{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2HEJCGUSL7IJZT6IL4WBC62DAD","short_pith_number":"pith:2HEJCGUS","schema_version":"1.0","canonical_sha256":"d1c8911a925fd09ccfc85f2c117b4300c823285756afa47d15a74a988f28f8fa","source":{"kind":"arxiv","id":"2408.16189","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Sample Aggregation In Transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Samory Kpotufe, Steve Hanneke","submitted_at":"2024-08-29T01:02:40Z","abstract_excerpt":"Transfer Learning aims to optimally aggregate samples from a target distribution, with related samples from a so-called source distribution to improve target risk. Multiple procedures have been proposed over the last two decades to address this problem, each driven by one of a multitude of possible divergence measures between source and target distributions. A first question asked in this work is whether there exist unified algorithmic approaches that automatically adapt to many of these divergence measures simultaneously.\n  We show that this is indeed the case for a large family of divergence"},"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":"2408.16189","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-08-29T01:02:40Z","cross_cats_sorted":["cs.AI","cs.LG","math.ST","stat.TH"],"title_canon_sha256":"99c1859121f52ffe8b27751e6f126500e2019c41428a6521915891361dd6151f","abstract_canon_sha256":"074bcc9160eb346bd867d8b44ee358aa7984a614901ccd21da22108326090ad7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:35.752799Z","signature_b64":"FjV7Uj8gv4F3ahTX/vXv3CghASqzSQ05YsNqBljRBwZb1hfhPQTb1ysSJ7SoKEPRXfrV0pWU0sJaJqe7/AgdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1c8911a925fd09ccfc85f2c117b4300c823285756afa47d15a74a988f28f8fa","last_reissued_at":"2026-07-05T10:54:35.752325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:35.752325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Sample Aggregation In Transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Samory Kpotufe, Steve Hanneke","submitted_at":"2024-08-29T01:02:40Z","abstract_excerpt":"Transfer Learning aims to optimally aggregate samples from a target distribution, with related samples from a so-called source distribution to improve target risk. Multiple procedures have been proposed over the last two decades to address this problem, each driven by one of a multitude of possible divergence measures between source and target distributions. A first question asked in this work is whether there exist unified algorithmic approaches that automatically adapt to many of these divergence measures simultaneously.\n  We show that this is indeed the case for a large family of divergence"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16189","kind":"arxiv","version":2},"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/2408.16189/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":"2408.16189","created_at":"2026-07-05T10:54:35.752388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.16189v2","created_at":"2026-07-05T10:54:35.752388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16189","created_at":"2026-07-05T10:54:35.752388+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HEJCGUSL7IJ","created_at":"2026-07-05T10:54:35.752388+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HEJCGUSL7IJZT6I","created_at":"2026-07-05T10:54:35.752388+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HEJCGUS","created_at":"2026-07-05T10:54:35.752388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07005","citing_title":"Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift","ref_index":175,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07005","citing_title":"Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift","ref_index":175,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2HEJCGUSL7IJZT6IL4WBC62DAD","json":"https://pith.science/pith/2HEJCGUSL7IJZT6IL4WBC62DAD.json","graph_json":"https://pith.science/api/pith-number/2HEJCGUSL7IJZT6IL4WBC62DAD/graph.json","events_json":"https://pith.science/api/pith-number/2HEJCGUSL7IJZT6IL4WBC62DAD/events.json","paper":"https://pith.science/paper/2HEJCGUS"},"agent_actions":{"view_html":"https://pith.science/pith/2HEJCGUSL7IJZT6IL4WBC62DAD","download_json":"https://pith.science/pith/2HEJCGUSL7IJZT6IL4WBC62DAD.json","view_paper":"https://pith.science/paper/2HEJCGUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.16189&json=true","fetch_graph":"https://pith.science/api/pith-number/2HEJCGUSL7IJZT6IL4WBC62DAD/graph.json","fetch_events":"https://pith.science/api/pith-number/2HEJCGUSL7IJZT6IL4WBC62DAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HEJCGUSL7IJZT6IL4WBC62DAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HEJCGUSL7IJZT6IL4WBC62DAD/action/storage_attestation","attest_author":"https://pith.science/pith/2HEJCGUSL7IJZT6IL4WBC62DAD/action/author_attestation","sign_citation":"https://pith.science/pith/2HEJCGUSL7IJZT6IL4WBC62DAD/action/citation_signature","submit_replication":"https://pith.science/pith/2HEJCGUSL7IJZT6IL4WBC62DAD/action/replication_record"}},"created_at":"2026-07-05T10:54:35.752388+00:00","updated_at":"2026-07-05T10:54:35.752388+00:00"}