{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:S6VTQT52GURTOTSFIJ6MZZCI4R","short_pith_number":"pith:S6VTQT52","schema_version":"1.0","canonical_sha256":"97ab384fba3523374e45427ccce448e44b3fc240db2a34dcd52ccf287aa52949","source":{"kind":"arxiv","id":"2212.10082","version":1},"attestation_state":"computed","paper":{"title":"An Information-Theoretic Approach to Transferability in Task Transfer Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Amir Zamir, Leonidas Guibas, Lin Zhang, Lizhong Zheng, Shao-Lun Huang, Yajie Bao, Yang Li","submitted_at":"2022-12-20T08:47:17Z","abstract_excerpt":"Task transfer learning is a popular technique in image processing applications that uses pre-trained models to reduce the supervision cost of related tasks. An important question is to determine task transferability, i.e. given a common input domain, estimating to what extent representations learned from a source task can help in learning a target task. Typically, transferability is either measured experimentally or inferred through task relatedness, which is often defined without a clear operational meaning. In this paper, we present a novel metric, H-score, an easily-computable evaluation fu"},"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":"2212.10082","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-20T08:47:17Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"831a3ca3b58ef3c526382649cd39c3cd3cbac747670d6a169850cf143b366209","abstract_canon_sha256":"f407246f50529bf5ba47b1be6736afce82459012faadb230c4a5e755c28af0f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:03.561958Z","signature_b64":"JtUUrwPgbVwqsJ+Dk0BU9Pbkj4Is2dmdGuPCyNzFnxKKqgooDnfQS/4AYNNLtAfe5KLb+346JPGJSTp6hHgSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97ab384fba3523374e45427ccce448e44b3fc240db2a34dcd52ccf287aa52949","last_reissued_at":"2026-07-05T05:27:03.561607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:03.561607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Information-Theoretic Approach to Transferability in Task Transfer Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Amir Zamir, Leonidas Guibas, Lin Zhang, Lizhong Zheng, Shao-Lun Huang, Yajie Bao, Yang Li","submitted_at":"2022-12-20T08:47:17Z","abstract_excerpt":"Task transfer learning is a popular technique in image processing applications that uses pre-trained models to reduce the supervision cost of related tasks. An important question is to determine task transferability, i.e. given a common input domain, estimating to what extent representations learned from a source task can help in learning a target task. Typically, transferability is either measured experimentally or inferred through task relatedness, which is often defined without a clear operational meaning. In this paper, we present a novel metric, H-score, an easily-computable evaluation fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10082","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/2212.10082/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":"2212.10082","created_at":"2026-07-05T05:27:03.561665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10082v1","created_at":"2026-07-05T05:27:03.561665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10082","created_at":"2026-07-05T05:27:03.561665+00:00"},{"alias_kind":"pith_short_12","alias_value":"S6VTQT52GURT","created_at":"2026-07-05T05:27:03.561665+00:00"},{"alias_kind":"pith_short_16","alias_value":"S6VTQT52GURTOTSF","created_at":"2026-07-05T05:27:03.561665+00:00"},{"alias_kind":"pith_short_8","alias_value":"S6VTQT52","created_at":"2026-07-05T05:27:03.561665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.00450","citing_title":"Unsupervised Source-Free Ranking of Biomedical Segmentation Models Under Distribution Shift","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S6VTQT52GURTOTSFIJ6MZZCI4R","json":"https://pith.science/pith/S6VTQT52GURTOTSFIJ6MZZCI4R.json","graph_json":"https://pith.science/api/pith-number/S6VTQT52GURTOTSFIJ6MZZCI4R/graph.json","events_json":"https://pith.science/api/pith-number/S6VTQT52GURTOTSFIJ6MZZCI4R/events.json","paper":"https://pith.science/paper/S6VTQT52"},"agent_actions":{"view_html":"https://pith.science/pith/S6VTQT52GURTOTSFIJ6MZZCI4R","download_json":"https://pith.science/pith/S6VTQT52GURTOTSFIJ6MZZCI4R.json","view_paper":"https://pith.science/paper/S6VTQT52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10082&json=true","fetch_graph":"https://pith.science/api/pith-number/S6VTQT52GURTOTSFIJ6MZZCI4R/graph.json","fetch_events":"https://pith.science/api/pith-number/S6VTQT52GURTOTSFIJ6MZZCI4R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S6VTQT52GURTOTSFIJ6MZZCI4R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S6VTQT52GURTOTSFIJ6MZZCI4R/action/storage_attestation","attest_author":"https://pith.science/pith/S6VTQT52GURTOTSFIJ6MZZCI4R/action/author_attestation","sign_citation":"https://pith.science/pith/S6VTQT52GURTOTSFIJ6MZZCI4R/action/citation_signature","submit_replication":"https://pith.science/pith/S6VTQT52GURTOTSFIJ6MZZCI4R/action/replication_record"}},"created_at":"2026-07-05T05:27:03.561665+00:00","updated_at":"2026-07-05T05:27:03.561665+00:00"}