{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AV52VXSUQSFEXQNVHP4AID2BCC","short_pith_number":"pith:AV52VXSU","schema_version":"1.0","canonical_sha256":"057baade54848a4bc1b53bf8040f41108499da7ee2a55f6d23e63dcef3b1c227","source":{"kind":"arxiv","id":"2410.02130","version":2},"attestation_state":"computed","paper":{"title":"MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chang D. Yoo, Tri Ton, Trung X. Pham","submitted_at":"2024-10-03T01:23:44Z","abstract_excerpt":"We introduce MDSGen, a novel framework for vision-guided open-domain sound generation optimized for model parameter size, memory consumption, and inference speed. This framework incorporates two key innovations: (1) a redundant video feature removal module that filters out unnecessary visual information, and (2) a temporal-aware masking strategy that leverages temporal context for enhanced audio generation accuracy. In contrast to existing resource-heavy Unet-based models, \\texttt{MDSGen} employs denoising masked diffusion transformers, facilitating efficient generation without reliance on pre"},"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":"2410.02130","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-03T01:23:44Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"7a2b7d4ef66e83fd3520aefd1be41b46852f15f52854feb10f2125e71b67cec7","abstract_canon_sha256":"70d0ab72d557ab174ea22a7491be77d156004dc86228cfdbd8a5d9a9b8734fc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:43.356255Z","signature_b64":"tvd7pE1YSTsR0Kgwdsp+Gak7Ic5ZxzLN8FH0+5r0jsGSVMBgmo9HENHgOUl8EOBCzs3w/Bd4BHbyEwISlCBNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"057baade54848a4bc1b53bf8040f41108499da7ee2a55f6d23e63dcef3b1c227","last_reissued_at":"2026-07-05T10:13:43.355777Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:43.355777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chang D. Yoo, Tri Ton, Trung X. Pham","submitted_at":"2024-10-03T01:23:44Z","abstract_excerpt":"We introduce MDSGen, a novel framework for vision-guided open-domain sound generation optimized for model parameter size, memory consumption, and inference speed. This framework incorporates two key innovations: (1) a redundant video feature removal module that filters out unnecessary visual information, and (2) a temporal-aware masking strategy that leverages temporal context for enhanced audio generation accuracy. In contrast to existing resource-heavy Unet-based models, \\texttt{MDSGen} employs denoising masked diffusion transformers, facilitating efficient generation without reliance on pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02130","kind":"arxiv","version":2},"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/2410.02130/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":"2410.02130","created_at":"2026-07-05T10:13:43.355828+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02130v2","created_at":"2026-07-05T10:13:43.355828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02130","created_at":"2026-07-05T10:13:43.355828+00:00"},{"alias_kind":"pith_short_12","alias_value":"AV52VXSUQSFE","created_at":"2026-07-05T10:13:43.355828+00:00"},{"alias_kind":"pith_short_16","alias_value":"AV52VXSUQSFEXQNV","created_at":"2026-07-05T10:13:43.355828+00:00"},{"alias_kind":"pith_short_8","alias_value":"AV52VXSU","created_at":"2026-07-05T10:13:43.355828+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00398","citing_title":"Occlusion-robust Stylization for Drawing-based 3D Animation","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AV52VXSUQSFEXQNVHP4AID2BCC","json":"https://pith.science/pith/AV52VXSUQSFEXQNVHP4AID2BCC.json","graph_json":"https://pith.science/api/pith-number/AV52VXSUQSFEXQNVHP4AID2BCC/graph.json","events_json":"https://pith.science/api/pith-number/AV52VXSUQSFEXQNVHP4AID2BCC/events.json","paper":"https://pith.science/paper/AV52VXSU"},"agent_actions":{"view_html":"https://pith.science/pith/AV52VXSUQSFEXQNVHP4AID2BCC","download_json":"https://pith.science/pith/AV52VXSUQSFEXQNVHP4AID2BCC.json","view_paper":"https://pith.science/paper/AV52VXSU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02130&json=true","fetch_graph":"https://pith.science/api/pith-number/AV52VXSUQSFEXQNVHP4AID2BCC/graph.json","fetch_events":"https://pith.science/api/pith-number/AV52VXSUQSFEXQNVHP4AID2BCC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AV52VXSUQSFEXQNVHP4AID2BCC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AV52VXSUQSFEXQNVHP4AID2BCC/action/storage_attestation","attest_author":"https://pith.science/pith/AV52VXSUQSFEXQNVHP4AID2BCC/action/author_attestation","sign_citation":"https://pith.science/pith/AV52VXSUQSFEXQNVHP4AID2BCC/action/citation_signature","submit_replication":"https://pith.science/pith/AV52VXSUQSFEXQNVHP4AID2BCC/action/replication_record"}},"created_at":"2026-07-05T10:13:43.355828+00:00","updated_at":"2026-07-05T10:13:43.355828+00:00"}