{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SOCIOHNIOWYGBHO2TOL4VNUQR4","short_pith_number":"pith:SOCIOHNI","schema_version":"1.0","canonical_sha256":"9384871da875b0609dda9b97cab6908f2b6a7d61c150ed5fb3d0c70a92d0fc1f","source":{"kind":"arxiv","id":"2402.00282","version":1},"attestation_state":"computed","paper":{"title":"PAM: Prompting Audio-Language Models for Audio Quality Assessment","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Benjamin Elizalde, Bhiksha Raj, Dareen Alharthi, Hannes Gamper, Huaming Wang, Mahmoud Al Ismail, Rita Singh, Soham Deshmukh","submitted_at":"2024-02-01T02:15:59Z","abstract_excerpt":"While audio quality is a key performance metric for various audio processing tasks, including generative modeling, its objective measurement remains a challenge. Audio-Language Models (ALMs) are pre-trained on audio-text pairs that may contain information about audio quality, the presence of artifacts, or noise. Given an audio input and a text prompt related to quality, an ALM can be used to calculate a similarity score between the two. Here, we exploit this capability and introduce PAM, a no-reference metric for assessing audio quality for different audio processing tasks. Contrary to other \""},"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":"2402.00282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-01T02:15:59Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"eccb0d108d3d117191f9da45c61451663502fa5ac3e50a6a275a4d44b095933a","abstract_canon_sha256":"5bab69ad1ac7f0c63581a0f1866d9d419c0dde316346c64008b97eed7bb9f7cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:09.447884Z","signature_b64":"VhOznm8ERdIs0K5p3OYLmEC67RzYK5/C9dlsmixU7CbrOSJNHmibVRc7Hq+DFjgKwA1I8aMF+ej5kitLfTHyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9384871da875b0609dda9b97cab6908f2b6a7d61c150ed5fb3d0c70a92d0fc1f","last_reissued_at":"2026-07-05T07:40:09.447373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:09.447373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAM: Prompting Audio-Language Models for Audio Quality Assessment","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Benjamin Elizalde, Bhiksha Raj, Dareen Alharthi, Hannes Gamper, Huaming Wang, Mahmoud Al Ismail, Rita Singh, Soham Deshmukh","submitted_at":"2024-02-01T02:15:59Z","abstract_excerpt":"While audio quality is a key performance metric for various audio processing tasks, including generative modeling, its objective measurement remains a challenge. Audio-Language Models (ALMs) are pre-trained on audio-text pairs that may contain information about audio quality, the presence of artifacts, or noise. Given an audio input and a text prompt related to quality, an ALM can be used to calculate a similarity score between the two. Here, we exploit this capability and introduce PAM, a no-reference metric for assessing audio quality for different audio processing tasks. Contrary to other \""},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00282","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/2402.00282/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":"2402.00282","created_at":"2026-07-05T07:40:09.447436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00282v1","created_at":"2026-07-05T07:40:09.447436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00282","created_at":"2026-07-05T07:40:09.447436+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOCIOHNIOWYG","created_at":"2026-07-05T07:40:09.447436+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOCIOHNIOWYGBHO2","created_at":"2026-07-05T07:40:09.447436+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOCIOHNI","created_at":"2026-07-05T07:40:09.447436+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":206,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05139","citing_title":"Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SOCIOHNIOWYGBHO2TOL4VNUQR4","json":"https://pith.science/pith/SOCIOHNIOWYGBHO2TOL4VNUQR4.json","graph_json":"https://pith.science/api/pith-number/SOCIOHNIOWYGBHO2TOL4VNUQR4/graph.json","events_json":"https://pith.science/api/pith-number/SOCIOHNIOWYGBHO2TOL4VNUQR4/events.json","paper":"https://pith.science/paper/SOCIOHNI"},"agent_actions":{"view_html":"https://pith.science/pith/SOCIOHNIOWYGBHO2TOL4VNUQR4","download_json":"https://pith.science/pith/SOCIOHNIOWYGBHO2TOL4VNUQR4.json","view_paper":"https://pith.science/paper/SOCIOHNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00282&json=true","fetch_graph":"https://pith.science/api/pith-number/SOCIOHNIOWYGBHO2TOL4VNUQR4/graph.json","fetch_events":"https://pith.science/api/pith-number/SOCIOHNIOWYGBHO2TOL4VNUQR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOCIOHNIOWYGBHO2TOL4VNUQR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOCIOHNIOWYGBHO2TOL4VNUQR4/action/storage_attestation","attest_author":"https://pith.science/pith/SOCIOHNIOWYGBHO2TOL4VNUQR4/action/author_attestation","sign_citation":"https://pith.science/pith/SOCIOHNIOWYGBHO2TOL4VNUQR4/action/citation_signature","submit_replication":"https://pith.science/pith/SOCIOHNIOWYGBHO2TOL4VNUQR4/action/replication_record"}},"created_at":"2026-07-05T07:40:09.447436+00:00","updated_at":"2026-07-05T07:40:09.447436+00:00"}