{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3PRNMURH45POCDLAPAANEOEPAN","short_pith_number":"pith:3PRNMURH","schema_version":"1.0","canonical_sha256":"dbe2d65227e75ee10d607800d2388f03543c87a8f0a0406074af91b943104b55","source":{"kind":"arxiv","id":"2406.10591","version":1},"attestation_state":"computed","paper":{"title":"MINT: a Multi-modal Image and Narrative Text Dubbing Dataset for Foley Audio Content Planning and Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chunyu Qiang, Guanjun Li, Hongming Guo, Jianhua Tao, Ruibo Fu, Shuai Zhang, Shuchen Shi, Tao Wang, Xiaopeng Wang, Xin Qi, Xuefei Liu, Yi Lu, Yukun Liu, Zhengqi Wen, Zhiyong Wang","submitted_at":"2024-06-15T10:47:36Z","abstract_excerpt":"Foley audio, critical for enhancing the immersive experience in multimedia content, faces significant challenges in the AI-generated content (AIGC) landscape. Despite advancements in AIGC technologies for text and image generation, the foley audio dubbing remains rudimentary due to difficulties in cross-modal scene matching and content correlation. Current text-to-audio technology, which relies on detailed and acoustically relevant textual descriptions, falls short in practical video dubbing applications. Existing datasets like AudioSet, AudioCaps, Clotho, Sound-of-Story, and WavCaps do not fu"},"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":"2406.10591","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-15T10:47:36Z","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","cs.SD"],"title_canon_sha256":"9b9e67388a87aff44d860dfc1befdec4eb16f4410a765978f440f9c833eeb9e7","abstract_canon_sha256":"98db4ec1a71b92c0009ba32d9e98512d33a8c4e9ff4cbb796157897152370931"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:44.101528Z","signature_b64":"66kcZjeXidVEaudg1cuCwH8cUCniUKsfQ2p1jRU3bCj3WSXUic1/WVg+UzSNX9i5JesgPb8XptrNU4Fze0iYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbe2d65227e75ee10d607800d2388f03543c87a8f0a0406074af91b943104b55","last_reissued_at":"2026-07-05T08:32:44.101021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:44.101021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MINT: a Multi-modal Image and Narrative Text Dubbing Dataset for Foley Audio Content Planning and Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chunyu Qiang, Guanjun Li, Hongming Guo, Jianhua Tao, Ruibo Fu, Shuai Zhang, Shuchen Shi, Tao Wang, Xiaopeng Wang, Xin Qi, Xuefei Liu, Yi Lu, Yukun Liu, Zhengqi Wen, Zhiyong Wang","submitted_at":"2024-06-15T10:47:36Z","abstract_excerpt":"Foley audio, critical for enhancing the immersive experience in multimedia content, faces significant challenges in the AI-generated content (AIGC) landscape. Despite advancements in AIGC technologies for text and image generation, the foley audio dubbing remains rudimentary due to difficulties in cross-modal scene matching and content correlation. Current text-to-audio technology, which relies on detailed and acoustically relevant textual descriptions, falls short in practical video dubbing applications. Existing datasets like AudioSet, AudioCaps, Clotho, Sound-of-Story, and WavCaps do not fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10591","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/2406.10591/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":"2406.10591","created_at":"2026-07-05T08:32:44.101079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10591v1","created_at":"2026-07-05T08:32:44.101079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10591","created_at":"2026-07-05T08:32:44.101079+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PRNMURH45PO","created_at":"2026-07-05T08:32:44.101079+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PRNMURH45POCDLA","created_at":"2026-07-05T08:32:44.101079+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PRNMURH","created_at":"2026-07-05T08:32:44.101079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25980","citing_title":"FoleySet: A Multi-Level Human-Annotated Foley Sound Dataset","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PRNMURH45POCDLAPAANEOEPAN","json":"https://pith.science/pith/3PRNMURH45POCDLAPAANEOEPAN.json","graph_json":"https://pith.science/api/pith-number/3PRNMURH45POCDLAPAANEOEPAN/graph.json","events_json":"https://pith.science/api/pith-number/3PRNMURH45POCDLAPAANEOEPAN/events.json","paper":"https://pith.science/paper/3PRNMURH"},"agent_actions":{"view_html":"https://pith.science/pith/3PRNMURH45POCDLAPAANEOEPAN","download_json":"https://pith.science/pith/3PRNMURH45POCDLAPAANEOEPAN.json","view_paper":"https://pith.science/paper/3PRNMURH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10591&json=true","fetch_graph":"https://pith.science/api/pith-number/3PRNMURH45POCDLAPAANEOEPAN/graph.json","fetch_events":"https://pith.science/api/pith-number/3PRNMURH45POCDLAPAANEOEPAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PRNMURH45POCDLAPAANEOEPAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PRNMURH45POCDLAPAANEOEPAN/action/storage_attestation","attest_author":"https://pith.science/pith/3PRNMURH45POCDLAPAANEOEPAN/action/author_attestation","sign_citation":"https://pith.science/pith/3PRNMURH45POCDLAPAANEOEPAN/action/citation_signature","submit_replication":"https://pith.science/pith/3PRNMURH45POCDLAPAANEOEPAN/action/replication_record"}},"created_at":"2026-07-05T08:32:44.101079+00:00","updated_at":"2026-07-05T08:32:44.101079+00:00"}