{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R6ZJVXCFYJWXIARXGCWL2GPFI7","short_pith_number":"pith:R6ZJVXCF","schema_version":"1.0","canonical_sha256":"8fb29adc45c26d74023730acbd19e547ee5c5521f7acf0a3ddededc60c4fd895","source":{"kind":"arxiv","id":"2409.10496","version":5},"attestation_state":"computed","paper":{"title":"MusicLIME: Explainable Multimodal Music Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Giorgos Stamou, Orfeas Menis Mastromichalakis, Theodoros Sotirou, Vassilis Lyberatos","submitted_at":"2024-09-16T17:28:21Z","abstract_excerpt":"Multimodal models are critical for music understanding tasks, as they capture the complex interplay between audio and lyrics. However, as these models become more prevalent, the need for explainability grows-understanding how these systems make decisions is vital for ensuring fairness, reducing bias, and fostering trust. In this paper, we introduce MusicLIME, a model-agnostic feature importance explanation method designed for multimodal music models. Unlike traditional unimodal methods, which analyze each modality separately without considering the interaction between them, often leading to in"},"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":"2409.10496","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-16T17:28:21Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"8d46ac8284730c509e36ccb17001b38e45ad74931b49fbc6f37b3a030ad26ee9","abstract_canon_sha256":"d023c947b21b90258893b9f5b2ee7b25be37b863c3742af94e48354e6d22549d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:05.234873Z","signature_b64":"xVYzWv/wwXoG1OXydDxvQ6mhFho5rHnpT3LzNh7MYcZUwCzxG5ZN+Pz8vyJN0q7boilg/SNcW++19wJkD0IKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fb29adc45c26d74023730acbd19e547ee5c5521f7acf0a3ddededc60c4fd895","last_reissued_at":"2026-07-05T10:33:05.234371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:05.234371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MusicLIME: Explainable Multimodal Music Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Giorgos Stamou, Orfeas Menis Mastromichalakis, Theodoros Sotirou, Vassilis Lyberatos","submitted_at":"2024-09-16T17:28:21Z","abstract_excerpt":"Multimodal models are critical for music understanding tasks, as they capture the complex interplay between audio and lyrics. However, as these models become more prevalent, the need for explainability grows-understanding how these systems make decisions is vital for ensuring fairness, reducing bias, and fostering trust. In this paper, we introduce MusicLIME, a model-agnostic feature importance explanation method designed for multimodal music models. Unlike traditional unimodal methods, which analyze each modality separately without considering the interaction between them, often leading to in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10496","kind":"arxiv","version":5},"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/2409.10496/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":"2409.10496","created_at":"2026-07-05T10:33:05.234432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10496v5","created_at":"2026-07-05T10:33:05.234432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10496","created_at":"2026-07-05T10:33:05.234432+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6ZJVXCFYJWX","created_at":"2026-07-05T10:33:05.234432+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6ZJVXCFYJWXIARX","created_at":"2026-07-05T10:33:05.234432+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6ZJVXCF","created_at":"2026-07-05T10:33:05.234432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02937","citing_title":"If It's Good Enough for You, It's Good Enough for Me: Transferability of Audio Sufficiencies across Models","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R6ZJVXCFYJWXIARXGCWL2GPFI7","json":"https://pith.science/pith/R6ZJVXCFYJWXIARXGCWL2GPFI7.json","graph_json":"https://pith.science/api/pith-number/R6ZJVXCFYJWXIARXGCWL2GPFI7/graph.json","events_json":"https://pith.science/api/pith-number/R6ZJVXCFYJWXIARXGCWL2GPFI7/events.json","paper":"https://pith.science/paper/R6ZJVXCF"},"agent_actions":{"view_html":"https://pith.science/pith/R6ZJVXCFYJWXIARXGCWL2GPFI7","download_json":"https://pith.science/pith/R6ZJVXCFYJWXIARXGCWL2GPFI7.json","view_paper":"https://pith.science/paper/R6ZJVXCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10496&json=true","fetch_graph":"https://pith.science/api/pith-number/R6ZJVXCFYJWXIARXGCWL2GPFI7/graph.json","fetch_events":"https://pith.science/api/pith-number/R6ZJVXCFYJWXIARXGCWL2GPFI7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6ZJVXCFYJWXIARXGCWL2GPFI7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6ZJVXCFYJWXIARXGCWL2GPFI7/action/storage_attestation","attest_author":"https://pith.science/pith/R6ZJVXCFYJWXIARXGCWL2GPFI7/action/author_attestation","sign_citation":"https://pith.science/pith/R6ZJVXCFYJWXIARXGCWL2GPFI7/action/citation_signature","submit_replication":"https://pith.science/pith/R6ZJVXCFYJWXIARXGCWL2GPFI7/action/replication_record"}},"created_at":"2026-07-05T10:33:05.234432+00:00","updated_at":"2026-07-05T10:33:05.234432+00:00"}