{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AV52VXSUQSFEXQNVHP4AID2BCC","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":"70d0ab72d557ab174ea22a7491be77d156004dc86228cfdbd8a5d9a9b8734fc6","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-03T01:23:44Z","title_canon_sha256":"7a2b7d4ef66e83fd3520aefd1be41b46852f15f52854feb10f2125e71b67cec7"},"schema_version":"1.0","source":{"id":"2410.02130","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02130","created_at":"2026-07-05T10:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02130v2","created_at":"2026-07-05T10:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02130","created_at":"2026-07-05T10:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"AV52VXSUQSFE","created_at":"2026-07-05T10:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"AV52VXSUQSFEXQNV","created_at":"2026-07-05T10:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"AV52VXSU","created_at":"2026-07-05T10:13:43Z"}],"graph_snapshots":[{"event_id":"sha256:8affe8199ddeab3a4a3d51aaf33b8aa6a3d6834fdd38c4111554e4fead0b09b6","target":"graph","created_at":"2026-07-05T10:13:43Z","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/2410.02130/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chang D. Yoo, Tri Ton, Trung X. Pham","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-03T01:23:44Z","title":"MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02130","kind":"arxiv","version":2},"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:bb4db5d8826c6dd4619410ecba7d6198261fc9638a88905f2d4fa49b3a249a31","target":"record","created_at":"2026-07-05T10:13:43Z","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":"70d0ab72d557ab174ea22a7491be77d156004dc86228cfdbd8a5d9a9b8734fc6","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-03T01:23:44Z","title_canon_sha256":"7a2b7d4ef66e83fd3520aefd1be41b46852f15f52854feb10f2125e71b67cec7"},"schema_version":"1.0","source":{"id":"2410.02130","kind":"arxiv","version":2}},"canonical_sha256":"057baade54848a4bc1b53bf8040f41108499da7ee2a55f6d23e63dcef3b1c227","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"057baade54848a4bc1b53bf8040f41108499da7ee2a55f6d23e63dcef3b1c227","first_computed_at":"2026-07-05T10:13:43.355777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:43.355777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tvd7pE1YSTsR0Kgwdsp+Gak7Ic5ZxzLN8FH0+5r0jsGSVMBgmo9HENHgOUl8EOBCzs3w/Bd4BHbyEwISlCBNCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:43.356255Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02130","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb4db5d8826c6dd4619410ecba7d6198261fc9638a88905f2d4fa49b3a249a31","sha256:8affe8199ddeab3a4a3d51aaf33b8aa6a3d6834fdd38c4111554e4fead0b09b6"],"state_sha256":"7d24e3a0a4775a46522ce389abdab31a0cd5e5a847a20d850eef6b5a248807dd"}