{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WOEANIJVWIEXMBUOKNLRNYMIS3","short_pith_number":"pith:WOEANIJV","canonical_record":{"source":{"id":"2605.30339","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:59:09Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"68f19c3aa9c565e57103c7e97ef81612a061f44890bcc8ba00e723b4a25d7430","abstract_canon_sha256":"7d993bf5de540d521e3df757ce076f139bbfb00f1807979485f0dcad0ab030f8"},"schema_version":"1.0"},"canonical_sha256":"b38806a135b20976068e535716e18896cca70f6a06886e942193f56a24d707bf","source":{"kind":"arxiv","id":"2605.30339","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30339","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30339v1","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30339","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"WOEANIJVWIEX","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"WOEANIJVWIEXMBUO","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"WOEANIJV","created_at":"2026-05-29T02:06:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WOEANIJVWIEXMBUOKNLRNYMIS3","target":"record","payload":{"canonical_record":{"source":{"id":"2605.30339","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:59:09Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"68f19c3aa9c565e57103c7e97ef81612a061f44890bcc8ba00e723b4a25d7430","abstract_canon_sha256":"7d993bf5de540d521e3df757ce076f139bbfb00f1807979485f0dcad0ab030f8"},"schema_version":"1.0"},"canonical_sha256":"b38806a135b20976068e535716e18896cca70f6a06886e942193f56a24d707bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:16.976808Z","signature_b64":"FITr+wxFQ6frp7kaUrsJGrTM/umzSaeYcKRNFUt7IkCOpWYvWgXizV9O5QSROdNQpcB2R7RNNhPCR056vmyyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b38806a135b20976068e535716e18896cca70f6a06886e942193f56a24d707bf","last_reissued_at":"2026-05-29T02:06:16.976393Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:16.976393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.30339","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":"2026-05-29T02:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KdRwpuI6mxIC6NC0EIZvTnCqVGEXYWMGW7vsei8nVk8L1ANILILu3gU8RMiIk9RpPRmrGhoVyF92EL/hsAXRBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T08:47:05.237616Z"},"content_sha256":"62caad82ff96b475002260c2a2928d1ef2810c32401ff1c4927413264dcb9902","schema_version":"1.0","event_id":"sha256:62caad82ff96b475002260c2a2928d1ef2810c32401ff1c4927413264dcb9902"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WOEANIJVWIEXMBUOKNLRNYMIS3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Single-Factor Physical Video-to-Audio Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Arushi Goel, Gantavya Bhatt, Gopala Anumanchipalli, Kevin J. Shih, Ming-Yu Liu, Sang-gil Lee, Siddharth Gururani, Tingle Li, Zhifeng Kong","submitted_at":"2026-05-28T17:59:09Z","abstract_excerpt":"Generative video-to-audio (V2A) models produce highly plausible soundtracks, but it remains unclear whether they capture the underlying physical processes. Existing evaluations emphasize perceptual realism and overlook physical correctness under controlled interventions. In this paper, we introduce FlatSounds, a benchmark that audits the physical reasoning of V2A models through: 1) controlled counterfactual pairs in which a single physical factor is varied, and 2) single-video pattern tests that probe internal consistency and directional trends. These settings test whether the generated audio "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30339","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/2605.30339/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":"2026-05-29T02:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L8YeFONB/c1hrs2BitSEeiiZ4ndWGWi5gG2z5FUUdXetGbeNyj81Aq2LX8OB//rrv+xRm6+4g4HYA/ymszyUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T08:47:05.238397Z"},"content_sha256":"37b8bb537aacdc1b972d11452e9228756f466bbe835c4a6779b9e3ec989691e7","schema_version":"1.0","event_id":"sha256:37b8bb537aacdc1b972d11452e9228756f466bbe835c4a6779b9e3ec989691e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WOEANIJVWIEXMBUOKNLRNYMIS3/bundle.json","state_url":"https://pith.