{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GYC46LNAAMBWV2HNXPHM3XWVUI","short_pith_number":"pith:GYC46LNA","schema_version":"1.0","canonical_sha256":"3605cf2da003036ae8edbbcecdded5a2339dfb5c31c7afa687251412a50936bb","source":{"kind":"arxiv","id":"2410.01565","version":1},"attestation_state":"computed","paper":{"title":"Bayes' Power for Explaining In-Context Learning Generalizations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Noah Hollmann, Samuel M\\\"uller","submitted_at":"2024-10-02T14:01:34Z","abstract_excerpt":"Traditionally, neural network training has been primarily viewed as an approximation of maximum likelihood estimation (MLE). This interpretation originated in a time when training for multiple epochs on small datasets was common and performance was data bound; but it falls short in the era of large-scale single-epoch trainings ushered in by large self-supervised setups, like language models. In this new setup, performance is compute-bound, but data is readily available. As models became more powerful, in-context learning (ICL), i.e., learning in a single forward-pass based on the context, emer"},"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":"2410.01565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T14:01:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"155100adb64c227473b247e13d8155a57e50c73e2f15444b7366c2a86e479e1f","abstract_canon_sha256":"89c0e403e155572123b93ab5df76fd2811bdc51ede6b05174158b5f1b0ae0ddc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:49.357843Z","signature_b64":"RASGpfGL7xTqcPz5KVOHTwh4HvrU+LNfHrTpBHmbUOcYbni14KwHZmMENFqLVzOSfx8EcgFZdmzK5Ftbi0K2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3605cf2da003036ae8edbbcecdded5a2339dfb5c31c7afa687251412a50936bb","last_reissued_at":"2026-07-05T09:14:49.357446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:49.357446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayes' Power for Explaining In-Context Learning Generalizations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Noah Hollmann, Samuel M\\\"uller","submitted_at":"2024-10-02T14:01:34Z","abstract_excerpt":"Traditionally, neural network training has been primarily viewed as an approximation of maximum likelihood estimation (MLE). This interpretation originated in a time when training for multiple epochs on small datasets was common and performance was data bound; but it falls short in the era of large-scale single-epoch trainings ushered in by large self-supervised setups, like language models. In this new setup, performance is compute-bound, but data is readily available. As models became more powerful, in-context learning (ICL), i.e., learning in a single forward-pass based on the context, emer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01565","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/2410.01565/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":"2410.01565","created_at":"2026-07-05T09:14:49.357514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01565v1","created_at":"2026-07-05T09:14:49.357514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01565","created_at":"2026-07-05T09:14:49.357514+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYC46LNAAMBW","created_at":"2026-07-05T09:14:49.357514+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYC46LNAAMBWV2HN","created_at":"2026-07-05T09:14:49.357514+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYC46LNA","created_at":"2026-07-05T09:14:49.357514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23947","citing_title":"Position: The Future of Bayesian Prediction Is Prior-Fitted","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYC46LNAAMBWV2HNXPHM3XWVUI","json":"https://pith.science/pith/GYC46LNAAMBWV2HNXPHM3XWVUI.json","graph_json":"https://pith.science/api/pith-number/GYC46LNAAMBWV2HNXPHM3XWVUI/graph.json","events_json":"https://pith.science/api/pith-number/GYC46LNAAMBWV2HNXPHM3XWVUI/events.json","paper":"https://pith.science/paper/GYC46LNA"},"agent_actions":{"view_html":"https://pith.science/pith/GYC46LNAAMBWV2HNXPHM3XWVUI","download_json":"https://pith.science/pith/GYC46LNAAMBWV2HNXPHM3XWVUI.json","view_paper":"https://pith.science/paper/GYC46LNA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01565&json=true","fetch_graph":"https://pith.science/api/pith-number/GYC46LNAAMBWV2HNXPHM3XWVUI/graph.json","fetch_events":"https://pith.science/api/pith-number/GYC46LNAAMBWV2HNXPHM3XWVUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYC46LNAAMBWV2HNXPHM3XWVUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYC46LNAAMBWV2HNXPHM3XWVUI/action/storage_attestation","attest_author":"https://pith.science/pith/GYC46LNAAMBWV2HNXPHM3XWVUI/action/author_attestation","sign_citation":"https://pith.science/pith/GYC46LNAAMBWV2HNXPHM3XWVUI/action/citation_signature","submit_replication":"https://pith.science/pith/GYC46LNAAMBWV2HNXPHM3XWVUI/action/replication_record"}},"created_at":"2026-07-05T09:14:49.357514+00:00","updated_at":"2026-07-05T09:14:49.357514+00:00"}