{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZJAEVJXFYBUL4VIZDTZHIO6S7Y","short_pith_number":"pith:ZJAEVJXF","schema_version":"1.0","canonical_sha256":"ca404aa6e5c068be55191cf2743bd2fe1e980a52b59cc0b02c3573c057221d56","source":{"kind":"arxiv","id":"2506.16704","version":3},"attestation_state":"computed","paper":{"title":"How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cynthia Dwork, Han Shao, Lunjia Hu","submitted_at":"2025-06-20T02:50:14Z","abstract_excerpt":"We study a fundamental question of domain generalization: given a family of domains (i.e., data distributions), how many randomly sampled domains do we need to collect data from in order to learn a model that performs reasonably well on every seen and unseen domain in the family? We model this problem in the PAC framework and introduce a new combinatorial measure, which we call the domain shattering dimension. We show that this dimension characterizes the domain sample complexity. Furthermore, we establish a tight quantitative relationship between the domain shattering dimension and the classi"},"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":"2506.16704","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T02:50:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"78b018516fed71c271c41e9e53d7542b6939b0dca6c0f9a5b8578462204276cc","abstract_canon_sha256":"6b80fe9ed1f616e674f3b7e24bf635972ab5e47ecca976db5163fe3ce4090d66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:05:03.724351Z","signature_b64":"Tnx7/n7grj5ohgNolwelPJlpbBH4zhh2Hb6jUmopPC9rMiY/pAoFNYpRzo9gSkck7x87EwGAEkIHj04yYp7FCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca404aa6e5c068be55191cf2743bd2fe1e980a52b59cc0b02c3573c057221d56","last_reissued_at":"2026-06-02T03:05:03.723809Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:05:03.723809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cynthia Dwork, Han Shao, Lunjia Hu","submitted_at":"2025-06-20T02:50:14Z","abstract_excerpt":"We study a fundamental question of domain generalization: given a family of domains (i.e., data distributions), how many randomly sampled domains do we need to collect data from in order to learn a model that performs reasonably well on every seen and unseen domain in the family? We model this problem in the PAC framework and introduce a new combinatorial measure, which we call the domain shattering dimension. We show that this dimension characterizes the domain sample complexity. Furthermore, we establish a tight quantitative relationship between the domain shattering dimension and the classi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16704","kind":"arxiv","version":3},"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/2506.16704/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":"2506.16704","created_at":"2026-06-02T03:05:03.723877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16704v3","created_at":"2026-06-02T03:05:03.723877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16704","created_at":"2026-06-02T03:05:03.723877+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJAEVJXFYBUL","created_at":"2026-06-02T03:05:03.723877+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJAEVJXFYBUL4VIZ","created_at":"2026-06-02T03:05:03.723877+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJAEVJXF","created_at":"2026-06-02T03:05:03.723877+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJAEVJXFYBUL4VIZDTZHIO6S7Y","json":"https://pith.science/pith/ZJAEVJXFYBUL4VIZDTZHIO6S7Y.json","graph_json":"https://pith.science/api/pith-number/ZJAEVJXFYBUL4VIZDTZHIO6S7Y/graph.json","events_json":"https://pith.science/api/pith-number/ZJAEVJXFYBUL4VIZDTZHIO6S7Y/events.json","paper":"https://pith.science/paper/ZJAEVJXF"},"agent_actions":{"view_html":"https://pith.science/pith/ZJAEVJXFYBUL4VIZDTZHIO6S7Y","download_json":"https://pith.science/pith/ZJAEVJXFYBUL4VIZDTZHIO6S7Y.json","view_paper":"https://pith.science/paper/ZJAEVJXF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16704&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJAEVJXFYBUL4VIZDTZHIO6S7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJAEVJXFYBUL4VIZDTZHIO6S7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJAEVJXFYBUL4VIZDTZHIO6S7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJAEVJXFYBUL4VIZDTZHIO6S7Y/action/storage_attestation","attest_author":"https://pith.science/pith/ZJAEVJXFYBUL4VIZDTZHIO6S7Y/action/author_attestation","sign_citation":"https://pith.science/pith/ZJAEVJXFYBUL4VIZDTZHIO6S7Y/action/citation_signature","submit_replication":"https://pith.science/pith/ZJAEVJXFYBUL4VIZDTZHIO6S7Y/action/replication_record"}},"created_at":"2026-06-02T03:05:03.723877+00:00","updated_at":"2026-06-02T03:05:03.723877+00:00"}