{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5UTZFYQ2CKGODCJ5RX5ZWECI6L","short_pith_number":"pith:5UTZFYQ2","schema_version":"1.0","canonical_sha256":"ed2792e21a128ce1893d8dfb9b1048f2e826e12fb4926f7bfb8ec175724217be","source":{"kind":"arxiv","id":"2606.04844","version":1},"attestation_state":"computed","paper":{"title":"Drift-Augmented Scoring: Text-Derived Noise Robustness for Zero-Shot Audio-Language Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.SD","authors_text":"Chan Y. Park, Sheir Zaheer, Tu Vo","submitted_at":"2026-06-03T13:12:34Z","abstract_excerpt":"Contrastive audio-language models such as CLAP enable zero-shot audio classification: a sound is labelled by matching its embedding to text prompt embeddings, with no labelled audio. This matching breaks down under acoustic noise, where accuracy and mAP fall by 12-30 percentage points at 0 dB SNR on standard benchmarks. We propose Drift Augmented Scoring (DAS), a small per-class bonus added to the cosine score. The bonus rewards a class when the noisy audio embedding drifts in the direction that the class's noise-conditioned text prompts predict. It is derived from text alone, computed once an"},"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":"2606.04844","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-03T13:12:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"30c66b4d9895bada04386019aee699ecde99782246b5e466ed291f99ce4b0be5","abstract_canon_sha256":"b4d505c04cfd5b2c677b52d26377a690d34f166749ac1c3ff825562c9dd47ffd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:32.026745Z","signature_b64":"JhIHOSff+FTZ970Q++Ihh2mwVNEIARw6c7VR2NchXZUFcLwVzO9Fk00WJvMUvrhhEw2+s6zFK6uUVsCANKs2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed2792e21a128ce1893d8dfb9b1048f2e826e12fb4926f7bfb8ec175724217be","last_reissued_at":"2026-06-04T01:09:32.026277Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:32.026277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Drift-Augmented Scoring: Text-Derived Noise Robustness for Zero-Shot Audio-Language Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.SD","authors_text":"Chan Y. Park, Sheir Zaheer, Tu Vo","submitted_at":"2026-06-03T13:12:34Z","abstract_excerpt":"Contrastive audio-language models such as CLAP enable zero-shot audio classification: a sound is labelled by matching its embedding to text prompt embeddings, with no labelled audio. This matching breaks down under acoustic noise, where accuracy and mAP fall by 12-30 percentage points at 0 dB SNR on standard benchmarks. We propose Drift Augmented Scoring (DAS), a small per-class bonus added to the cosine score. The bonus rewards a class when the noisy audio embedding drifts in the direction that the class's noise-conditioned text prompts predict. It is derived from text alone, computed once an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04844","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/2606.04844/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":"2606.04844","created_at":"2026-06-04T01:09:32.026359+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04844v1","created_at":"2026-06-04T01:09:32.026359+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04844","created_at":"2026-06-04T01:09:32.026359+00:00"},{"alias_kind":"pith_short_12","alias_value":"5UTZFYQ2CKGO","created_at":"2026-06-04T01:09:32.026359+00:00"},{"alias_kind":"pith_short_16","alias_value":"5UTZFYQ2CKGODCJ5","created_at":"2026-06-04T01:09:32.026359+00:00"},{"alias_kind":"pith_short_8","alias_value":"5UTZFYQ2","created_at":"2026-06-04T01:09:32.026359+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/5UTZFYQ2CKGODCJ5RX5ZWECI6L","json":"https://pith.science/pith/5UTZFYQ2CKGODCJ5RX5ZWECI6L.json","graph_json":"https://pith.science/api/pith-number/5UTZFYQ2CKGODCJ5RX5ZWECI6L/graph.json","events_json":"https://pith.science/api/pith-number/5UTZFYQ2CKGODCJ5RX5ZWECI6L/events.json","paper":"https://pith.science/paper/5UTZFYQ2"},"agent_actions":{"view_html":"https://pith.science/pith/5UTZFYQ2CKGODCJ5RX5ZWECI6L","download_json":"https://pith.science/pith/5UTZFYQ2CKGODCJ5RX5ZWECI6L.json","view_paper":"https://pith.science/paper/5UTZFYQ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04844&json=true","fetch_graph":"https://pith.science/api/pith-number/5UTZFYQ2CKGODCJ5RX5ZWECI6L/graph.json","fetch_events":"https://pith.science/api/pith-number/5UTZFYQ2CKGODCJ5RX5ZWECI6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5UTZFYQ2CKGODCJ5RX5ZWECI6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5UTZFYQ2CKGODCJ5RX5ZWECI6L/action/storage_attestation","attest_author":"https://pith.science/pith/5UTZFYQ2CKGODCJ5RX5ZWECI6L/action/author_attestation","sign_citation":"https://pith.science/pith/5UTZFYQ2CKGODCJ5RX5ZWECI6L/action/citation_signature","submit_replication":"https://pith.science/pith/5UTZFYQ2CKGODCJ5RX5ZWECI6L/action/replication_record"}},"created_at":"2026-06-04T01:09:32.026359+00:00","updated_at":"2026-06-04T01:09:32.026359+00:00"}