e28b8845e72ee4701349c6ee5f2daee05b8b"},"schema_version":"1.0","source":{"id":"2306.17203","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17203","created_at":"2026-07-05T06:26:23Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17203v1","created_at":"2026-07-05T06:26:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17203","created_at":"2026-07-05T06:26:23Z"},{"alias_kind":"pith_short_12","alias_value":"P2TDLSYZWBXY","created_at":"2026-07-05T06:26:23Z"},{"alias_kind":"pith_short_16","alias_value":"P2TDLSYZWBXY72BQ","created_at":"2026-07-05T06:26:23Z"},{"alias_kind":"pith_short_8","alias_value":"P2TDLSYZ","created_at":"2026-07-05T06:26:23Z"}],"graph_snapshots":[{"event_id":"sha256:0ddaf78884ae4289f4eb237880e4d0ff63bce92d24e937055d0fbc134a2ca2d7","target":"graph","created_at":"2026-07-05T06:26:23Z","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/2306.17203/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Video-to-Audio (V2A) model has recently gained attention for its practical application in generating audio directly from silent videos, particularly in video/film production. However, previous methods in V2A have limited generation quality in terms of temporal synchronization and audio-visual relevance. We present Diff-Foley, a synchronized Video-to-Audio synthesis method with a latent diffusion model (LDM) that generates high-quality audio with improved synchronization and audio-visual relevance. We adopt contrastive audio-visual pretraining (CAVP) to learn more temporally and semanticall","authors_text":"Chenxu Hu, Chuanhao Yan, Hang Zhao, Simian Luo","cross_cats":["cs.CV","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-29T12:39:58Z","title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17203","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":"sha256:1e980a5684b6a0981b31f558af95d316ffb53e811e22f963001053eac6565375","target":"record","created_at":"2026-07-05T06:26:23Z","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":"5abb9bc6981dbad4a378869fdbf9a74bc54130277f2770be0ddb06e0929ac751","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-29T12:39:58Z","title_canon_sha256":"738f6bd004be43b211f3ca083606e28b8845e72ee4701349c6ee5f2daee05b8b"},"schema_version":"1.0","source":{"id":"2306.17203","kind":"arxiv","version":1}},"canonical_sha256":"7ea635cb19b06f8fe830d80b94008f24d0ed4711a907b633566564ed7b1d28ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ea635cb19b06f8fe830d80b94008f24d0ed4711a907b633566564ed7b1d28ac","first_computed_at":"2026-07-05T06:26:23.345970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:23.345970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"COgXOZb2BLlz32XFm0YLhvPsuu/URaE5HF8Bz8ofkiiCGJNlRQNp3UB8EikM3UXLkgSDuH9DCzQ5YUjZwZ3KCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:23.346485Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.17203","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e980a5684b6a0981b31f558af95d316ffb53e811e22f963001053eac6565375","sha256:0ddaf78884ae4289f4eb237880e4d0ff63bce92d24e937055d0fbc134a2ca2d7"],"state_sha256":"bc589449df013a3ca29e27edef864346bebae53ad8d2c613b42aaa0b7cebe81c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YE6Vf1IRsjAh+1N3HnoTROOdI/CPtPViQgOJkKdWP4h7AvlfmSe8OKjT0t0rLYAD/5Ey+lDrWldVI7pH+iERCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:24:09.770524Z","bundle_sha256":"dc82e9f04c47f5426a77df43098301297bee803437b3f26a4d426ad26977aef7"}}