{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NA6FZXPBZKZADLMNJTOLJQ7AX3","short_pith_number":"pith:NA6FZXPB","schema_version":"1.0","canonical_sha256":"683c5cdde1cab201ad8d4cdcb4c3e0bed9ad3ea4a0345f93b788b09a39df7921","source":{"kind":"arxiv","id":"2110.09940","version":1},"attestation_state":"computed","paper":{"title":"Learning Representations that Support Robust Transfer of Predictors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Tommi Jaakkola, Yilun Xu","submitted_at":"2021-10-19T13:00:37Z","abstract_excerpt":"Ensuring generalization to unseen environments remains a challenge. Domain shift can lead to substantially degraded performance unless shifts are well-exercised within the available training environments. We introduce a simple robust estimation criterion -- transfer risk -- that is specifically geared towards optimizing transfer to new environments. Effectively, the criterion amounts to finding a representation that minimizes the risk of applying any optimal predictor trained on one environment to another. The transfer risk essentially decomposes into two terms, a direct transfer term and a we"},"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":"2110.09940","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T13:00:37Z","cross_cats_sorted":[],"title_canon_sha256":"a59f95b99ea46f04002cf8ee63e6a136719452f890e2a9dfa48e9080c5c3367e","abstract_canon_sha256":"9eb6c91c8ee76dd79e9ec7c3c17f502d553cf096112dad4a81ef7b58059df1db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:01.305068Z","signature_b64":"oZqyZF70rcH2Uy5oTrhd4eaHkW7bBAykoCQoVRT6a4acZE4mPsYojv3CnKV1FywagO3BZ3roItvtzyXBmGqvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"683c5cdde1cab201ad8d4cdcb4c3e0bed9ad3ea4a0345f93b788b09a39df7921","last_reissued_at":"2026-07-05T03:24:01.304529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:01.304529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Representations that Support Robust Transfer of Predictors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Tommi Jaakkola, Yilun Xu","submitted_at":"2021-10-19T13:00:37Z","abstract_excerpt":"Ensuring generalization to unseen environments remains a challenge. Domain shift can lead to substantially degraded performance unless shifts are well-exercised within the available training environments. We introduce a simple robust estimation criterion -- transfer risk -- that is specifically geared towards optimizing transfer to new environments. Effectively, the criterion amounts to finding a representation that minimizes the risk of applying any optimal predictor trained on one environment to another. The transfer risk essentially decomposes into two terms, a direct transfer term and a we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09940","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/2110.09940/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":"2110.09940","created_at":"2026-07-05T03:24:01.304589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.09940v1","created_at":"2026-07-05T03:24:01.304589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09940","created_at":"2026-07-05T03:24:01.304589+00:00"},{"alias_kind":"pith_short_12","alias_value":"NA6FZXPBZKZA","created_at":"2026-07-05T03:24:01.304589+00:00"},{"alias_kind":"pith_short_16","alias_value":"NA6FZXPBZKZADLMN","created_at":"2026-07-05T03:24:01.304589+00:00"},{"alias_kind":"pith_short_8","alias_value":"NA6FZXPB","created_at":"2026-07-05T03:24:01.304589+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24781","citing_title":"Assessing Distribution Shift in Human Activity Recognition for Domain Generalization","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NA6FZXPBZKZADLMNJTOLJQ7AX3","json":"https://pith.science/pith/NA6FZXPBZKZADLMNJTOLJQ7AX3.json","graph_json":"https://pith.science/api/pith-number/NA6FZXPBZKZADLMNJTOLJQ7AX3/graph.json","events_json":"https://pith.science/api/pith-number/NA6FZXPBZKZADLMNJTOLJQ7AX3/events.json","paper":"https://pith.science/paper/NA6FZXPB"},"agent_actions":{"view_html":"https://pith.science/pith/NA6FZXPBZKZADLMNJTOLJQ7AX3","download_json":"https://pith.science/pith/NA6FZXPBZKZADLMNJTOLJQ7AX3.json","view_paper":"https://pith.science/paper/NA6FZXPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.09940&json=true","fetch_graph":"https://pith.science/api/pith-number/NA6FZXPBZKZADLMNJTOLJQ7AX3/graph.json","fetch_events":"https://pith.science/api/pith-number/NA6FZXPBZKZADLMNJTOLJQ7AX3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NA6FZXPBZKZADLMNJTOLJQ7AX3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NA6FZXPBZKZADLMNJTOLJQ7AX3/action/storage_attestation","attest_author":"https://pith.science/pith/NA6FZXPBZKZADLMNJTOLJQ7AX3/action/author_attestation","sign_citation":"https://pith.science/pith/NA6FZXPBZKZADLMNJTOLJQ7AX3/action/citation_signature","submit_replication":"https://pith.science/pith/NA6FZXPBZKZADLMNJTOLJQ7AX3/action/replication_record"}},"created_at":"2026-07-05T03:24:01.304589+00:00","updated_at":"2026-07-05T03:24:01.304589+00:00"}