{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RZZB4VQADN4WVDENFUO6DCBHS4","short_pith_number":"pith:RZZB4VQA","schema_version":"1.0","canonical_sha256":"8e721e56001b796a8c8d2d1de18827972247ae17ec60e6201af27f48b1812758","source":{"kind":"arxiv","id":"2207.12944","version":1},"attestation_state":"computed","paper":{"title":"AMF: Adaptable Weighting Fusion with Multiple Fine-tuning for Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jo Plested, Sabrina Caldwell, Tom Gedeon, Xuyang Shen, Yiran Zhong","submitted_at":"2022-07-26T14:50:03Z","abstract_excerpt":"Fine-tuning is widely applied in image classification tasks as a transfer learning approach. It re-uses the knowledge from a source task to learn and obtain a high performance in target tasks. Fine-tuning is able to alleviate the challenge of insufficient training data and expensive labelling of new data. However, standard fine-tuning has limited performance in complex data distributions. To address this issue, we propose the Adaptable Multi-tuning method, which adaptively determines each data sample's fine-tuning strategy. In this framework, multiple fine-tuning settings and one policy networ"},"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":"2207.12944","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-26T14:50:03Z","cross_cats_sorted":[],"title_canon_sha256":"663a2b73b4edcba1a3f09e61ec2510c5cb6547000c1815ec31bdbae65966b8e3","abstract_canon_sha256":"0f8015a46e0900c6593ef3a544f4aff4ae0bc64826ccd6a367ea3f392009b8c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:43:51.800729Z","signature_b64":"VzX7+9fcvdhquIeRoHrpJQ9a+CFH+VVF6kjkmLwESTDz+rSpunZycdao9JE/G1Iq9CpsGQKwihzmwgdNhO0yBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e721e56001b796a8c8d2d1de18827972247ae17ec60e6201af27f48b1812758","last_reissued_at":"2026-07-05T04:43:51.800382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:43:51.800382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AMF: Adaptable Weighting Fusion with Multiple Fine-tuning for Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jo Plested, Sabrina Caldwell, Tom Gedeon, Xuyang Shen, Yiran Zhong","submitted_at":"2022-07-26T14:50:03Z","abstract_excerpt":"Fine-tuning is widely applied in image classification tasks as a transfer learning approach. It re-uses the knowledge from a source task to learn and obtain a high performance in target tasks. Fine-tuning is able to alleviate the challenge of insufficient training data and expensive labelling of new data. However, standard fine-tuning has limited performance in complex data distributions. To address this issue, we propose the Adaptable Multi-tuning method, which adaptively determines each data sample's fine-tuning strategy. In this framework, multiple fine-tuning settings and one policy networ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.12944","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/2207.12944/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":"2207.12944","created_at":"2026-07-05T04:43:51.800436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.12944v1","created_at":"2026-07-05T04:43:51.800436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.12944","created_at":"2026-07-05T04:43:51.800436+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZZB4VQADN4W","created_at":"2026-07-05T04:43:51.800436+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZZB4VQADN4WVDEN","created_at":"2026-07-05T04:43:51.800436+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZZB4VQA","created_at":"2026-07-05T04:43:51.800436+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/RZZB4VQADN4WVDENFUO6DCBHS4","json":"https://pith.science/pith/RZZB4VQADN4WVDENFUO6DCBHS4.json","graph_json":"https://pith.science/api/pith-number/RZZB4VQADN4WVDENFUO6DCBHS4/graph.json","events_json":"https://pith.science/api/pith-number/RZZB4VQADN4WVDENFUO6DCBHS4/events.json","paper":"https://pith.science/paper/RZZB4VQA"},"agent_actions":{"view_html":"https://pith.science/pith/RZZB4VQADN4WVDENFUO6DCBHS4","download_json":"https://pith.science/pith/RZZB4VQADN4WVDENFUO6DCBHS4.json","view_paper":"https://pith.science/paper/RZZB4VQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.12944&json=true","fetch_graph":"https://pith.science/api/pith-number/RZZB4VQADN4WVDENFUO6DCBHS4/graph.json","fetch_events":"https://pith.science/api/pith-number/RZZB4VQADN4WVDENFUO6DCBHS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZZB4VQADN4WVDENFUO6DCBHS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZZB4VQADN4WVDENFUO6DCBHS4/action/storage_attestation","attest_author":"https://pith.science/pith/RZZB4VQADN4WVDENFUO6DCBHS4/action/author_attestation","sign_citation":"https://pith.science/pith/RZZB4VQADN4WVDENFUO6DCBHS4/action/citation_signature","submit_replication":"https://pith.science/pith/RZZB4VQADN4WVDENFUO6DCBHS4/action/replication_record"}},"created_at":"2026-07-05T04:43:51.800436+00:00","updated_at":"2026-07-05T04:43:51.800436+00:00"}