{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AV52VXSUQSFEXQNVHP4AID2BCC","short_pith_number":"pith:AV52VXSU","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"},"canonical_sha256":"057baade54848a4bc1b53bf8040f41108499da7ee2a55f6d23e63dcef3b1c227","source":{"kind":"arxiv","id":"2410.02130","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AV52VXSUQSFEXQNVHP4AID2BCC","target":"record","payload":{"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"},"canonical_sha256":"057baade54848a4bc1b53bf8040f41108499da7ee2a55f6d23e63dcef3b1c227","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"},"source_kind":"arxiv","source_id":"2410.02130","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pNDDQhxyz9kaHX40DmXdtV4av0V7KnqH81U8AQXcXe2rjbRtsejpEgCWFzpIya45qZLRm7zZijEicJLuZ376DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:37:06.093459Z"},"content_sha256":"bb4db5d8826c6dd4619410ecba7d6198261fc9638a88905f2d4fa49b3a249a31","schema_version":"1.0","event_id":"sha256:bb4db5d8826c6dd4619410ecba7d6198261fc9638a88905f2d4fa49b3a249a31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AV52VXSUQSFEXQNVHP4AID2BCC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"doIHqstKZvkGBGAG4D3KNO1Rk3s4Dl6z9fBwWC/47TSmiKMgQ7syDMhmB0NjDyo0xspjjIBB80JG2ckrvCdhBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:37:06.094457Z"},"content_sha256":"8affe8199ddeab3a4a3d51aaf33b8aa6a3d6834fdd38c4111554e4fead0b09b6","schema_version":"1.0","event_id":"sha256:8affe8199ddeab3a4a3d51aaf33b8aa6a3d6834fdd38c4111554e4fead0b09b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AV52VXSUQSFEXQNVHP4AID2BCC/bundle.json","state_url":"https://pith.science/pith/AV52VXSUQSFEXQNVHP4AID2BCC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AV52VXSUQSFEXQNVHP4AID2BCC/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":"2026-08-07T18:37:06Z","links":{"resolver":"https://pith.science/pith/AV52VXSUQSFEXQNVHP4AID2BCC","bundle":"https://pith.science/pith/AV52VXSUQSFEXQNVHP4AID2BCC/bundle.json","state":"https://pith.science/pith/AV52VXSUQSFEXQNVHP4AID2BCC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AV52VXSUQSFEXQNVHP4AID2BCC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VOt6cyUH4fDv2U788ibdM1mNCA6niBqYsDNOgxjBQ1C8HQFmQZYi7b6+3fbjYUuscXi2L4VCQuyTmAiRsOqmBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:37:06.100798Z","bundle_sha256":"2e1dc7c1008a92dd6208bb1dc6ea72e38a599f425c178bcdbd9845ca72e88fa6"}}