{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:ES2IMB3AOKIRB7O6C62RHXFKW7","short_pith_number":"pith:ES2IMB3A","schema_version":"1.0","canonical_sha256":"24b4860760729110fdde17b513dcaab7d8fa6d222dda2040f86a49cd28f6c298","source":{"kind":"arxiv","id":"1102.1808","version":3},"attestation_state":"computed","paper":{"title":"From Machine Learning to Machine Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Leon Bottou","submitted_at":"2011-02-09T08:25:36Z","abstract_excerpt":"A plausible definition of \"reasoning\" could be \"algebraically manipulating previously acquired knowledge in order to answer a new question\". This definition covers first-order logical inference or probabilistic inference. It also includes much simpler manipulations commonly used to build large learning systems. For instance, we can build an optical character recognition system by first training a character segmenter, an isolated character recognizer, and a language model, using appropriate labeled training sets. Adequately concatenating these modules and fine tuning the resulting system can be"},"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":"1102.1808","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-02-09T08:25:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3950ee601fa70574384622fa39e9850c8032663a69afd35b24cb33ce5c5da25b","abstract_canon_sha256":"bfb3730f11db476f68b6e761e0ba2b366b1712f3f19562e9fbaa707e31ea6390"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:28:56.498175Z","signature_b64":"V11ypBLiHSjAwcAyHRKnx7FUTPqfxtAmHTDbatAXz8QDwJRVRL9Cdp5kQ+nLAmcyzxdziaM3rNLHEYtXSn6BDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24b4860760729110fdde17b513dcaab7d8fa6d222dda2040f86a49cd28f6c298","last_reissued_at":"2026-05-18T04:28:56.497665Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:28:56.497665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Machine Learning to Machine Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Leon Bottou","submitted_at":"2011-02-09T08:25:36Z","abstract_excerpt":"A plausible definition of \"reasoning\" could be \"algebraically manipulating previously acquired knowledge in order to answer a new question\". This definition covers first-order logical inference or probabilistic inference. It also includes much simpler manipulations commonly used to build large learning systems. For instance, we can build an optical character recognition system by first training a character segmenter, an isolated character recognizer, and a language model, using appropriate labeled training sets. Adequately concatenating these modules and fine tuning the resulting system can be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1102.1808","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":""},"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":"1102.1808","created_at":"2026-05-18T04:28:56.497732+00:00"},{"alias_kind":"arxiv_version","alias_value":"1102.1808v3","created_at":"2026-05-18T04:28:56.497732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1102.1808","created_at":"2026-05-18T04:28:56.497732+00:00"},{"alias_kind":"pith_short_12","alias_value":"ES2IMB3AOKIR","created_at":"2026-05-18T12:26:28.662955+00:00"},{"alias_kind":"pith_short_16","alias_value":"ES2IMB3AOKIRB7O6","created_at":"2026-05-18T12:26:28.662955+00:00"},{"alias_kind":"pith_short_8","alias_value":"ES2IMB3A","created_at":"2026-05-18T12:26:28.662955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.14751","citing_title":"AI for the Open-World: the Learning Principles","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ES2IMB3AOKIRB7O6C62RHXFKW7","json":"https://pith.science/pith/ES2IMB3AOKIRB7O6C62RHXFKW7.json","graph_json":"https://pith.science/api/pith-number/ES2IMB3AOKIRB7O6C62RHXFKW7/graph.json","events_json":"https://pith.science/api/pith-number/ES2IMB3AOKIRB7O6C62RHXFKW7/events.json","paper":"https://pith.science/paper/ES2IMB3A"},"agent_actions":{"view_html":"https://pith.science/pith/ES2IMB3AOKIRB7O6C62RHXFKW7","download_json":"https://pith.science/pith/ES2IMB3AOKIRB7O6C62RHXFKW7.json","view_paper":"https://pith.science/paper/ES2IMB3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1102.1808&json=true","fetch_graph":"https://pith.science/api/pith-number/ES2IMB3AOKIRB7O6C62RHXFKW7/graph.json","fetch_events":"https://pith.science/api/pith-number/ES2IMB3AOKIRB7O6C62RHXFKW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ES2IMB3AOKIRB7O6C62RHXFKW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ES2IMB3AOKIRB7O6C62RHXFKW7/action/storage_attestation","attest_author":"https://pith.science/pith/ES2IMB3AOKIRB7O6C62RHXFKW7/action/author_attestation","sign_citation":"https://pith.science/pith/ES2IMB3AOKIRB7O6C62RHXFKW7/action/citation_signature","submit_replication":"https://pith.science/pith/ES2IMB3AOKIRB7O6C62RHXFKW7/action/replication_record"}},"created_at":"2026-05-18T04:28:56.497732+00:00","updated_at":"2026-05-18T04:28:56.497732+00:00"}