{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MPMEP6HL5KXNPSZL4WMGDNSLY5","short_pith_number":"pith:MPMEP6HL","canonical_record":{"source":{"id":"2305.12903","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-22T10:37:27Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"a5de60dd852c853ed9256c3a8a5d34aa312b393df9fab1a8c7afe14718fc2e8d","abstract_canon_sha256":"066ff19a4e4a783327d45a8faaedf5a07637303b2dd939ea74306f08eec6f3fd"},"schema_version":"1.0"},"canonical_sha256":"63d847f8ebeaaed7cb2be59861b64bc7580b4821a10674cf13c5615204deb966","source":{"kind":"arxiv","id":"2305.12903","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12903","created_at":"2026-07-05T06:12:16Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12903v1","created_at":"2026-07-05T06:12:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12903","created_at":"2026-07-05T06:12:16Z"},{"alias_kind":"pith_short_12","alias_value":"MPMEP6HL5KXN","created_at":"2026-07-05T06:12:16Z"},{"alias_kind":"pith_short_16","alias_value":"MPMEP6HL5KXNPSZL","created_at":"2026-07-05T06:12:16Z"},{"alias_kind":"pith_short_8","alias_value":"MPMEP6HL","created_at":"2026-07-05T06:12:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MPMEP6HL5KXNPSZL4WMGDNSLY5","target":"record","payload":{"canonical_record":{"source":{"id":"2305.12903","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-22T10:37:27Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"a5de60dd852c853ed9256c3a8a5d34aa312b393df9fab1a8c7afe14718fc2e8d","abstract_canon_sha256":"066ff19a4e4a783327d45a8faaedf5a07637303b2dd939ea74306f08eec6f3fd"},"schema_version":"1.0"},"canonical_sha256":"63d847f8ebeaaed7cb2be59861b64bc7580b4821a10674cf13c5615204deb966","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:16.513769Z","signature_b64":"3ho6ETaL3LCzzcyhtnM/vLCZF6l3sAIuA/ZDzdTbEjy9MfbI/MBV2bW/1vN68wHH/jFIf7TDqmIkCV8Os7dzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63d847f8ebeaaed7cb2be59861b64bc7580b4821a10674cf13c5615204deb966","last_reissued_at":"2026-07-05T06:12:16.513222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:16.513222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.12903","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":"2026-07-05T06:12:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VDjHKZMEF8QYpY17hitauOFWTJmxqMhr0UKKIWGtIrgN8gnDX7k4ybqgcNEiEKwRZW01imRMXp1pVD7m4kuxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:55:00.978857Z"},"content_sha256":"4b8a495d08dd18a70549b2899503802dbbb2b0104e9d90ed49b2d303a1ee6630","schema_version":"1.0","event_id":"sha256:4b8a495d08dd18a70549b2899503802dbbb2b0104e9d90ed49b2d303a1ee6630"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MPMEP6HL5KXNPSZL4WMGDNSLY5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiffAVA: Personalized Text-to-Audio Generation with Visual Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jing Shi, Shentong Mo, Yapeng Tian","submitted_at":"2023-05-22T10:37:27Z","abstract_excerpt":"Text-to-audio (TTA) generation is a recent popular problem that aims to synthesize general audio given text descriptions. Previous methods utilized latent diffusion models to learn audio embedding in a latent space with text embedding as the condition. However, they ignored the synchronization between audio and visual content in the video, and tended to generate audio mismatching from video frames. In this work, we propose a novel and personalized text-to-sound generation approach with visual alignment based on latent diffusion models, namely DiffAVA, that can simply fine-tune lightweight visu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12903","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/2305.12903/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":"2026-07-05T06:12:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h6LgoqEXFSYOOTxMmNCyKDjNvpBmjM0Im+S0HWQaJyJ0XdY8Sf0T9PobGrKOigCWI9yQhfQXkYq+o8dfnCyNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:55:00.979219Z"},"content_sha256":"93fc999f209fcff61baf269d39358f12b259a5f8e98cc3fe98d5a97f4bba9b46","schema_version":"1.0","event_id":"sha256:93fc999f209fcff61baf269d39358f12b259a5f8e98cc3fe98d5a97f4bba9b46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MPMEP6HL5KXNPSZL4WMGDNSLY5/bundle.json","state_url":"https://pith.science/pith/MPMEP6HL5KXNPSZL4WMGDNSLY5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MPMEP6HL5KXNPSZL4WMGDNSLY5/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":"2026-08-19T19:55:00Z","links":{"resolver":"https://pith.science/pith/MPMEP6HL5KXNPSZL4WMGDNSLY5","bundle":"https://pith.science/pith/MPMEP6HL5KXNPSZL4WMGDNSLY5/bundle.json","state":"https://pith.science/pith/MPMEP6HL5KXNPSZL4WMGDNSLY5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MPMEP6HL5KXNPSZL4WMGDNSLY5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MPMEP6HL5KXNPSZL4WMGDNSLY5","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":"066ff19a4e4a783327d45a8faaedf5a07637303b2dd939ea74306f08eec6f3fd","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-22T10:37:27Z","title_canon_sha256":"a5de60dd852c853ed9256c3a8a5d34aa312b393df9fab1a8c7afe14718fc2e8d"},"schema_version":"1.0","source":{"id":"2305.12903","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12903","created_at":"2026-07-05T06:12:16Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12903v1","created_at":"2026-07-05T06:12:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12903","created_at":"2026-07-05T06:12:16Z"},{"alias_kind":"pith_short_12","alias_value":"MPMEP6HL5KXN","created_at":"2026-07-05T06:12:16Z"},{"alias_kind":"pith_short_16","alias_value":"MPMEP6HL5KXNPSZL","created_at":"2026-07-05T06:12:16Z"},{"alias_kind":"pith_short_8","alias_value":"MPMEP6HL","created_at":"2026-07-05T06:12:16Z"}],"graph_snapshots":[{"event_id":"sha256:93fc999f209fcff61baf269d39358f12b259a5f8e98cc3fe98d5a97f4bba9b46","target":"graph","created_at":"2026-07-05T06:12:16Z","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/2305.12903/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-audio (TTA) generation is a recent popular problem that aims to synthesize general audio given text descriptions. Previous methods utilized latent diffusion models to learn audio embedding in a latent space with text embedding as the condition. However, they ignored the synchronization between audio and visual content in the video, and tended to generate audio mismatching from video frames. In this work, we propose a novel and personalized text-to-sound generation approach with visual alignment based on latent diffusion models, namely DiffAVA, that can simply fine-tune lightweight visu","authors_text":"Jing Shi, Shentong Mo, Yapeng Tian","cross_cats":["cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-22T10:37:27Z","title":"DiffAVA: Personalized Text-to-Audio Generation with Visual Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12903","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":"sha256:4b8a495d08dd18a70549b2899503802dbbb2b0104e9d90ed49b2d303a1ee6630","target":"record","created_at":"2026-07-05T06:12:16Z","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":"066ff19a4e4a783327d45a8faaedf5a07637303b2dd939ea74306f08eec6f3fd","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-22T10:37:27Z","title_canon_sha256":"a5de60dd852c853ed9256c3a8a5d34aa312b393df9fab1a8c7afe14718fc2e8d"},"schema_version":"1.0","source":{"id":"2305.12903","kind":"arxiv","version":1}},"canonical_sha256":"63d847f8ebeaaed7cb2be59861b64bc7580b4821a10674cf13c5615204deb966","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63d847f8ebeaaed7cb2be59861b64bc7580b4821a10674cf13c5615204deb966","first_computed_at":"2026-07-05T06:12:16.513222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:16.513222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ho6ETaL3LCzzcyhtnM/vLCZF6l3sAIuA/ZDzdTbEjy9MfbI/MBV2bW/1vN68wHH/jFIf7TDqmIkCV8Os7dzCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:16.513769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12903","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b8a495d08dd18a70549b2899503802dbbb2b0104e9d90ed49b2d303a1ee6630","sha256:93fc999f209fcff61baf269d39358f12b259a5f8e98cc3fe98d5a97f4bba9b46"],"state_sha256":"d0978c8ec751828bf5807753f00fc1e43561055736724c0f2a90ceed11d102d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j8WocCV+ImG2uUqizcQbuOym75ITMP6pyNAjseGeR/cJj4p7DegoXaRB65go5aLnOIyzyZnmNuVq3fXjMGazDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T19:55:00.982259Z","bundle_sha256":"159eb881bdbe78583d68b9e9543298432c4d87fe10e6ddf921f89ef100517dc5"}}