{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BLBPQHN7QNHYRW745T5RSEKY5U","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":"63cc21e512f2ac0ae74590aad9b74c93e3a74729d4e2c56e8ea36de934c46a31","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-22T01:22:25Z","title_canon_sha256":"4aa58ff8a33652a2690fcf40b8f542ebef2d92c53ed8dbd6e6f8495c61ae7d8a"},"schema_version":"1.0","source":{"id":"2111.10937","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.10937","created_at":"2026-07-05T03:33:58Z"},{"alias_kind":"arxiv_version","alias_value":"2111.10937v1","created_at":"2026-07-05T03:33:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10937","created_at":"2026-07-05T03:33:58Z"},{"alias_kind":"pith_short_12","alias_value":"BLBPQHN7QNHY","created_at":"2026-07-05T03:33:58Z"},{"alias_kind":"pith_short_16","alias_value":"BLBPQHN7QNHYRW74","created_at":"2026-07-05T03:33:58Z"},{"alias_kind":"pith_short_8","alias_value":"BLBPQHN7","created_at":"2026-07-05T03:33:58Z"}],"graph_snapshots":[{"event_id":"sha256:4715ee83501129972927f123f9ec7b116dc5cfa35a36469f9edef134dd02487f","target":"graph","created_at":"2026-07-05T03:33:58Z","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/2111.10937/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transfer learning (TL) leverages previously obtained knowledge to learn new tasks efficiently and has been used to train deep learning (DL) models with limited amount of data. When TL is applied to DL, pretrained (teacher) models are fine-tuned to build domain specific (student) models. This fine-tuning relies on the fact that DL model can be decomposed to classifiers and feature extractors, and a line of studies showed that the same feature extractors can be used to train classifiers on multiple tasks. Furthermore, recent studies proposed multiple algorithms that can fine-tune teacher models'","authors_text":"Courtney D. Corley, Elliott Skomski, Henry J Kvinge, Jessica Hibler, John Buckheit, Jung H Lee, Lauren A. Phillips, Nathan O. Hodas, Scott Howland, Zachary New","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-22T01:22:25Z","title":"Adaptive Transfer Learning: a simple but effective transfer learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10937","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":"sha256:9f81ca9d1d840c68048340bbc92c72664781b2dfb6f1008682d4f9288120300d","target":"record","created_at":"2026-07-05T03:33:58Z","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":"63cc21e512f2ac0ae74590aad9b74c93e3a74729d4e2c56e8ea36de934c46a31","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-22T01:22:25Z","title_canon_sha256":"4aa58ff8a33652a2690fcf40b8f542ebef2d92c53ed8dbd6e6f8495c61ae7d8a"},"schema_version":"1.0","source":{"id":"2111.10937","kind":"arxiv","version":1}},"canonical_sha256":"0ac2f81dbf834f88dbfcecfb191158ed091cce3e4ca866d1c43f3fef3abedbc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ac2f81dbf834f88dbfcecfb191158ed091cce3e4ca866d1c43f3fef3abedbc8","first_computed_at":"2026-07-05T03:33:58.385099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:33:58.385099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p2ofSAg0udK7ZF57wfHasH6btByqfyBnnirG7JF96W2+qFaEpHhbXenlqrhRCezaIb0p4zANBBzVANHEpDRdDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:33:58.385563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.10937","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f81ca9d1d840c68048340bbc92c72664781b2dfb6f1008682d4f9288120300d","sha256:4715ee83501129972927f123f9ec7b116dc5cfa35a36469f9edef134dd02487f"],"state_sha256":"553789ae80afbfe37407e37b1af2e10d59d238edb15e05209bfd5e5474878704"}