science/pith/WOEANIJVWIEXMBUOKNLRNYMIS3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WOEANIJVWIEXMBUOKNLRNYMIS3/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":"2026-06-07T08:47:05Z","links":{"resolver":"https://pith.science/pith/WOEANIJVWIEXMBUOKNLRNYMIS3","bundle":"https://pith.science/pith/WOEANIJVWIEXMBUOKNLRNYMIS3/bundle.json","state":"https://pith.science/pith/WOEANIJVWIEXMBUOKNLRNYMIS3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WOEANIJVWIEXMBUOKNLRNYMIS3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WOEANIJVWIEXMBUOKNLRNYMIS3","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":"7d993bf5de540d521e3df757ce076f139bbfb00f1807979485f0dcad0ab030f8","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:59:09Z","title_canon_sha256":"68f19c3aa9c565e57103c7e97ef81612a061f44890bcc8ba00e723b4a25d7430"},"schema_version":"1.0","source":{"id":"2605.30339","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30339","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30339v1","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30339","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"WOEANIJVWIEX","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"WOEANIJVWIEXMBUO","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"WOEANIJV","created_at":"2026-05-29T02:06:16Z"}],"graph_snapshots":[{"event_id":"sha256:37b8bb537aacdc1b972d11452e9228756f466bbe835c4a6779b9e3ec989691e7","target":"graph","created_at":"2026-05-29T02:06:16Z","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/2605.30339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative video-to-audio (V2A) models produce highly plausible soundtracks, but it remains unclear whether they capture the underlying physical processes. Existing evaluations emphasize perceptual realism and overlook physical correctness under controlled interventions. In this paper, we introduce FlatSounds, a benchmark that audits the physical reasoning of V2A models through: 1) controlled counterfactual pairs in which a single physical factor is varied, and 2) single-video pattern tests that probe internal consistency and directional trends. These settings test whether the generated audio ","authors_text":"Arushi Goel, Gantavya Bhatt, Gopala Anumanchipalli, Kevin J. Shih, Ming-Yu Liu, Sang-gil Lee, Siddharth Gururani, Tingle Li, Zhifeng Kong","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:59:09Z","title":"Benchmarking Single-Factor Physical Video-to-Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30339","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":"sha256:62caad82ff96b475002260c2a2928d1ef2810c32401ff1c4927413264dcb9902","target":"record","created_at":"2026-05-29T02:06:16Z","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":"7d993bf5de540d521e3df757ce076f139bbfb00f1807979485f0dcad0ab030f8","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:59:09Z","title_canon_sha256":"68f19c3aa9c565e57103c7e97ef81612a061f44890bcc8ba00e723b4a25d7430"},"schema_version":"1.0","source":{"id":"2605.30339","kind":"arxiv","version":1}},"canonical_sha256":"b38806a135b20976068e535716e18896cca70f6a06886e942193f56a24d707bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b38806a135b20976068e535716e18896cca70f6a06886e942193f56a24d707bf","first_computed_at":"2026-05-29T02:06:16.976393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:16.976393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FITr+wxFQ6frp7kaUrsJGrTM/umzSaeYcKRNFUt7IkCOpWYvWgXizV9O5QSROdNQpcB2R7RNNhPCR056vmyyBA==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:16.976808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30339","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62caad82ff96b475002260c2a2928d1ef2810c32401ff1c4927413264dcb9902","sha256:37b8bb537aacdc1b972d11452e9228756f466bbe835c4a6779b9e3ec989691e7"],"state_sha256":"5003ceb43a146bd68fb480fd290183c3d87636aca0c686a91908e78bfd1c5be4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6y7ZIvlc3cfrccfLBkpZdsikZ1K1T53PWe3os9kFGx3Zv9rqSbnOvwc7Xdqrp+11NBfk6MpTFri3tl4n+A4oBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T08:47:05.242306Z","bundle_sha256":"6a57167c00ad6cf9b1d0af019a45bcc4597f18709497303a8b58fca95fa4fe9e"}}