{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M6VYR4ZH2CBGRCJMEX3WRBG4UE","short_pith_number":"pith:M6VYR4ZH","schema_version":"1.0","canonical_sha256":"67ab88f327d08268892c25f76884dca10f6e04e05d0157a8505e876060ccf1d2","source":{"kind":"arxiv","id":"2501.00398","version":2},"attestation_state":"computed","paper":{"title":"TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ashish Seth, Dinesh Manocha, Nishit Anand, Ramani Duraiswami","submitted_at":"2024-12-31T11:27:17Z","abstract_excerpt":"Audio-language models (ALMs) excel in zero-shot audio classification, a task where models classify previously unseen audio clips at test time by leveraging descriptive natural language prompts. We introduce TSPE (Task-Specific Prompt Ensemble), a simple, training-free hard prompting method that boosts ALEs' zero-shot performance by customizing prompts for diverse audio classification tasks. Rather than using generic template-based prompts like \"Sound of a car\" we generate context-rich prompts, such as \"Sound of a car coming from a tunnel\". Specifically, we leverage label information to identif"},"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":"2501.00398","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-31T11:27:17Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"fb007957d93063631d75c061fd5ef641e652a3ecdb706b2675a2b82b292ab972","abstract_canon_sha256":"3bd62b4331d114229278d6cbb5c7c707c0df4c1d999a0b8423dc1afce41b75c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:42.570209Z","signature_b64":"twOhWYm+3pbS1N/q7jXfwS4ETThmMdsdHo1CMIbDtes3LwId3O+TrYwbEHtcX/0MKMsWvjHQ/fO8nB21J8jyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67ab88f327d08268892c25f76884dca10f6e04e05d0157a8505e876060ccf1d2","last_reissued_at":"2026-07-05T10:43:42.569698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:42.569698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ashish Seth, Dinesh Manocha, Nishit Anand, Ramani Duraiswami","submitted_at":"2024-12-31T11:27:17Z","abstract_excerpt":"Audio-language models (ALMs) excel in zero-shot audio classification, a task where models classify previously unseen audio clips at test time by leveraging descriptive natural language prompts. We introduce TSPE (Task-Specific Prompt Ensemble), a simple, training-free hard prompting method that boosts ALEs' zero-shot performance by customizing prompts for diverse audio classification tasks. Rather than using generic template-based prompts like \"Sound of a car\" we generate context-rich prompts, such as \"Sound of a car coming from a tunnel\". Specifically, we leverage label information to identif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00398","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/2501.00398/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":"2501.00398","created_at":"2026-07-05T10:43:42.569772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00398v2","created_at":"2026-07-05T10:43:42.569772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00398","created_at":"2026-07-05T10:43:42.569772+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6VYR4ZH2CBG","created_at":"2026-07-05T10:43:42.569772+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6VYR4ZH2CBGRCJM","created_at":"2026-07-05T10:43:42.569772+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6VYR4ZH","created_at":"2026-07-05T10:43:42.569772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6VYR4ZH2CBGRCJMEX3WRBG4UE","json":"https://pith.science/pith/M6VYR4ZH2CBGRCJMEX3WRBG4UE.json","graph_json":"https://pith.science/api/pith-number/M6VYR4ZH2CBGRCJMEX3WRBG4UE/graph.json","events_json":"https://pith.science/api/pith-number/M6VYR4ZH2CBGRCJMEX3WRBG4UE/events.json","paper":"https://pith.science/paper/M6VYR4ZH"},"agent_actions":{"view_html":"https://pith.science/pith/M6VYR4ZH2CBGRCJMEX3WRBG4UE","download_json":"https://pith.science/pith/M6VYR4ZH2CBGRCJMEX3WRBG4UE.json","view_paper":"https://pith.science/paper/M6VYR4ZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00398&json=true","fetch_graph":"https://pith.science/api/pith-number/M6VYR4ZH2CBGRCJMEX3WRBG4UE/graph.json","fetch_events":"https://pith.science/api/pith-number/M6VYR4ZH2CBGRCJMEX3WRBG4UE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6VYR4ZH2CBGRCJMEX3WRBG4UE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6VYR4ZH2CBGRCJMEX3WRBG4UE/action/storage_attestation","attest_author":"https://pith.science/pith/M6VYR4ZH2CBGRCJMEX3WRBG4UE/action/author_attestation","sign_citation":"https://pith.science/pith/M6VYR4ZH2CBGRCJMEX3WRBG4UE/action/citation_signature","submit_replication":"https://pith.science/pith/M6VYR4ZH2CBGRCJMEX3WRBG4UE/action/replication_record"}},"created_at":"2026-07-05T10:43:42.569772+00:00","updated_at":"2026-07-05T10:43:42.569772+00:00"}