{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4JYNZT3H4WH355N5YYR5DVCUVD","short_pith_number":"pith:4JYNZT3H","schema_version":"1.0","canonical_sha256":"e270dccf67e58fbef5bdc623d1d454a8de0f4bdb3a60e3c0b1445f1cdd2f5739","source":{"kind":"arxiv","id":"2406.11814","version":5},"attestation_state":"computed","paper":{"title":"Stochastic Neural Network Symmetrisation in Markov Categories","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.CT"],"primary_cat":"stat.ML","authors_text":"Rob Cornish","submitted_at":"2024-06-17T17:54:42Z","abstract_excerpt":"We consider the problem of symmetrising a neural network along a group homomorphism: given a homomorphism $\\varphi : H \\to G$, we would like a procedure that converts $H$-equivariant neural networks to $G$-equivariant ones. We formulate this in terms of Markov categories, which allows us to consider neural networks whose outputs may be stochastic, but with measure-theoretic details abstracted away. We obtain a flexible and compositional framework for symmetrisation that relies on minimal assumptions about the structure of the group and the underlying neural network architecture. Our approach r"},"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":"2406.11814","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-06-17T17:54:42Z","cross_cats_sorted":["cs.LG","math.CT"],"title_canon_sha256":"b8dcf0d461a580329456b708ef83fd60addae0bdf0eea3e4ead245d85f5750e5","abstract_canon_sha256":"755f531f88c1469c8a457f1c531db13d6f2c806eae5d8e7dc646e93f130334d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:58.740502Z","signature_b64":"j5Y5ANu52gbpFhqKEM3B8bNcB3cDJpUcEU43XFaAbAnBbULtoKNytIMOCIao+wgqq8nW2jKRse7gpjbpPvdQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e270dccf67e58fbef5bdc623d1d454a8de0f4bdb3a60e3c0b1445f1cdd2f5739","last_reissued_at":"2026-07-05T09:58:58.740026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:58.740026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Neural Network Symmetrisation in Markov Categories","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.CT"],"primary_cat":"stat.ML","authors_text":"Rob Cornish","submitted_at":"2024-06-17T17:54:42Z","abstract_excerpt":"We consider the problem of symmetrising a neural network along a group homomorphism: given a homomorphism $\\varphi : H \\to G$, we would like a procedure that converts $H$-equivariant neural networks to $G$-equivariant ones. We formulate this in terms of Markov categories, which allows us to consider neural networks whose outputs may be stochastic, but with measure-theoretic details abstracted away. We obtain a flexible and compositional framework for symmetrisation that relies on minimal assumptions about the structure of the group and the underlying neural network architecture. Our approach r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11814","kind":"arxiv","version":5},"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/2406.11814/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":"2406.11814","created_at":"2026-07-05T09:58:58.740084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11814v5","created_at":"2026-07-05T09:58:58.740084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11814","created_at":"2026-07-05T09:58:58.740084+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JYNZT3H4WH3","created_at":"2026-07-05T09:58:58.740084+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JYNZT3H4WH355N5","created_at":"2026-07-05T09:58:58.740084+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JYNZT3H","created_at":"2026-07-05T09:58:58.740084+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.14716","citing_title":"Approaching the Continuous from the Discrete: an Infinite Tensor Product Construction","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4JYNZT3H4WH355N5YYR5DVCUVD","json":"https://pith.science/pith/4JYNZT3H4WH355N5YYR5DVCUVD.json","graph_json":"https://pith.science/api/pith-number/4JYNZT3H4WH355N5YYR5DVCUVD/graph.json","events_json":"https://pith.science/api/pith-number/4JYNZT3H4WH355N5YYR5DVCUVD/events.json","paper":"https://pith.science/paper/4JYNZT3H"},"agent_actions":{"view_html":"https://pith.science/pith/4JYNZT3H4WH355N5YYR5DVCUVD","download_json":"https://pith.science/pith/4JYNZT3H4WH355N5YYR5DVCUVD.json","view_paper":"https://pith.science/paper/4JYNZT3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11814&json=true","fetch_graph":"https://pith.science/api/pith-number/4JYNZT3H4WH355N5YYR5DVCUVD/graph.json","fetch_events":"https://pith.science/api/pith-number/4JYNZT3H4WH355N5YYR5DVCUVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JYNZT3H4WH355N5YYR5DVCUVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JYNZT3H4WH355N5YYR5DVCUVD/action/storage_attestation","attest_author":"https://pith.science/pith/4JYNZT3H4WH355N5YYR5DVCUVD/action/author_attestation","sign_citation":"https://pith.science/pith/4JYNZT3H4WH355N5YYR5DVCUVD/action/citation_signature","submit_replication":"https://pith.science/pith/4JYNZT3H4WH355N5YYR5DVCUVD/action/replication_record"}},"created_at":"2026-07-05T09:58:58.740084+00:00","updated_at":"2026-07-05T09:58:58.740084+00:00"}