{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WZEEDQYE4C6LG6QS6EXQM2YE3J","short_pith_number":"pith:WZEEDQYE","canonical_record":{"source":{"id":"2509.20641","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-25T00:56:35Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"cc8e22324138315582279f69485da4abfd80d00081ed380ea7d4f148c29bf17a","abstract_canon_sha256":"77bf7d765be5c8a63fff978b7baef8e07541ee5854d5b1189e23b7fa153e4959"},"schema_version":"1.0"},"canonical_sha256":"b64841c304e0bcb37a12f12f066b04da7507a10fb1f3936c0a29d7d474a365f8","source":{"kind":"arxiv","id":"2509.20641","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.20641","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"arxiv_version","alias_value":"2509.20641v2","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.20641","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"pith_short_12","alias_value":"WZEEDQYE4C6L","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"pith_short_16","alias_value":"WZEEDQYE4C6LG6QS","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"pith_short_8","alias_value":"WZEEDQYE","created_at":"2026-05-20T00:01:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WZEEDQYE4C6LG6QS6EXQM2YE3J","target":"record","payload":{"canonical_record":{"source":{"id":"2509.20641","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-25T00:56:35Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"cc8e22324138315582279f69485da4abfd80d00081ed380ea7d4f148c29bf17a","abstract_canon_sha256":"77bf7d765be5c8a63fff978b7baef8e07541ee5854d5b1189e23b7fa153e4959"},"schema_version":"1.0"},"canonical_sha256":"b64841c304e0bcb37a12f12f066b04da7507a10fb1f3936c0a29d7d474a365f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:35.526859Z","signature_b64":"LoUzrrFaMXrWwX2ZdETFf8zlY7At4QKSbF0V/3mD9HRbL8JBKbkaLXzWwEjUZX9B0GmGXv6YqauOUwqo2uOdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b64841c304e0bcb37a12f12f066b04da7507a10fb1f3936c0a29d7d474a365f8","last_reissued_at":"2026-05-20T00:01:35.526024Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:35.526024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.20641","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":"2026-05-20T00:01:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"28DGmOnFUuZ5P3DZGSI2TCzzW6Yh9mPVS7dYAqyEVowSfB0cHugMBW2zPZgvPu6Psp8QQt25IJv0uU+dU/D1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T14:58:13.195985Z"},"content_sha256":"02c6d1daf0a4c652ddc2e92bf442e9d8ec0edddb4218c4eb3cbefdd8109afad5","schema_version":"1.0","event_id":"sha256:02c6d1daf0a4c652ddc2e92bf442e9d8ec0edddb4218c4eb3cbefdd8109afad5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WZEEDQYE4C6LG6QS6EXQM2YE3J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Modality Contribution in Audio LLMs for Music","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.LG","authors_text":"Giovana Morais, Magdalena Fuentes","submitted_at":"2025-09-25T00:56:35Z","abstract_excerpt":"Audio Large Language Models (Audio LLMs) enable human-like conversation about music, yet it is unclear if they are truly listening to the audio or just using textual reasoning, as recent benchmarks suggest. This paper investigates this issue by quantifying the contribution of each modality to a model's output. We adapt the MM-SHAP framework, a performance-agnostic score based on Shapley values that quantifies the relative contribution of each modality to a model's prediction. We evaluate two models on the MuChoMusic benchmark and find that the model with higher accuracy relies more on text to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.20641","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/2509.20641/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":"2026-05-20T00:01:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cb4+qq3mBTf0tWcYz0yrml2ovbDnX0CVXMfmsbDPNTkbDUafjlS1EnxFAhqNcFpKb+3DIMA5z0UmNcwRSmQHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T14:58:13.196818Z"},"content_sha256":"3ae4b89889515bc156a44c0bf6b60ea4aeafdc3d3c9494001db6610363382d42","schema_version":"1.0","event_id":"sha256:3ae4b89889515bc156a44c0bf6b60ea4aeafdc3d3c9494001db6610363382d42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WZEEDQYE4C6LG6QS6EXQM2YE3J/bundle.json","state_url":"https