{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OWL2L6HIMTKW53JMJGDVVU5EYK","short_pith_number":"pith:OWL2L6HI","schema_version":"1.0","canonical_sha256":"7597a5f8e864d56eed2c49875ad3a4c28f6eb65a6ebae454672ece80fa4a844c","source":{"kind":"arxiv","id":"2110.11328","version":2},"attestation_state":"computed","paper":{"title":"A Fine-Grained Analysis on Distribution Shift","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Florian Stimberg, Ira Ktena, Krishnamurthy Dvijotham, Olivia Wiles, Sven Gowal, Sylvestre Alvise-Rebuffi, Taylan Cemgil","submitted_at":"2021-10-21T17:57:08Z","abstract_excerpt":"Robustness to distribution shifts is critical for deploying machine learning models in the real world. Despite this necessity, there has been little work in defining the underlying mechanisms that cause these shifts and evaluating the robustness of algorithms across multiple, different distribution shifts. To this end, we introduce a framework that enables fine-grained analysis of various distribution shifts. We provide a holistic analysis of current state-of-the-art methods by evaluating 19 distinct methods grouped into five categories across both synthetic and real-world datasets. Overall, w"},"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":"2110.11328","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-21T17:57:08Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a97ac3ecbdaf52031c69ddd9c70cf65be1b12f7747a3378633f68d5d9ca3b082","abstract_canon_sha256":"bc28def5c3cbf8f6e239d0a4b770d71926d4d4dbbbbd4f28e248d2da031355af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:13.643889Z","signature_b64":"MfNA1SUPO/xXS+ka/RpYHTGV9029g7LIOifjhvmvrJJEQ5iJoX1xuXOTNOHpDov7FPE6DywPuNMSaBBVI1c/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7597a5f8e864d56eed2c49875ad3a4c28f6eb65a6ebae454672ece80fa4a844c","last_reissued_at":"2026-07-05T03:35:13.642147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:13.642147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Fine-Grained Analysis on Distribution Shift","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Florian Stimberg, Ira Ktena, Krishnamurthy Dvijotham, Olivia Wiles, Sven Gowal, Sylvestre Alvise-Rebuffi, Taylan Cemgil","submitted_at":"2021-10-21T17:57:08Z","abstract_excerpt":"Robustness to distribution shifts is critical for deploying machine learning models in the real world. Despite this necessity, there has been little work in defining the underlying mechanisms that cause these shifts and evaluating the robustness of algorithms across multiple, different distribution shifts. To this end, we introduce a framework that enables fine-grained analysis of various distribution shifts. We provide a holistic analysis of current state-of-the-art methods by evaluating 19 distinct methods grouped into five categories across both synthetic and real-world datasets. Overall, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.11328","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/2110.11328/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":"2110.11328","created_at":"2026-07-05T03:35:13.643366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.11328v2","created_at":"2026-07-05T03:35:13.643366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.11328","created_at":"2026-07-05T03:35:13.643366+00:00"},{"alias_kind":"pith_short_12","alias_value":"OWL2L6HIMTKW","created_at":"2026-07-05T03:35:13.643366+00:00"},{"alias_kind":"pith_short_16","alias_value":"OWL2L6HIMTKW53JM","created_at":"2026-07-05T03:35:13.643366+00:00"},{"alias_kind":"pith_short_8","alias_value":"OWL2L6HI","created_at":"2026-07-05T03:35:13.643366+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00620","citing_title":"Identifying Latent Concepts and Structures for Generalized Category Discovery","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06522","citing_title":"Agentic AIs Are the Missing Paradigm for Out-of-Distribution Generalization in Foundation Models","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OWL2L6HIMTKW53JMJGDVVU5EYK","json":"https://pith.science/pith/OWL2L6HIMTKW53JMJGDVVU5EYK.json","graph_json":"https://pith.science/api/pith-number/OWL2L6HIMTKW53JMJGDVVU5EYK/graph.json","events_json":"https://pith.science/api/pith-number/OWL2L6HIMTKW53JMJGDVVU5EYK/events.json","paper":"https://pith.science/paper/OWL2L6HI"},"agent_actions":{"view_html":"https://pith.science/pith/OWL2L6HIMTKW53JMJGDVVU5EYK","download_json":"https://pith.science/pith/OWL2L6HIMTKW53JMJGDVVU5EYK.json","view_paper":"https://pith.science/paper/OWL2L6HI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.11328&json=true","fetch_graph":"https://pith.science/api/pith-number/OWL2L6HIMTKW53JMJGDVVU5EYK/graph.json","fetch_events":"https://pith.science/api/pith-number/OWL2L6HIMTKW53JMJGDVVU5EYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OWL2L6HIMTKW53JMJGDVVU5EYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OWL2L6HIMTKW53JMJGDVVU5EYK/action/storage_attestation","attest_author":"https://pith.science/pith/OWL2L6HIMTKW53JMJGDVVU5EYK/action/author_attestation","sign_citation":"https://pith.science/pith/OWL2L6HIMTKW53JMJGDVVU5EYK/action/citation_signature","submit_replication":"https://pith.science/pith/OWL2L6HIMTKW53JMJGDVVU5EYK/action/replication_record"}},"created_at":"2026-07-05T03:35:13.643366+00:00","updated_at":"2026-07-05T03:35:13.643366+00:00"}