{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:APIIOHKJVBV2H3NQOZQP4ZTQ3H","short_pith_number":"pith:APIIOHKJ","schema_version":"1.0","canonical_sha256":"03d0871d49a86ba3edb07660fe6670d9c5cd87916ec9aa6fa2f2feb2a9da2ba7","source":{"kind":"arxiv","id":"2303.03267","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Parameter-Efficient Transfer Learning Approaches on SURE Benchmark for Speech Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ambuj Mehrish, Amir Zadeh, Navonil Majumder, Rada Mihalcea, Rishabh Bhardwaj, Shuai Zhao, Soujanya Poria, Yingting Li","submitted_at":"2023-03-02T08:57:33Z","abstract_excerpt":"Fine-tuning is widely used as the default algorithm for transfer learning from pre-trained models. Parameter inefficiency can however arise when, during transfer learning, all the parameters of a large pre-trained model need to be updated for individual downstream tasks. As the number of parameters grows, fine-tuning is prone to overfitting and catastrophic forgetting. In addition, full fine-tuning can become prohibitively expensive when the model is used for many tasks. To mitigate this issue, parameter-efficient transfer learning algorithms, such as adapters and prefix tuning, have been prop"},"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":"2303.03267","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-02T08:57:33Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"2fb498f53a8ff7010fb1d7e139775667b7943c062f5ee2e81dc05158cae0b979","abstract_canon_sha256":"dbe589b130dd958b7835ea141202477fe4e1d1311ef8b007a2464b6b20fc1860"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:27.698030Z","signature_b64":"FGBVasdWeFk75ae/ac67OkmEMZfSd15DBaPT83s+LizL47MSybxBeUwCy6ISBx8nqW2uS6iu0cJv4NxBljS2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03d0871d49a86ba3edb07660fe6670d9c5cd87916ec9aa6fa2f2feb2a9da2ba7","last_reissued_at":"2026-07-05T05:48:27.697493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:27.697493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Parameter-Efficient Transfer Learning Approaches on SURE Benchmark for Speech Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ambuj Mehrish, Amir Zadeh, Navonil Majumder, Rada Mihalcea, Rishabh Bhardwaj, Shuai Zhao, Soujanya Poria, Yingting Li","submitted_at":"2023-03-02T08:57:33Z","abstract_excerpt":"Fine-tuning is widely used as the default algorithm for transfer learning from pre-trained models. Parameter inefficiency can however arise when, during transfer learning, all the parameters of a large pre-trained model need to be updated for individual downstream tasks. As the number of parameters grows, fine-tuning is prone to overfitting and catastrophic forgetting. In addition, full fine-tuning can become prohibitively expensive when the model is used for many tasks. To mitigate this issue, parameter-efficient transfer learning algorithms, such as adapters and prefix tuning, have been prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03267","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/2303.03267/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":"2303.03267","created_at":"2026-07-05T05:48:27.697573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03267v1","created_at":"2026-07-05T05:48:27.697573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03267","created_at":"2026-07-05T05:48:27.697573+00:00"},{"alias_kind":"pith_short_12","alias_value":"APIIOHKJVBV2","created_at":"2026-07-05T05:48:27.697573+00:00"},{"alias_kind":"pith_short_16","alias_value":"APIIOHKJVBV2H3NQ","created_at":"2026-07-05T05:48:27.697573+00:00"},{"alias_kind":"pith_short_8","alias_value":"APIIOHKJ","created_at":"2026-07-05T05:48:27.697573+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/APIIOHKJVBV2H3NQOZQP4ZTQ3H","json":"https://pith.science/pith/APIIOHKJVBV2H3NQOZQP4ZTQ3H.json","graph_json":"https://pith.science/api/pith-number/APIIOHKJVBV2H3NQOZQP4ZTQ3H/graph.json","events_json":"https://pith.science/api/pith-number/APIIOHKJVBV2H3NQOZQP4ZTQ3H/events.json","paper":"https://pith.science/paper/APIIOHKJ"},"agent_actions":{"view_html":"https://pith.science/pith/APIIOHKJVBV2H3NQOZQP4ZTQ3H","download_json":"https://pith.science/pith/APIIOHKJVBV2H3NQOZQP4ZTQ3H.json","view_paper":"https://pith.science/paper/APIIOHKJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03267&json=true","fetch_graph":"https://pith.science/api/pith-number/APIIOHKJVBV2H3NQOZQP4ZTQ3H/graph.json","fetch_events":"https://pith.science/api/pith-number/APIIOHKJVBV2H3NQOZQP4ZTQ3H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APIIOHKJVBV2H3NQOZQP4ZTQ3H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APIIOHKJVBV2H3NQOZQP4ZTQ3H/action/storage_attestation","attest_author":"https://pith.science/pith/APIIOHKJVBV2H3NQOZQP4ZTQ3H/action/author_attestation","sign_citation":"https://pith.science/pith/APIIOHKJVBV2H3NQOZQP4ZTQ3H/action/citation_signature","submit_replication":"https://pith.science/pith/APIIOHKJVBV2H3NQOZQP4ZTQ3H/action/replication_record"}},"created_at":"2026-07-05T05:48:27.697573+00:00","updated_at":"2026-07-05T05:48:27.697573+00:00"}