{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OOYH2CP6TEXIA3M5L5XS3TMS3U","short_pith_number":"pith:OOYH2CP6","schema_version":"1.0","canonical_sha256":"73b07d09fe992e806d9d5f6f2dcd92dd3cc383154e8f28cd24a35b4e7d1060fc","source":{"kind":"arxiv","id":"2312.03694","version":4},"attestation_state":"computed","paper":{"title":"Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Alessio Brutti, Daniele Falavigna, Mirco Ravanelli, Umberto Cappellazzo","submitted_at":"2023-12-06T18:55:34Z","abstract_excerpt":"Parameter-efficient transfer learning (PETL) methods have emerged as a solid alternative to the standard full fine-tuning approach. They only train a few extra parameters for each downstream task, without sacrificing performance and dispensing with the issue of storing a copy of the pre-trained model for each task. For audio classification tasks, the Audio Spectrogram Transformer (AST) model shows impressive results. However, surprisingly, how to efficiently adapt it to several downstream tasks has not been tackled before. In this paper, we bridge this gap and present a detailed investigation "},"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":"2312.03694","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-12-06T18:55:34Z","cross_cats_sorted":[],"title_canon_sha256":"e42f8a0fb75ff7658f85ee4d529bb443cdad57ecf572d3ae7a47983be7172582","abstract_canon_sha256":"f054afc02eaa9ab59b9b36232cb73bea69ab18d5fbe1b690e554872b66592f8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:51.766405Z","signature_b64":"nKHKHHKYRqhm2D9BGAPPZVJki6nwkviKf9V3clNV1X7SRRZlcIBj5H6nW0o6Xhg9UQGLTPO/J9w7WY4G21pYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73b07d09fe992e806d9d5f6f2dcd92dd3cc383154e8f28cd24a35b4e7d1060fc","last_reissued_at":"2026-07-05T08:43:51.765881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:51.765881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Alessio Brutti, Daniele Falavigna, Mirco Ravanelli, Umberto Cappellazzo","submitted_at":"2023-12-06T18:55:34Z","abstract_excerpt":"Parameter-efficient transfer learning (PETL) methods have emerged as a solid alternative to the standard full fine-tuning approach. They only train a few extra parameters for each downstream task, without sacrificing performance and dispensing with the issue of storing a copy of the pre-trained model for each task. For audio classification tasks, the Audio Spectrogram Transformer (AST) model shows impressive results. However, surprisingly, how to efficiently adapt it to several downstream tasks has not been tackled before. In this paper, we bridge this gap and present a detailed investigation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03694","kind":"arxiv","version":4},"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/2312.03694/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":"2312.03694","created_at":"2026-07-05T08:43:51.765939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03694v4","created_at":"2026-07-05T08:43:51.765939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03694","created_at":"2026-07-05T08:43:51.765939+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOYH2CP6TEXI","created_at":"2026-07-05T08:43:51.765939+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOYH2CP6TEXIA3M5","created_at":"2026-07-05T08:43:51.765939+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOYH2CP6","created_at":"2026-07-05T08:43:51.765939+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/OOYH2CP6TEXIA3M5L5XS3TMS3U","json":"https://pith.science/pith/OOYH2CP6TEXIA3M5L5XS3TMS3U.json","graph_json":"https://pith.science/api/pith-number/OOYH2CP6TEXIA3M5L5XS3TMS3U/graph.json","events_json":"https://pith.science/api/pith-number/OOYH2CP6TEXIA3M5L5XS3TMS3U/events.json","paper":"https://pith.science/paper/OOYH2CP6"},"agent_actions":{"view_html":"https://pith.science/pith/OOYH2CP6TEXIA3M5L5XS3TMS3U","download_json":"https://pith.science/pith/OOYH2CP6TEXIA3M5L5XS3TMS3U.json","view_paper":"https://pith.science/paper/OOYH2CP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03694&json=true","fetch_graph":"https://pith.science/api/pith-number/OOYH2CP6TEXIA3M5L5XS3TMS3U/graph.json","fetch_events":"https://pith.science/api/pith-number/OOYH2CP6TEXIA3M5L5XS3TMS3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOYH2CP6TEXIA3M5L5XS3TMS3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOYH2CP6TEXIA3M5L5XS3TMS3U/action/storage_attestation","attest_author":"https://pith.science/pith/OOYH2CP6TEXIA3M5L5XS3TMS3U/action/author_attestation","sign_citation":"https://pith.science/pith/OOYH2CP6TEXIA3M5L5XS3TMS3U/action/citation_signature","submit_replication":"https://pith.science/pith/OOYH2CP6TEXIA3M5L5XS3TMS3U/action/replication_record"}},"created_at":"2026-07-05T08:43:51.765939+00:00","updated_at":"2026-07-05T08:43:51.765939+00:00"}