{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TDUUXFNHYNX3Z4UZFU5DKQAOJU","short_pith_number":"pith:TDUUXFNH","schema_version":"1.0","canonical_sha256":"98e94b95a7c36fbcf2992d3a35400e4d07c45e62157dd3a039274adcbe967123","source":{"kind":"arxiv","id":"2203.06430","version":2},"attestation_state":"computed","paper":{"title":"Categories of Differentiable Polynomial Circuits for Machine Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["math.CT"],"primary_cat":"cs.LG","authors_text":"Fabio Zanasi, Paul Wilson","submitted_at":"2022-03-12T13:03:30Z","abstract_excerpt":"Reverse derivative categories (RDCs) have recently been shown to be a suitable semantic framework for studying machine learning algorithms. Whereas emphasis has been put on training methodologies, less attention has been devoted to particular \\emph{model classes}: the concrete categories whose morphisms represent machine learning models. In this paper we study presentations by generators and equations of classes of RDCs. In particular, we propose \\emph{polynomial circuits} as a suitable machine learning model. We give an axiomatisation for these circuits and prove a functional completeness res"},"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":"2203.06430","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-12T13:03:30Z","cross_cats_sorted":["math.CT"],"title_canon_sha256":"3db24eda0366a1b7b86e1f6ed5e4161efd061e7db7e3eb877bb98c7df4c89a94","abstract_canon_sha256":"006bddf8528ada5580490dcc66133ed95011b77d44b3eeda8a4a1d490793c6db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:11.006442Z","signature_b64":"hhcoacee/oRJG6vN4oRTjdYgoPp/RMLajmfB+d0RTMRJ73wj8bl3DbmLI4k7wM3DrrFpKb5ewp2yMd6Co19pBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98e94b95a7c36fbcf2992d3a35400e4d07c45e62157dd3a039274adcbe967123","last_reissued_at":"2026-07-05T04:21:11.005959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:11.005959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Categories of Differentiable Polynomial Circuits for Machine Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["math.CT"],"primary_cat":"cs.LG","authors_text":"Fabio Zanasi, Paul Wilson","submitted_at":"2022-03-12T13:03:30Z","abstract_excerpt":"Reverse derivative categories (RDCs) have recently been shown to be a suitable semantic framework for studying machine learning algorithms. Whereas emphasis has been put on training methodologies, less attention has been devoted to particular \\emph{model classes}: the concrete categories whose morphisms represent machine learning models. In this paper we study presentations by generators and equations of classes of RDCs. In particular, we propose \\emph{polynomial circuits} as a suitable machine learning model. We give an axiomatisation for these circuits and prove a functional completeness res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06430","kind":"arxiv","version":2},"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/2203.06430/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":"2203.06430","created_at":"2026-07-05T04:21:11.006022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.06430v2","created_at":"2026-07-05T04:21:11.006022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06430","created_at":"2026-07-05T04:21:11.006022+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDUUXFNHYNX3","created_at":"2026-07-05T04:21:11.006022+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDUUXFNHYNX3Z4UZ","created_at":"2026-07-05T04:21:11.006022+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDUUXFNH","created_at":"2026-07-05T04:21:11.006022+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.09326","citing_title":"Accelerating Machine Learning Systems via Category Theory: Applications to Spherical Attention for Gene Regulatory Networks","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TDUUXFNHYNX3Z4UZFU5DKQAOJU","json":"https://pith.science/pith/TDUUXFNHYNX3Z4UZFU5DKQAOJU.json","graph_json":"https://pith.science/api/pith-number/TDUUXFNHYNX3Z4UZFU5DKQAOJU/graph.json","events_json":"https://pith.science/api/pith-number/TDUUXFNHYNX3Z4UZFU5DKQAOJU/events.json","paper":"https://pith.science/paper/TDUUXFNH"},"agent_actions":{"view_html":"https://pith.science/pith/TDUUXFNHYNX3Z4UZFU5DKQAOJU","download_json":"https://pith.science/pith/TDUUXFNHYNX3Z4UZFU5DKQAOJU.json","view_paper":"https://pith.science/paper/TDUUXFNH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.06430&json=true","fetch_graph":"https://pith.science/api/pith-number/TDUUXFNHYNX3Z4UZFU5DKQAOJU/graph.json","fetch_events":"https://pith.science/api/pith-number/TDUUXFNHYNX3Z4UZFU5DKQAOJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDUUXFNHYNX3Z4UZFU5DKQAOJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDUUXFNHYNX3Z4UZFU5DKQAOJU/action/storage_attestation","attest_author":"https://pith.science/pith/TDUUXFNHYNX3Z4UZFU5DKQAOJU/action/author_attestation","sign_citation":"https://pith.science/pith/TDUUXFNHYNX3Z4UZFU5DKQAOJU/action/citation_signature","submit_replication":"https://pith.science/pith/TDUUXFNHYNX3Z4UZFU5DKQAOJU/action/replication_record"}},"created_at":"2026-07-05T04:21:11.006022+00:00","updated_at":"2026-07-05T04:21:11.006022+00:00"}