{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SMFL4XYXZMII4APZ5FBNLBDFPI","short_pith_number":"pith:SMFL4XYX","schema_version":"1.0","canonical_sha256":"930abe5f17cb108e01f9e942d584657a103f952d22fdbecef504132e8e92d72c","source":{"kind":"arxiv","id":"2501.15177","version":3},"attestation_state":"computed","paper":{"title":"Audio-Language Models for Audio-Centric Tasks: A Systematic Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jisheng Bai, Kele Xu, Qisheng Xu, Yi Su, Yong Dou","submitted_at":"2025-01-25T11:15:06Z","abstract_excerpt":"Audio-Language Models (ALMs), trained on paired audio-text data, are designed to process, understand, and reason about audio-centric multimodal content. Unlike traditional supervised approaches that use predefined labels, ALMs leverage natural language supervision to better handle complex real-world audio scenes with multiple overlapping events. While demonstrating impressive zero-shot and task generalization capabilities, there is still a notable lack of systematic surveys that comprehensively organize and analyze developments. In this paper, we present the first systematic review of ALMs wit"},"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":"2501.15177","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-25T11:15:06Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"963add4d977165d2f1d03e4ff6a965d4e548eab6d30543ed3fc61cbdf87ce226","abstract_canon_sha256":"631986dcf9e9c8757b7701fc8f10005267adc8f1ed0f9851c144af57d80a86d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:17:05.480147Z","signature_b64":"5BcpjM9aHykgjXQrFJM3gERbVzsAawCxNk5iyPJWyv93CIhvnO5hwqPA0dnEhWROiBY2UXYUlVxheCiFW3N0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"930abe5f17cb108e01f9e942d584657a103f952d22fdbecef504132e8e92d72c","last_reissued_at":"2026-07-07T02:17:05.479404Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:17:05.479404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Language Models for Audio-Centric Tasks: A Systematic Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jisheng Bai, Kele Xu, Qisheng Xu, Yi Su, Yong Dou","submitted_at":"2025-01-25T11:15:06Z","abstract_excerpt":"Audio-Language Models (ALMs), trained on paired audio-text data, are designed to process, understand, and reason about audio-centric multimodal content. Unlike traditional supervised approaches that use predefined labels, ALMs leverage natural language supervision to better handle complex real-world audio scenes with multiple overlapping events. While demonstrating impressive zero-shot and task generalization capabilities, there is still a notable lack of systematic surveys that comprehensively organize and analyze developments. In this paper, we present the first systematic review of ALMs wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15177","kind":"arxiv","version":3},"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/2501.15177/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":"2501.15177","created_at":"2026-07-07T02:17:05.479511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15177v3","created_at":"2026-07-07T02:17:05.479511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15177","created_at":"2026-07-07T02:17:05.479511+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMFL4XYXZMII","created_at":"2026-07-07T02:17:05.479511+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMFL4XYXZMII4APZ","created_at":"2026-07-07T02:17:05.479511+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMFL4XYX","created_at":"2026-07-07T02:17:05.479511+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":13,"sample":[{"citing_arxiv_id":"2606.22868","citing_title":"MSU-Bench: Towards Speaker-Centric Understanding in Conversational Multi-Speaker Scenarios","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21147","citing_title":"AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries?","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17404","citing_title":"ELSA: Acoustic Event-Level Semantic Alignment for Fine-Grained Reference-Free Text-to-Audio Evaluation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2606.15088","citing_title":"When the Same Musical Knowledge Forgets Differently: A Clean Probe of Pathway-Dependent Forgetting","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2606.08194","citing_title":"GlobeAudio: A Multilingual Multicultural Benchmark for Naturalistic Evaluation of Large Audio-Language Models","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07309","citing_title":"Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognition","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":180,"is_internal_anchor":true},{"citing_arxiv_id":"2605.27190","citing_title":"Learning When to Think While Listening in Large Audio-Language Models","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20266","citing_title":"A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21008","citing_title":"A Survey of Audio Reasoning in Multimodal Foundation Models","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16659","citing_title":"Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMFL4XYXZMII4APZ5FBNLBDFPI","json":"https://pith.science/pith/SMFL4XYXZMII4APZ5FBNLBDFPI.json","graph_json":"https://pith.science/api/pith-number/SMFL4XYXZMII4APZ5FBNLBDFPI/graph.json","events_json":"https://pith.science/api/pith-number/SMFL4XYXZMII4APZ5FBNLBDFPI/events.json","paper":"https://pith.science/paper/SMFL4XYX"},"agent_actions":{"view_html":"https://pith.science/pith/SMFL4XYXZMII4APZ5FBNLBDFPI","download_json":"https://pith.science/pith/SMFL4XYXZMII4APZ5FBNLBDFPI.json","view_paper":"https://pith.science/paper/SMFL4XYX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15177&json=true","fetch_graph":"https://pith.science/api/pith-number/SMFL4XYXZMII4APZ5FBNLBDFPI/graph.json","fetch_events":"https://pith.science/api/pith-number/SMFL4XYXZMII4APZ5FBNLBDFPI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMFL4XYXZMII4APZ5FBNLBDFPI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMFL4XYXZMII4APZ5FBNLBDFPI/action/storage_attestation","attest_author":"https://pith.science/pith/SMFL4XYXZMII4APZ5FBNLBDFPI/action/author_attestation","sign_citation":"https://pith.science/pith/SMFL4XYXZMII4APZ5FBNLBDFPI/action/citation_signature","submit_replication":"https://pith.science/pith/SMFL4XYXZMII4APZ5FBNLBDFPI/action/replication_record"}},"created_at":"2026-07-07T02:17:05.479511+00:00","updated_at":"2026-07-07T02:17:05.479511+00:00"}