{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KCWL6KGALS2KFV5Y63EQF4GR7J","short_pith_number":"pith:KCWL6KGA","schema_version":"1.0","canonical_sha256":"50acbf28c05cb4a2d7b8f6c902f0d1fa4e026c7eea97ba12a953a4654e877ce2","source":{"kind":"arxiv","id":"2606.07531","version":1},"attestation_state":"computed","paper":{"title":"mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jakub Muszy\\'nski, Maria Ganzha, Pawe{\\l} Pozorski","submitted_at":"2026-04-21T10:01:51Z","abstract_excerpt":"We introduce mllm-shap, an open-source Python framework designed to extend Shapley Value (SV) explainability from text-only Large Language Models to Multimodal LLMs (MLLMs) processing joint text and audio inputs. While text-based attribution is well-studied, mllm-shap addresses three critical challenges unique to the multimodal regime:\n  (1) Modality-aware coalition masking, which manages the interleaved processing of discrete text tokens and dense audio encoder frames.\n  (2) Multi-turn conversation tracking, utilizing per-token metadata to maintain role and modality context.\n  (3) Phonetic al"},"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":"2606.07531","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-21T10:01:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7ceea663557ffc47f2a305e7be4ba0979052199c23db7167cc868833e916a43e","abstract_canon_sha256":"5c2226b326d00b7799c5aba18b1cfdd66adee53bce2d303744e284edf667a598"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T00:04:41.829509Z","signature_b64":"d4GBh4NUTCpKBF371zWpI2PFZvPfLmN4QplTft+gtJYzDJZor+i14elN4/OqxAB4cbVvC+OVXsAi4EA+x0HSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50acbf28c05cb4a2d7b8f6c902f0d1fa4e026c7eea97ba12a953a4654e877ce2","last_reissued_at":"2026-06-09T00:04:41.828767Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T00:04:41.828767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jakub Muszy\\'nski, Maria Ganzha, Pawe{\\l} Pozorski","submitted_at":"2026-04-21T10:01:51Z","abstract_excerpt":"We introduce mllm-shap, an open-source Python framework designed to extend Shapley Value (SV) explainability from text-only Large Language Models to Multimodal LLMs (MLLMs) processing joint text and audio inputs. While text-based attribution is well-studied, mllm-shap addresses three critical challenges unique to the multimodal regime:\n  (1) Modality-aware coalition masking, which manages the interleaved processing of discrete text tokens and dense audio encoder frames.\n  (2) Multi-turn conversation tracking, utilizing per-token metadata to maintain role and modality context.\n  (3) Phonetic al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07531","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/2606.07531/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":"2606.07531","created_at":"2026-06-09T00:04:41.828873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07531v1","created_at":"2026-06-09T00:04:41.828873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07531","created_at":"2026-06-09T00:04:41.828873+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCWL6KGALS2K","created_at":"2026-06-09T00:04:41.828873+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCWL6KGALS2KFV5Y","created_at":"2026-06-09T00:04:41.828873+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCWL6KGA","created_at":"2026-06-09T00:04:41.828873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KCWL6KGALS2KFV5Y63EQF4GR7J","json":"https://pith.science/pith/KCWL6KGALS2KFV5Y63EQF4GR7J.json","graph_json":"https://pith.science/api/pith-number/KCWL6KGALS2KFV5Y63EQF4GR7J/graph.json","events_json":"https://pith.science/api/pith-number/KCWL6KGALS2KFV5Y63EQF4GR7J/events.json","paper":"https://pith.science/paper/KCWL6KGA"},"agent_actions":{"view_html":"https://pith.science/pith/KCWL6KGALS2KFV5Y63EQF4GR7J","download_json":"https://pith.science/pith/KCWL6KGALS2KFV5Y63EQF4GR7J.json","view_paper":"https://pith.science/paper/KCWL6KGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07531&json=true","fetch_graph":"https://pith.science/api/pith-number/KCWL6KGALS2KFV5Y63EQF4GR7J/graph.json","fetch_events":"https://pith.science/api/pith-number/KCWL6KGALS2KFV5Y63EQF4GR7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCWL6KGALS2KFV5Y63EQF4GR7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCWL6KGALS2KFV5Y63EQF4GR7J/action/storage_attestation","attest_author":"https://pith.science/pith/KCWL6KGALS2KFV5Y63EQF4GR7J/action/author_attestation","sign_citation":"https://pith.science/pith/KCWL6KGALS2KFV5Y63EQF4GR7J/action/citation_signature","submit_replication":"https://pith.science/pith/KCWL6KGALS2KFV5Y63EQF4GR7J/action/replication_record"}},"created_at":"2026-06-09T00:04:41.828873+00:00","updated_at":"2026-06-09T00:04:41.828873+00:00"}