://pith.science/pith/WZEEDQYE4C6LG6QS6EXQM2YE3J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WZEEDQYE4C6LG6QS6EXQM2YE3J/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":"2026-06-10T14:58:13Z","links":{"resolver":"https://pith.science/pith/WZEEDQYE4C6LG6QS6EXQM2YE3J","bundle":"https://pith.science/pith/WZEEDQYE4C6LG6QS6EXQM2YE3J/bundle.json","state":"https://pith.science/pith/WZEEDQYE4C6LG6QS6EXQM2YE3J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WZEEDQYE4C6LG6QS6EXQM2YE3J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WZEEDQYE4C6LG6QS6EXQM2YE3J","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":"77bf7d765be5c8a63fff978b7baef8e07541ee5854d5b1189e23b7fa153e4959","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-25T00:56:35Z","title_canon_sha256":"cc8e22324138315582279f69485da4abfd80d00081ed380ea7d4f148c29bf17a"},"schema_version":"1.0","source":{"id":"2509.20641","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.20641","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"arxiv_version","alias_value":"2509.20641v2","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.20641","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"pith_short_12","alias_value":"WZEEDQYE4C6L","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"pith_short_16","alias_value":"WZEEDQYE4C6LG6QS","created_at":"2026-05-20T00:01:35Z"},{"alias_kind":"pith_short_8","alias_value":"WZEEDQYE","created_at":"2026-05-20T00:01:35Z"}],"graph_snapshots":[{"event_id":"sha256:3ae4b89889515bc156a44c0bf6b60ea4aeafdc3d3c9494001db6610363382d42","target":"graph","created_at":"2026-05-20T00:01:35Z","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/2509.20641/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio Large Language Models (Audio LLMs) enable human-like conversation about music, yet it is unclear if they are truly listening to the audio or just using textual reasoning, as recent benchmarks suggest. This paper investigates this issue by quantifying the contribution of each modality to a model's output. We adapt the MM-SHAP framework, a performance-agnostic score based on Shapley values that quantifies the relative contribution of each modality to a model's prediction. We evaluate two models on the MuChoMusic benchmark and find that the model with higher accuracy relies more on text to ","authors_text":"Giovana Morais, Magdalena Fuentes","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-25T00:56:35Z","title":"Investigating Modality Contribution in Audio LLMs for Music"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.20641","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":"sha256:02c6d1daf0a4c652ddc2e92bf442e9d8ec0edddb4218c4eb3cbefdd8109afad5","target":"record","created_at":"2026-05-20T00:01:35Z","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":"77bf7d765be5c8a63fff978b7baef8e07541ee5854d5b1189e23b7fa153e4959","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-25T00:56:35Z","title_canon_sha256":"cc8e22324138315582279f69485da4abfd80d00081ed380ea7d4f148c29bf17a"},"schema_version":"1.0","source":{"id":"2509.20641","kind":"arxiv","version":2}},"canonical_sha256":"b64841c304e0bcb37a12f12f066b04da7507a10fb1f3936c0a29d7d474a365f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b64841c304e0bcb37a12f12f066b04da7507a10fb1f3936c0a29d7d474a365f8","first_computed_at":"2026-05-20T00:01:35.526024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:35.526024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LoUzrrFaMXrWwX2ZdETFf8zlY7At4QKSbF0V/3mD9HRbL8JBKbkaLXzWwEjUZX9B0GmGXv6YqauOUwqo2uOdCw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:35.526859Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.20641","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02c6d1daf0a4c652ddc2e92bf442e9d8ec0edddb4218c4eb3cbefdd8109afad5","sha256:3ae4b89889515bc156a44c0bf6b60ea4aeafdc3d3c9494001db6610363382d42"],"state_sha256":"5d69214ec06d60ad44d77bff465f8184eca6ce9026efa487c1572cd1047c2f27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tkf+mSlJNtPWzXq+R+CuzlsCWh8akVpxc67c9HpelSzVeaIBvRZ2h6DHe+lynyvhgYHmRspj6tZvxxdvE/yDCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T14:58:13.200940Z","bundle_sha256":"a827d878984851e6d886c3540d5f00d3dcb5dacf5b46f232837c81180a6cd03a"}}