{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TJCNSCR4UKAKULMCXQ4CRONTKL","short_pith_number":"pith:TJCNSCR4","schema_version":"1.0","canonical_sha256":"9a44d90a3ca280aa2d82bc3828b9b352df33323b9a4e3ddf2625c35fa4f86f4e","source":{"kind":"arxiv","id":"2402.09585","version":2},"attestation_state":"computed","paper":{"title":"Domain Adaptation for Contrastive Audio-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bhiksha Raj, Rita Singh, Soham Deshmukh","submitted_at":"2024-02-14T21:25:06Z","abstract_excerpt":"Audio-Language Models (ALM) aim to be general-purpose audio models by providing zero-shot capabilities at test time. The zero-shot performance of ALM improves by using suitable text prompts for each domain. The text prompts are usually hand-crafted through an ad-hoc process and lead to a drop in ALM generalization and out-of-distribution performance. Existing approaches to improve domain performance, like few-shot learning or fine-tuning, require access to annotated data and iterations of training. Therefore, we propose a test-time domain adaptation method for ALMs that does not require access"},"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":"2402.09585","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-14T21:25:06Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"06f1dac7817846912326f0afcd20cfb5780d1f90ab492fb164076bfaf2159f37","abstract_canon_sha256":"d410f4f56c0932df1c080c06df660e274ebf1ad26637f1b27748cba588272991"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:21.470984Z","signature_b64":"wcz8fbEoD/Jwy4K0mpTxEjH0fO0K8v/RQ0Zvq6lJ0I4g/48d8s88UHX6PSug67W0Nsr6amwgtT5LYqMnQAk6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a44d90a3ca280aa2d82bc3828b9b352df33323b9a4e3ddf2625c35fa4f86f4e","last_reissued_at":"2026-07-05T08:46:21.470606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:21.470606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Adaptation for Contrastive Audio-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bhiksha Raj, Rita Singh, Soham Deshmukh","submitted_at":"2024-02-14T21:25:06Z","abstract_excerpt":"Audio-Language Models (ALM) aim to be general-purpose audio models by providing zero-shot capabilities at test time. The zero-shot performance of ALM improves by using suitable text prompts for each domain. The text prompts are usually hand-crafted through an ad-hoc process and lead to a drop in ALM generalization and out-of-distribution performance. Existing approaches to improve domain performance, like few-shot learning or fine-tuning, require access to annotated data and iterations of training. Therefore, we propose a test-time domain adaptation method for ALMs that does not require access"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09585","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/2402.09585/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":"2402.09585","created_at":"2026-07-05T08:46:21.470662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09585v2","created_at":"2026-07-05T08:46:21.470662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09585","created_at":"2026-07-05T08:46:21.470662+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJCNSCR4UKAK","created_at":"2026-07-05T08:46:21.470662+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJCNSCR4UKAKULMC","created_at":"2026-07-05T08:46:21.470662+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJCNSCR4","created_at":"2026-07-05T08:46:21.470662+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.04376","citing_title":"Domain Adaptation Method and Modality Gap Impact in Audio-Text Models for Prototypical Sound Classification","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TJCNSCR4UKAKULMCXQ4CRONTKL","json":"https://pith.science/pith/TJCNSCR4UKAKULMCXQ4CRONTKL.json","graph_json":"https://pith.science/api/pith-number/TJCNSCR4UKAKULMCXQ4CRONTKL/graph.json","events_json":"https://pith.science/api/pith-number/TJCNSCR4UKAKULMCXQ4CRONTKL/events.json","paper":"https://pith.science/paper/TJCNSCR4"},"agent_actions":{"view_html":"https://pith.science/pith/TJCNSCR4UKAKULMCXQ4CRONTKL","download_json":"https://pith.science/pith/TJCNSCR4UKAKULMCXQ4CRONTKL.json","view_paper":"https://pith.science/paper/TJCNSCR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09585&json=true","fetch_graph":"https://pith.science/api/pith-number/TJCNSCR4UKAKULMCXQ4CRONTKL/graph.json","fetch_events":"https://pith.science/api/pith-number/TJCNSCR4UKAKULMCXQ4CRONTKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJCNSCR4UKAKULMCXQ4CRONTKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJCNSCR4UKAKULMCXQ4CRONTKL/action/storage_attestation","attest_author":"https://pith.science/pith/TJCNSCR4UKAKULMCXQ4CRONTKL/action/author_attestation","sign_citation":"https://pith.science/pith/TJCNSCR4UKAKULMCXQ4CRONTKL/action/citation_signature","submit_replication":"https://pith.science/pith/TJCNSCR4UKAKULMCXQ4CRONTKL/action/replication_record"}},"created_at":"2026-07-05T08:46:21.470662+00:00","updated_at":"2026-07-05T08:46:21.470662+00:00"}