{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J5EIRLII6I3IUU2KTGJZKXFKMN","short_pith_number":"pith:J5EIRLII","schema_version":"1.0","canonical_sha256":"4f4888ad08f2368a534a9993955caa634c46d447ed049449f4fb1053f478e299","source":{"kind":"arxiv","id":"2411.12058","version":1},"attestation_state":"computed","paper":{"title":"Vision Language Models Are Few-Shot Audio Spectrogram Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chris Donahue, Laurie M. Heller, Satvik Dixit","submitted_at":"2024-11-18T20:56:44Z","abstract_excerpt":"We demonstrate that vision language models (VLMs) are capable of recognizing the content in audio recordings when given corresponding spectrogram images. Specifically, we instruct VLMs to perform audio classification tasks in a few-shot setting by prompting them to classify a spectrogram image given example spectrogram images of each class. By carefully designing the spectrogram image representation and selecting good few-shot examples, we show that GPT-4o can achieve 59.00% cross-validated accuracy on the ESC-10 environmental sound classification dataset. Moreover, we demonstrate that VLMs cu"},"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":"2411.12058","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-18T20:56:44Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d90c3fa1a6c0b070ba0515f7fddd61ad918ca3ff384ae367d4cc16fb318acca2","abstract_canon_sha256":"78921ea8297cc5cf3577467861d478d8844cefed8fc81d0f8a599b9798babe92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:15.464269Z","signature_b64":"4xqaqKjy5MjO+foIvepHvSHCEkdS3gn6HkmiTDInRk/vrGWrhUFTjcNvrEk/KWFeyaFEF26ciEVT2vUD89OdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f4888ad08f2368a534a9993955caa634c46d447ed049449f4fb1053f478e299","last_reissued_at":"2026-07-05T09:37:15.463868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:15.463868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision Language Models Are Few-Shot Audio Spectrogram Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chris Donahue, Laurie M. Heller, Satvik Dixit","submitted_at":"2024-11-18T20:56:44Z","abstract_excerpt":"We demonstrate that vision language models (VLMs) are capable of recognizing the content in audio recordings when given corresponding spectrogram images. Specifically, we instruct VLMs to perform audio classification tasks in a few-shot setting by prompting them to classify a spectrogram image given example spectrogram images of each class. By carefully designing the spectrogram image representation and selecting good few-shot examples, we show that GPT-4o can achieve 59.00% cross-validated accuracy on the ESC-10 environmental sound classification dataset. Moreover, we demonstrate that VLMs cu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12058","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/2411.12058/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":"2411.12058","created_at":"2026-07-05T09:37:15.463922+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12058v1","created_at":"2026-07-05T09:37:15.463922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12058","created_at":"2026-07-05T09:37:15.463922+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5EIRLII6I3I","created_at":"2026-07-05T09:37:15.463922+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5EIRLII6I3IUU2K","created_at":"2026-07-05T09:37:15.463922+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5EIRLII","created_at":"2026-07-05T09:37:15.463922+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05703","citing_title":"Knowledge-Augmented Vision Language Models for Underwater Bioacoustic Spectrogram Analysis","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J5EIRLII6I3IUU2KTGJZKXFKMN","json":"https://pith.science/pith/J5EIRLII6I3IUU2KTGJZKXFKMN.json","graph_json":"https://pith.science/api/pith-number/J5EIRLII6I3IUU2KTGJZKXFKMN/graph.json","events_json":"https://pith.science/api/pith-number/J5EIRLII6I3IUU2KTGJZKXFKMN/events.json","paper":"https://pith.science/paper/J5EIRLII"},"agent_actions":{"view_html":"https://pith.science/pith/J5EIRLII6I3IUU2KTGJZKXFKMN","download_json":"https://pith.science/pith/J5EIRLII6I3IUU2KTGJZKXFKMN.json","view_paper":"https://pith.science/paper/J5EIRLII","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12058&json=true","fetch_graph":"https://pith.science/api/pith-number/J5EIRLII6I3IUU2KTGJZKXFKMN/graph.json","fetch_events":"https://pith.science/api/pith-number/J5EIRLII6I3IUU2KTGJZKXFKMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5EIRLII6I3IUU2KTGJZKXFKMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5EIRLII6I3IUU2KTGJZKXFKMN/action/storage_attestation","attest_author":"https://pith.science/pith/J5EIRLII6I3IUU2KTGJZKXFKMN/action/author_attestation","sign_citation":"https://pith.science/pith/J5EIRLII6I3IUU2KTGJZKXFKMN/action/citation_signature","submit_replication":"https://pith.science/pith/J5EIRLII6I3IUU2KTGJZKXFKMN/action/replication_record"}},"created_at":"2026-07-05T09:37:15.463922+00:00","updated_at":"2026-07-05T09:37:15.463922+00:00"}