{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F5H6GOIVFXJ6X6PXQAXPMBJNR6","short_pith_number":"pith:F5H6GOIV","schema_version":"1.0","canonical_sha256":"2f4fe339152dd3ebf9f7802ef6052d8fae5c94f332632bd1ec464b082f0d9aa3","source":{"kind":"arxiv","id":"2403.05523","version":2},"attestation_state":"computed","paper":{"title":"Beyond Finite Data: Towards Data-free Out-of-distribution Generalization via Extrapolation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Edith Ngai, Haohan Wang, Sucheng Ren, Weipeng Deng, Yijiang Li, Ying Gao, Yuzhi Xu","submitted_at":"2024-03-08T18:44:23Z","abstract_excerpt":"Out-of-distribution (OOD) generalization is a favorable yet challenging property for deep neural networks. The core challenges lie in the limited availability of source domains that help models learn an invariant representation from the spurious features. Various domain augmentation have been proposed but largely rely on interpolating existing domains and frequently face difficulties in creating truly \"novel\" domains. Humans, on the other hand, can easily extrapolate novel domains, thus, an intriguing question arises: How can neural networks extrapolate like humans and achieve OOD generalizati"},"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":"2403.05523","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-08T18:44:23Z","cross_cats_sorted":[],"title_canon_sha256":"af2254095ccf00bd82c4c16dab086fe33f9eac4d35aeaa9cbeb8b224438e5d2d","abstract_canon_sha256":"80e88749f8f475f3812305881ba6c21f807c1e8efeb48a1203560b32f38fbd39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:37.189464Z","signature_b64":"Urt/ZPsb4sRFVrqfNCap5YAfn5g1rt8jfMCFWN1AVao/l/UQUMFQclMz1wa1LoC11AxtWlT/LQ4Cklsbat79Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f4fe339152dd3ebf9f7802ef6052d8fae5c94f332632bd1ec464b082f0d9aa3","last_reissued_at":"2026-07-05T07:54:37.188903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:37.188903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Finite Data: Towards Data-free Out-of-distribution Generalization via Extrapolation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Edith Ngai, Haohan Wang, Sucheng Ren, Weipeng Deng, Yijiang Li, Ying Gao, Yuzhi Xu","submitted_at":"2024-03-08T18:44:23Z","abstract_excerpt":"Out-of-distribution (OOD) generalization is a favorable yet challenging property for deep neural networks. The core challenges lie in the limited availability of source domains that help models learn an invariant representation from the spurious features. Various domain augmentation have been proposed but largely rely on interpolating existing domains and frequently face difficulties in creating truly \"novel\" domains. Humans, on the other hand, can easily extrapolate novel domains, thus, an intriguing question arises: How can neural networks extrapolate like humans and achieve OOD generalizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05523","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/2403.05523/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":"2403.05523","created_at":"2026-07-05T07:54:37.188980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.05523v2","created_at":"2026-07-05T07:54:37.188980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05523","created_at":"2026-07-05T07:54:37.188980+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5H6GOIVFXJ6","created_at":"2026-07-05T07:54:37.188980+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5H6GOIVFXJ6X6PX","created_at":"2026-07-05T07:54:37.188980+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5H6GOIV","created_at":"2026-07-05T07:54:37.188980+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05531","citing_title":"Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F5H6GOIVFXJ6X6PXQAXPMBJNR6","json":"https://pith.science/pith/F5H6GOIVFXJ6X6PXQAXPMBJNR6.json","graph_json":"https://pith.science/api/pith-number/F5H6GOIVFXJ6X6PXQAXPMBJNR6/graph.json","events_json":"https://pith.science/api/pith-number/F5H6GOIVFXJ6X6PXQAXPMBJNR6/events.json","paper":"https://pith.science/paper/F5H6GOIV"},"agent_actions":{"view_html":"https://pith.science/pith/F5H6GOIVFXJ6X6PXQAXPMBJNR6","download_json":"https://pith.science/pith/F5H6GOIVFXJ6X6PXQAXPMBJNR6.json","view_paper":"https://pith.science/paper/F5H6GOIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.05523&json=true","fetch_graph":"https://pith.science/api/pith-number/F5H6GOIVFXJ6X6PXQAXPMBJNR6/graph.json","fetch_events":"https://pith.science/api/pith-number/F5H6GOIVFXJ6X6PXQAXPMBJNR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5H6GOIVFXJ6X6PXQAXPMBJNR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5H6GOIVFXJ6X6PXQAXPMBJNR6/action/storage_attestation","attest_author":"https://pith.science/pith/F5H6GOIVFXJ6X6PXQAXPMBJNR6/action/author_attestation","sign_citation":"https://pith.science/pith/F5H6GOIVFXJ6X6PXQAXPMBJNR6/action/citation_signature","submit_replication":"https://pith.science/pith/F5H6GOIVFXJ6X6PXQAXPMBJNR6/action/replication_record"}},"created_at":"2026-07-05T07:54:37.188980+00:00","updated_at":"2026-07-05T07:54:37.188980+00:00"}