{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OPSEG5A4UT7LZDAFBVOUP4BCN3","short_pith_number":"pith:OPSEG5A4","schema_version":"1.0","canonical_sha256":"73e443741ca4febc8c050d5d47f0226ed0cd3c3e7f2cc782a900fb78927dc000","source":{"kind":"arxiv","id":"1905.02072","version":1},"attestation_state":"computed","paper":{"title":"Characterizing the invariances of learning algorithms using category theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.CT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kenneth D. Harris","submitted_at":"2019-05-06T14:48:33Z","abstract_excerpt":"Many learning algorithms have invariances: when their training data is transformed in certain ways, the function they learn transforms in a predictable manner. Here we formalize this notion using concepts from the mathematical field of category theory. The invariances that a supervised learning algorithm possesses are formalized by categories of predictor and target spaces, whose morphisms represent the algorithm's invariances, and an index category whose morphisms represent permutations of the training examples. An invariant learning algorithm is a natural transformation between two functors "},"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":"1905.02072","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-06T14:48:33Z","cross_cats_sorted":["math.CT","stat.ML"],"title_canon_sha256":"ab6c822104fb005c4bc7f689a76e5a1a75d57d98ed3679e01f876a09380f9b98","abstract_canon_sha256":"05f2c5d40dbf3c8497418df24af3652be33747b6e23a4643de21a17f41b98312"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:56.499029Z","signature_b64":"Hz63vhV250dfJm8Z5M1ECq5E9/0EtN0k+dv4gQDG4BYnB1TarzYMfXgz9f0YXlWP8vI5J0mQSZ42enqF7Q6kAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73e443741ca4febc8c050d5d47f0226ed0cd3c3e7f2cc782a900fb78927dc000","last_reissued_at":"2026-05-17T23:46:56.498416Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:56.498416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Characterizing the invariances of learning algorithms using category theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.CT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kenneth D. Harris","submitted_at":"2019-05-06T14:48:33Z","abstract_excerpt":"Many learning algorithms have invariances: when their training data is transformed in certain ways, the function they learn transforms in a predictable manner. Here we formalize this notion using concepts from the mathematical field of category theory. The invariances that a supervised learning algorithm possesses are formalized by categories of predictor and target spaces, whose morphisms represent the algorithm's invariances, and an index category whose morphisms represent permutations of the training examples. An invariant learning algorithm is a natural transformation between two functors "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02072","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":""},"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":"1905.02072","created_at":"2026-05-17T23:46:56.498501+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.02072v1","created_at":"2026-05-17T23:46:56.498501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02072","created_at":"2026-05-17T23:46:56.498501+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPSEG5A4UT7L","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPSEG5A4UT7LZDAF","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPSEG5A4","created_at":"2026-05-18T12:33:24.271573+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/OPSEG5A4UT7LZDAFBVOUP4BCN3","json":"https://pith.science/pith/OPSEG5A4UT7LZDAFBVOUP4BCN3.json","graph_json":"https://pith.science/api/pith-number/OPSEG5A4UT7LZDAFBVOUP4BCN3/graph.json","events_json":"https://pith.science/api/pith-number/OPSEG5A4UT7LZDAFBVOUP4BCN3/events.json","paper":"https://pith.science/paper/OPSEG5A4"},"agent_actions":{"view_html":"https://pith.science/pith/OPSEG5A4UT7LZDAFBVOUP4BCN3","download_json":"https://pith.science/pith/OPSEG5A4UT7LZDAFBVOUP4BCN3.json","view_paper":"https://pith.science/paper/OPSEG5A4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.02072&json=true","fetch_graph":"https://pith.science/api/pith-number/OPSEG5A4UT7LZDAFBVOUP4BCN3/graph.json","fetch_events":"https://pith.science/api/pith-number/OPSEG5A4UT7LZDAFBVOUP4BCN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPSEG5A4UT7LZDAFBVOUP4BCN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPSEG5A4UT7LZDAFBVOUP4BCN3/action/storage_attestation","attest_author":"https://pith.science/pith/OPSEG5A4UT7LZDAFBVOUP4BCN3/action/author_attestation","sign_citation":"https://pith.science/pith/OPSEG5A4UT7LZDAFBVOUP4BCN3/action/citation_signature","submit_replication":"https://pith.science/pith/OPSEG5A4UT7LZDAFBVOUP4BCN3/action/replication_record"}},"created_at":"2026-05-17T23:46:56.498501+00:00","updated_at":"2026-05-17T23:46:56.498501+00:00"}