{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:J5EIRLII6I3IUU2KTGJZKXFKMN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"78921ea8297cc5cf3577467861d478d8844cefed8fc81d0f8a599b9798babe92","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-18T20:56:44Z","title_canon_sha256":"d90c3fa1a6c0b070ba0515f7fddd61ad918ca3ff384ae367d4cc16fb318acca2"},"schema_version":"1.0","source":{"id":"2411.12058","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12058","created_at":"2026-07-05T09:37:15Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12058v1","created_at":"2026-07-05T09:37:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12058","created_at":"2026-07-05T09:37:15Z"},{"alias_kind":"pith_short_12","alias_value":"J5EIRLII6I3I","created_at":"2026-07-05T09:37:15Z"},{"alias_kind":"pith_short_16","alias_value":"J5EIRLII6I3IUU2K","created_at":"2026-07-05T09:37:15Z"},{"alias_kind":"pith_short_8","alias_value":"J5EIRLII","created_at":"2026-07-05T09:37:15Z"}],"graph_snapshots":[{"event_id":"sha256:bfde902dae0043d6ddbedc2463d90121e5281f490ec20cb1e345150a1406a091","target":"graph","created_at":"2026-07-05T09:37:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.12058/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chris Donahue, Laurie M. Heller, Satvik Dixit","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-18T20:56:44Z","title":"Vision Language Models Are Few-Shot Audio Spectrogram Classifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12058","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ba994028098a7f94c1fe8e604c52f21f8dca9185be653dfc76c749f97e49d292","target":"record","created_at":"2026-07-05T09:37:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"78921ea8297cc5cf3577467861d478d8844cefed8fc81d0f8a599b9798babe92","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-18T20:56:44Z","title_canon_sha256":"d90c3fa1a6c0b070ba0515f7fddd61ad918ca3ff384ae367d4cc16fb318acca2"},"schema_version":"1.0","source":{"id":"2411.12058","kind":"arxiv","version":1}},"canonical_sha256":"4f4888ad08f2368a534a9993955caa634c46d447ed049449f4fb1053f478e299","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f4888ad08f2368a534a9993955caa634c46d447ed049449f4fb1053f478e299","first_computed_at":"2026-07-05T09:37:15.463868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:37:15.463868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4xqaqKjy5MjO+foIvepHvSHCEkdS3gn6HkmiTDInRk/vrGWrhUFTjcNvrEk/KWFeyaFEF26ciEVT2vUD89OdAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:37:15.464269Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.12058","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba994028098a7f94c1fe8e604c52f21f8dca9185be653dfc76c749f97e49d292","sha256:bfde902dae0043d6ddbedc2463d90121e5281f490ec20cb1e345150a1406a091"],"state_sha256":"a80c05e344f488fb0f2be744e4ca15c944d9aa2b393a5e4eda3da1806be76e62"}