{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ULL4QEMJA5A5K6FUYCT7AVOEBM","short_pith_number":"pith:ULL4QEMJ","canonical_record":{"source":{"id":"2502.04476","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-06T20:00:43Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"9ef1fbb98c3a05dc84b1af097737fcd615b77d4f99b1040d91d2d4d7ef6d8b53","abstract_canon_sha256":"5348daa614dc4a6db1f73a00343683020a442b949a65fd757c5a103e29635365"},"schema_version":"1.0"},"canonical_sha256":"a2d7c811890741d578b4c0a7f055c40b045bbaf4bb689faea9caf3993f740a8f","source":{"kind":"arxiv","id":"2502.04476","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04476","created_at":"2026-07-05T10:10:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04476v1","created_at":"2026-07-05T10:10:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04476","created_at":"2026-07-05T10:10:52Z"},{"alias_kind":"pith_short_12","alias_value":"ULL4QEMJA5A5","created_at":"2026-07-05T10:10:52Z"},{"alias_kind":"pith_short_16","alias_value":"ULL4QEMJA5A5K6FU","created_at":"2026-07-05T10:10:52Z"},{"alias_kind":"pith_short_8","alias_value":"ULL4QEMJ","created_at":"2026-07-05T10:10:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ULL4QEMJA5A5K6FUYCT7AVOEBM","target":"record","payload":{"canonical_record":{"source":{"id":"2502.04476","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-06T20:00:43Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"9ef1fbb98c3a05dc84b1af097737fcd615b77d4f99b1040d91d2d4d7ef6d8b53","abstract_canon_sha256":"5348daa614dc4a6db1f73a00343683020a442b949a65fd757c5a103e29635365"},"schema_version":"1.0"},"canonical_sha256":"a2d7c811890741d578b4c0a7f055c40b045bbaf4bb689faea9caf3993f740a8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:52.297923Z","signature_b64":"VjTqDGV1X6jvLSuw/isC0FRea33nkmgz33IPg+XndqfiovFcKI1PbwQzhSnQgO6u0yUPDxQnwG7ByBT1hwWtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2d7c811890741d578b4c0a7f055c40b045bbaf4bb689faea9caf3993f740a8f","last_reissued_at":"2026-07-05T10:10:52.297508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:52.297508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.04476","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":"2026-07-05T10:10:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xTJrKqUjnDyOwmA3mXg8jnTbgydqalc28IEXKRyc2iwzQaLebJDVcNc3qL1fjhO9QX+CLHuiIWsxRvIXQGYXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:13:30.596056Z"},"content_sha256":"76dc2049b478378207857e608a936c1bf14f593db9c41ec56547106996a673e6","schema_version":"1.0","event_id":"sha256:76dc2049b478378207857e608a936c1bf14f593db9c41ec56547106996a673e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ULL4QEMJA5A5K6FUYCT7AVOEBM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ADIFF: Explaining audio difference using natural language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bhiksha Raj, Rita Singh, Shuo Han, Soham Deshmukh","submitted_at":"2025-02-06T20:00:43Z","abstract_excerpt":"Understanding and explaining differences between audio recordings is crucial for fields like audio forensics, quality assessment, and audio generation. This involves identifying and describing audio events, acoustic scenes, signal characteristics, and their emotional impact on listeners. This paper stands out as the first work to comprehensively study the task of explaining audio differences and then propose benchmark, baselines for the task. First, we present two new datasets for audio difference explanation derived from the AudioCaps and Clotho audio captioning datasets. Using Large Language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04476","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/2502.04476/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":"2026-07-05T10:10:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FAaIKwXWYx8MBrKdSZxYQ+09iVcx8vn259grRuqo5N28xuG3SX+mMGo7y2kZ1Is4g3GaCcA1eZbNNMJ1MuH3Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:13:30.596672Z"},"content_sha256":"1b446891e7d8f8ce04be66b4b4069fa5b336f603d28caaff9192baabcf080b0f","schema_version":"1.0","event_id":"sha256:1b446891e7d8f8ce04be66b4b4069fa5b336f603d28caaff9192baabcf080b0f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ULL4QEMJA5A5K6FUYCT7AVOEBM/bundle.json","state_url":"https://pith.science/pith/ULL4QEMJA5A5K6FUYCT7AVOEBM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ULL4QEMJA5A5K6FUYCT7AVOEBM/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":"2026-08-09T01:13:30Z","links":{"resolver":"https://pith.science/pith/ULL4QEMJA5A5K6FUYCT7AVOEBM","bundle":"https://pith.science/pith/ULL4QEMJA5A5K6FUYCT7AVOEBM/bundle.json","state":"https://pith.science/pith/ULL4QEMJA5A5K6FUYCT7AVOEBM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ULL4QEMJA5A5K6FUYCT7AVOEBM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ULL4QEMJA5A5K6FUYCT7AVOEBM","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":"5348daa614dc4a6db1f73a00343683020a442b949a65fd757c5a103e29635365","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-06T20:00:43Z","title_canon_sha256":"9ef1fbb98c3a05dc84b1af097737fcd615b77d4f99b1040d91d2d4d7ef6d8b53"},"schema_version":"1.0","source":{"id":"2502.04476","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04476","created_at":"2026-07-05T10:10:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04476v1","created_at":"2026-07-05T10:10:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04476","created_at":"2026-07-05T10:10:52Z"},{"alias_kind":"pith_short_12","alias_value":"ULL4QEMJA5A5","created_at":"2026-07-05T10:10:52Z"},{"alias_kind":"pith_short_16","alias_value":"ULL4QEMJA5A5K6FU","created_at":"2026-07-05T10:10:52Z"},{"alias_kind":"pith_short_8","alias_value":"ULL4QEMJ","created_at":"2026-07-05T10:10:52Z"}],"graph_snapshots":[{"event_id":"sha256:1b446891e7d8f8ce04be66b4b4069fa5b336f603d28caaff9192baabcf080b0f","target":"graph","created_at":"2026-07-05T10:10:52Z","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/2502.04476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding and explaining differences between audio recordings is crucial for fields like audio forensics, quality assessment, and audio generation. This involves identifying and describing audio events, acoustic scenes, signal characteristics, and their emotional impact on listeners. This paper stands out as the first work to comprehensively study the task of explaining audio differences and then propose benchmark, baselines for the task. First, we present two new datasets for audio difference explanation derived from the AudioCaps and Clotho audio captioning datasets. Using Large Language","authors_text":"Bhiksha Raj, Rita Singh, Shuo Han, Soham Deshmukh","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-06T20:00:43Z","title":"ADIFF: Explaining audio difference using natural language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04476","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":"sha256:76dc2049b478378207857e608a936c1bf14f593db9c41ec56547106996a673e6","target":"record","created_at":"2026-07-05T10:10:52Z","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":"5348daa614dc4a6db1f73a00343683020a442b949a65fd757c5a103e29635365","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-06T20:00:43Z","title_canon_sha256":"9ef1fbb98c3a05dc84b1af097737fcd615b77d4f99b1040d91d2d4d7ef6d8b53"},"schema_version":"1.0","source":{"id":"2502.04476","kind":"arxiv","version":1}},"canonical_sha256":"a2d7c811890741d578b4c0a7f055c40b045bbaf4bb689faea9caf3993f740a8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2d7c811890741d578b4c0a7f055c40b045bbaf4bb689faea9caf3993f740a8f","first_computed_at":"2026-07-05T10:10:52.297508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:52.297508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VjTqDGV1X6jvLSuw/isC0FRea33nkmgz33IPg+XndqfiovFcKI1PbwQzhSnQgO6u0yUPDxQnwG7ByBT1hwWtAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:52.297923Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04476","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76dc2049b478378207857e608a936c1bf14f593db9c41ec56547106996a673e6","sha256:1b446891e7d8f8ce04be66b4b4069fa5b336f603d28caaff9192baabcf080b0f"],"state_sha256":"9d9aaadc703b0ec5af0334c3767ba08d5d27f0da9487caf4517611f888b90d4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8kGT2QJgdXft6IATAnpvRyMrAQ4BNdAna9MHqiw/GuHo4czGPCRfcO2hw1vDyr78h3lIrvby/N44NEQxajLzAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T01:13:30.600263Z","bundle_sha256":"7c014dbf3bde543b51b8b7027ec30913d822d90614375d68c78c59d7adec6e1c"}}