{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OOCKOH3BJ3FWQTEZMOUH4NBOGW","short_pith_number":"pith:OOCKOH3B","schema_version":"1.0","canonical_sha256":"7384a71f614ecb684c9963a87e342e358823601b064b1cd1d9fddc1ae5a8e07e","source":{"kind":"arxiv","id":"2410.08977","version":1},"attestation_state":"computed","paper":{"title":"Online-to-PAC generalization bounds under graph-mixing dependencies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Baptiste Ab\\'el\\`es, Eugenio Clerico, Gergely Neu","submitted_at":"2024-10-11T16:49:01Z","abstract_excerpt":"Traditional generalization results in statistical learning require a training data set made of independently drawn examples. Most of the recent efforts to relax this independence assumption have considered either purely temporal (mixing) dependencies, or graph-dependencies, where non-adjacent vertices correspond to independent random variables. Both approaches have their own limitations, the former requiring a temporal ordered structure, and the latter lacking a way to quantify the strength of inter-dependencies. In this work, we bridge these two lines of work by proposing a framework where de"},"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":"2410.08977","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-11T16:49:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aa7b6cffe85681df678e63b14cf05721971f91a9590e3a7250a24c753bee3159","abstract_canon_sha256":"98c1b0c97d9df97c6f6a78e9434a3a66dbe398cf5e9ff023690c23de5acc8d4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:20.273509Z","signature_b64":"mCMebKYGVFRki6g+Kf9DIiMmtiNr1z3JXr8JLu8j9uPlSJGyN+ZS6qQ0bbh+kS4s1jagZJEaXAwR8adyb17HAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7384a71f614ecb684c9963a87e342e358823601b064b1cd1d9fddc1ae5a8e07e","last_reissued_at":"2026-07-05T09:19:20.272950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:20.272950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online-to-PAC generalization bounds under graph-mixing dependencies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Baptiste Ab\\'el\\`es, Eugenio Clerico, Gergely Neu","submitted_at":"2024-10-11T16:49:01Z","abstract_excerpt":"Traditional generalization results in statistical learning require a training data set made of independently drawn examples. Most of the recent efforts to relax this independence assumption have considered either purely temporal (mixing) dependencies, or graph-dependencies, where non-adjacent vertices correspond to independent random variables. Both approaches have their own limitations, the former requiring a temporal ordered structure, and the latter lacking a way to quantify the strength of inter-dependencies. In this work, we bridge these two lines of work by proposing a framework where de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08977","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/2410.08977/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":"2410.08977","created_at":"2026-07-05T09:19:20.273012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08977v1","created_at":"2026-07-05T09:19:20.273012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08977","created_at":"2026-07-05T09:19:20.273012+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOCKOH3BJ3FW","created_at":"2026-07-05T09:19:20.273012+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOCKOH3BJ3FWQTEZ","created_at":"2026-07-05T09:19:20.273012+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOCKOH3B","created_at":"2026-07-05T09:19:20.273012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07826","citing_title":"An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOCKOH3BJ3FWQTEZMOUH4NBOGW","json":"https://pith.science/pith/OOCKOH3BJ3FWQTEZMOUH4NBOGW.json","graph_json":"https://pith.science/api/pith-number/OOCKOH3BJ3FWQTEZMOUH4NBOGW/graph.json","events_json":"https://pith.science/api/pith-number/OOCKOH3BJ3FWQTEZMOUH4NBOGW/events.json","paper":"https://pith.science/paper/OOCKOH3B"},"agent_actions":{"view_html":"https://pith.science/pith/OOCKOH3BJ3FWQTEZMOUH4NBOGW","download_json":"https://pith.science/pith/OOCKOH3BJ3FWQTEZMOUH4NBOGW.json","view_paper":"https://pith.science/paper/OOCKOH3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08977&json=true","fetch_graph":"https://pith.science/api/pith-number/OOCKOH3BJ3FWQTEZMOUH4NBOGW/graph.json","fetch_events":"https://pith.science/api/pith-number/OOCKOH3BJ3FWQTEZMOUH4NBOGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOCKOH3BJ3FWQTEZMOUH4NBOGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOCKOH3BJ3FWQTEZMOUH4NBOGW/action/storage_attestation","attest_author":"https://pith.science/pith/OOCKOH3BJ3FWQTEZMOUH4NBOGW/action/author_attestation","sign_citation":"https://pith.science/pith/OOCKOH3BJ3FWQTEZMOUH4NBOGW/action/citation_signature","submit_replication":"https://pith.science/pith/OOCKOH3BJ3FWQTEZMOUH4NBOGW/action/replication_record"}},"created_at":"2026-07-05T09:19:20.273012+00:00","updated_at":"2026-07-05T09:19:20.273012+00:00"}