{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EB2JW3EVCEYB5XWGH3XKWP36ES","short_pith_number":"pith:EB2JW3EV","schema_version":"1.0","canonical_sha256":"20749b6c9511301edec63eeeab3f7e24a303b7168ded1341b66ef09b44d05ea7","source":{"kind":"arxiv","id":"2106.03632","version":2},"attestation_state":"computed","paper":{"title":"Quantifying and Improving Transferability in Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guojun Zhang, Han Zhao, Pascal Poupart, Yaoliang Yu","submitted_at":"2021-06-07T14:04:32Z","abstract_excerpt":"Out-of-distribution generalization is one of the key challenges when transferring a model from the lab to the real world. Existing efforts mostly focus on building invariant features among source and target domains. Based on invariant features, a high-performing classifier on source domains could hopefully behave equally well on a target domain. In other words, the invariant features are \\emph{transferable}. However, in practice, there are no perfectly transferable features, and some algorithms seem to learn \"more transferable\" features than others. How can we understand and quantify such \\emp"},"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":"2106.03632","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-07T14:04:32Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b4bff5b20c9ffa954c2ef5cbf5d21d16a9a1c531041266401721f19ea0341539","abstract_canon_sha256":"92d977f20e35cd144d87e877c1e88ad12d6d1bf4fe9e8d0968193a5d2a85bb1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:57.419087Z","signature_b64":"fC3H2/N4OzHbFoebZblMKDQMsPxp8S5VkM3qX4baGCOk17LB3wMdNicLAK8EJ8eFrOo///7j4NdBaqf3AmbfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20749b6c9511301edec63eeeab3f7e24a303b7168ded1341b66ef09b44d05ea7","last_reissued_at":"2026-07-05T03:27:57.418537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:57.418537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying and Improving Transferability in Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guojun Zhang, Han Zhao, Pascal Poupart, Yaoliang Yu","submitted_at":"2021-06-07T14:04:32Z","abstract_excerpt":"Out-of-distribution generalization is one of the key challenges when transferring a model from the lab to the real world. Existing efforts mostly focus on building invariant features among source and target domains. Based on invariant features, a high-performing classifier on source domains could hopefully behave equally well on a target domain. In other words, the invariant features are \\emph{transferable}. However, in practice, there are no perfectly transferable features, and some algorithms seem to learn \"more transferable\" features than others. How can we understand and quantify such \\emp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03632","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/2106.03632/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":"2106.03632","created_at":"2026-07-05T03:27:57.418602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03632v2","created_at":"2026-07-05T03:27:57.418602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03632","created_at":"2026-07-05T03:27:57.418602+00:00"},{"alias_kind":"pith_short_12","alias_value":"EB2JW3EVCEYB","created_at":"2026-07-05T03:27:57.418602+00:00"},{"alias_kind":"pith_short_16","alias_value":"EB2JW3EVCEYB5XWG","created_at":"2026-07-05T03:27:57.418602+00:00"},{"alias_kind":"pith_short_8","alias_value":"EB2JW3EV","created_at":"2026-07-05T03:27:57.418602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07378","citing_title":"Moment Alignment: Unifying Gradient and Hessian Matching for Domain Generalization","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EB2JW3EVCEYB5XWGH3XKWP36ES","json":"https://pith.science/pith/EB2JW3EVCEYB5XWGH3XKWP36ES.json","graph_json":"https://pith.science/api/pith-number/EB2JW3EVCEYB5XWGH3XKWP36ES/graph.json","events_json":"https://pith.science/api/pith-number/EB2JW3EVCEYB5XWGH3XKWP36ES/events.json","paper":"https://pith.science/paper/EB2JW3EV"},"agent_actions":{"view_html":"https://pith.science/pith/EB2JW3EVCEYB5XWGH3XKWP36ES","download_json":"https://pith.science/pith/EB2JW3EVCEYB5XWGH3XKWP36ES.json","view_paper":"https://pith.science/paper/EB2JW3EV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03632&json=true","fetch_graph":"https://pith.science/api/pith-number/EB2JW3EVCEYB5XWGH3XKWP36ES/graph.json","fetch_events":"https://pith.science/api/pith-number/EB2JW3EVCEYB5XWGH3XKWP36ES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EB2JW3EVCEYB5XWGH3XKWP36ES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EB2JW3EVCEYB5XWGH3XKWP36ES/action/storage_attestation","attest_author":"https://pith.science/pith/EB2JW3EVCEYB5XWGH3XKWP36ES/action/author_attestation","sign_citation":"https://pith.science/pith/EB2JW3EVCEYB5XWGH3XKWP36ES/action/citation_signature","submit_replication":"https://pith.science/pith/EB2JW3EVCEYB5XWGH3XKWP36ES/action/replication_record"}},"created_at":"2026-07-05T03:27:57.418602+00:00","updated_at":"2026-07-05T03:27:57.418602+00:00"}