{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EJLCXXSQ6DYJHT2VLX45TGKKSC","short_pith_number":"pith:EJLCXXSQ","canonical_record":{"source":{"id":"2506.05140","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T15:22:47Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"2fe86952217eb07c54abf4816ade3f112b678465240bdc83c2462502b79b93a7","abstract_canon_sha256":"4e06bcce4a5562c54ef20f96b464f74b75edd737052e0d05b088c412f209b16e"},"schema_version":"1.0"},"canonical_sha256":"22562bde50f0f093cf555df9d9994a908bd6445d21eb614f93111bd473421859","source":{"kind":"arxiv","id":"2506.05140","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05140","created_at":"2026-07-05T11:58:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05140v2","created_at":"2026-07-05T11:58:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05140","created_at":"2026-07-05T11:58:30Z"},{"alias_kind":"pith_short_12","alias_value":"EJLCXXSQ6DYJ","created_at":"2026-07-05T11:58:30Z"},{"alias_kind":"pith_short_16","alias_value":"EJLCXXSQ6DYJHT2V","created_at":"2026-07-05T11:58:30Z"},{"alias_kind":"pith_short_8","alias_value":"EJLCXXSQ","created_at":"2026-07-05T11:58:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EJLCXXSQ6DYJHT2VLX45TGKKSC","target":"record","payload":{"canonical_record":{"source":{"id":"2506.05140","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T15:22:47Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"2fe86952217eb07c54abf4816ade3f112b678465240bdc83c2462502b79b93a7","abstract_canon_sha256":"4e06bcce4a5562c54ef20f96b464f74b75edd737052e0d05b088c412f209b16e"},"schema_version":"1.0"},"canonical_sha256":"22562bde50f0f093cf555df9d9994a908bd6445d21eb614f93111bd473421859","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:30.766579Z","signature_b64":"EuhkvTrhiiK6eLsic4WLoZBFVDVNBJ5sKsISfR6isDAjZVnKPgw7iSbqqRRTZGhsvBkUE1+jYrWu1eo6QoKgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22562bde50f0f093cf555df9d9994a908bd6445d21eb614f93111bd473421859","last_reissued_at":"2026-07-05T11:58:30.766117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:30.766117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.05140","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":"2026-07-05T11:58:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sBXWG4SYfkbeLlP7yhS3akZxW9nDrqn7GsbkO5vGsT523r1f1V2BxnO/4S7LaPZ489OpEkcvZgq4V4cZwexTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:09:52.945288Z"},"content_sha256":"8313b78389db65e6d90be82f123d94c6d486d8e8bff9a534ae45c50aa9e10b82","schema_version":"1.0","event_id":"sha256:8313b78389db65e6d90be82f123d94c6d486d8e8bff9a534ae45c50aa9e10b82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EJLCXXSQ6DYJHT2VLX45TGKKSC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chih-Kai Yang, Hung-yi Lee, Neo Ho, Yi-Jyun Lee","submitted_at":"2025-06-05T15:22:47Z","abstract_excerpt":"Understanding the internal mechanisms of large audio-language models (LALMs) is crucial for interpreting their behavior and improving performance. This work presents the first in-depth analysis of how LALMs internally perceive and recognize auditory attributes. By applying vocabulary projection on three state-of-the-art LALMs, we track how attribute information evolves across layers and token positions. We find that attribute information generally decreases with layer depth when recognition fails, and that resolving attributes at earlier layers correlates with better accuracy. Moreover, LALMs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05140","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/2506.05140/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":"2026-07-05T11:58:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UNailDVm3bhOBk7jf3xghSsSIHyCz/mjlP9iYIAXNN9ZcxSr4gYIcNk9k3l6fwvliLAIejHGMlfOQca6gNl4Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:09:52.945795Z"},"content_sha256":"9ea9d6777ccb8a5b5847c7353ef5ecdd4ce80836ede4aaa58c5a21e7090d7b54","schema_version":"1.0","event_id":"sha256:9ea9d6777ccb8a5b5847c7353ef5ecdd4ce80836ede4aaa58c5a21e7090d7b54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EJLCXXSQ6DYJHT2VLX45TGKKSC/bundle.json","state_url":"https://pith.science/pith/EJLCXXSQ6DYJHT2VLX45TGKKSC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EJLCXXSQ6DYJHT2VLX45TGKKSC/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":"2026-08-08T03:09:52Z","links":{"resolver":"https://pith.science/pith/EJLCXXSQ6DYJHT2VLX45TGKKSC","bundle":"https://pith.science/pith/EJLCXXSQ6DYJHT2VLX45TGKKSC/bundle.json","state":"https://pith.science/pith/EJLCXXSQ6DYJHT2VLX45TGKKSC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EJLCXXSQ6DYJHT2VLX45TGKKSC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EJLCXXSQ6DYJHT2VLX45TGKKSC","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":"4e06bcce4a5562c54ef20f96b464f74b75edd737052e0d05b088c412f209b16e","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T15:22:47Z","title_canon_sha256":"2fe86952217eb07c54abf4816ade3f112b678465240bdc83c2462502b79b93a7"},"schema_version":"1.0","source":{"id":"2506.05140","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05140","created_at":"2026-07-05T11:58:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05140v2","created_at":"2026-07-05T11:58:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05140","created_at":"2026-07-05T11:58:30Z"},{"alias_kind":"pith_short_12","alias_value":"EJLCXXSQ6DYJ","created_at":"2026-07-05T11:58:30Z"},{"alias_kind":"pith_short_16","alias_value":"EJLCXXSQ6DYJHT2V","created_at":"2026-07-05T11:58:30Z"},{"alias_kind":"pith_short_8","alias_value":"EJLCXXSQ","created_at":"2026-07-05T11:58:30Z"}],"graph_snapshots":[{"event_id":"sha256:9ea9d6777ccb8a5b5847c7353ef5ecdd4ce80836ede4aaa58c5a21e7090d7b54","target":"graph","created_at":"2026-07-05T11:58:30Z","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/2506.05140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the internal mechanisms of large audio-language models (LALMs) is crucial for interpreting their behavior and improving performance. This work presents the first in-depth analysis of how LALMs internally perceive and recognize auditory attributes. By applying vocabulary projection on three state-of-the-art LALMs, we track how attribute information evolves across layers and token positions. We find that attribute information generally decreases with layer depth when recognition fails, and that resolving attributes at earlier layers correlates with better accuracy. Moreover, LALMs ","authors_text":"Chih-Kai Yang, Hung-yi Lee, Neo Ho, Yi-Jyun Lee","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T15:22:47Z","title":"AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05140","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":"sha256:8313b78389db65e6d90be82f123d94c6d486d8e8bff9a534ae45c50aa9e10b82","target":"record","created_at":"2026-07-05T11:58:30Z","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":"4e06bcce4a5562c54ef20f96b464f74b75edd737052e0d05b088c412f209b16e","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T15:22:47Z","title_canon_sha256":"2fe86952217eb07c54abf4816ade3f112b678465240bdc83c2462502b79b93a7"},"schema_version":"1.0","source":{"id":"2506.05140","kind":"arxiv","version":2}},"canonical_sha256":"22562bde50f0f093cf555df9d9994a908bd6445d21eb614f93111bd473421859","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22562bde50f0f093cf555df9d9994a908bd6445d21eb614f93111bd473421859","first_computed_at":"2026-07-05T11:58:30.766117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:30.766117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EuhkvTrhiiK6eLsic4WLoZBFVDVNBJ5sKsISfR6isDAjZVnKPgw7iSbqqRRTZGhsvBkUE1+jYrWu1eo6QoKgAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:30.766579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05140","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8313b78389db65e6d90be82f123d94c6d486d8e8bff9a534ae45c50aa9e10b82","sha256:9ea9d6777ccb8a5b5847c7353ef5ecdd4ce80836ede4aaa58c5a21e7090d7b54"],"state_sha256":"a7775f14e069b810e7999d467032828a2e84fdf7450c1171f2750b34f8ecc02e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VuROd51lxtfk1eoYCB2Uq2V3bA7JfqTgnJ4tG0zaVrD7mn3NCjSPHBBfulGIdLIrM8mP21YsDAwwYYwWL4BCDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:09:52.951226Z","bundle_sha256":"671c92b37e620af12593452580ea3b09f3555ed95cde0ad457862d861164dc4e"}}