{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LJLC77WZOETFWQISRWRAWHC72V","short_pith_number":"pith:LJLC77WZ","schema_version":"1.0","canonical_sha256":"5a562ffed971265b41128da20b1c5fd57d669171b025f4755a9e83ce3bd0a60b","source":{"kind":"arxiv","id":"2605.24608","version":1},"attestation_state":"computed","paper":{"title":"Lattice theory and algebraic models for deep convolutional learning based on mathematical morphology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Gustavo (Jesus) Angulo","submitted_at":"2026-05-23T14:43:52Z","abstract_excerpt":"We develop a rigorous algebraic framework for deep convolutional architectures, CNNs, ResNets, and encoder--decoder networks such as UNet, grounded in lattice theory and mathematical morphology. The central tool is the Matheron--Maragos--Banon--Barrera (MMBB) universal representation theory for translation-invariant operators, which we apply systematically to every layer of a standard deep network.\n  The principal finding is that the standard CNN pipeline (linear convolution~$+$ ReLU~$+$ flat max-pooling) is a cross-lattice operator: the convolution is an erosion in the Fourier inf-semilattice"},"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":"2605.24608","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T14:43:52Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"02c6bae4c6c7447dbccf0eec17eee39ff000f254fba5ee5b753154174e35bdae","abstract_canon_sha256":"e57dbf9cc34fb054acd6c15ebc8c6f864c6f822bc1fce282c82dc9476cfe8c18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:48.691170Z","signature_b64":"iGpU7qIQEEGNfFifETM2fepoPpK1qON4vH9JuMZ/F5lInJiKDRO6GqWeEuMxPtVzvacGq/Gb70qcdhNtjzytDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a562ffed971265b41128da20b1c5fd57d669171b025f4755a9e83ce3bd0a60b","last_reissued_at":"2026-05-26T01:03:48.690378Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:48.690378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lattice theory and algebraic models for deep convolutional learning based on mathematical morphology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Gustavo (Jesus) Angulo","submitted_at":"2026-05-23T14:43:52Z","abstract_excerpt":"We develop a rigorous algebraic framework for deep convolutional architectures, CNNs, ResNets, and encoder--decoder networks such as UNet, grounded in lattice theory and mathematical morphology. The central tool is the Matheron--Maragos--Banon--Barrera (MMBB) universal representation theory for translation-invariant operators, which we apply systematically to every layer of a standard deep network.\n  The principal finding is that the standard CNN pipeline (linear convolution~$+$ ReLU~$+$ flat max-pooling) is a cross-lattice operator: the convolution is an erosion in the Fourier inf-semilattice"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24608","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/2605.24608/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":"2605.24608","created_at":"2026-05-26T01:03:48.690498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24608v1","created_at":"2026-05-26T01:03:48.690498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24608","created_at":"2026-05-26T01:03:48.690498+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJLC77WZOETF","created_at":"2026-05-26T01:03:48.690498+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJLC77WZOETFWQIS","created_at":"2026-05-26T01:03:48.690498+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJLC77WZ","created_at":"2026-05-26T01:03:48.690498+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/LJLC77WZOETFWQISRWRAWHC72V","json":"https://pith.science/pith/LJLC77WZOETFWQISRWRAWHC72V.json","graph_json":"https://pith.science/api/pith-number/LJLC77WZOETFWQISRWRAWHC72V/graph.json","events_json":"https://pith.science/api/pith-number/LJLC77WZOETFWQISRWRAWHC72V/events.json","paper":"https://pith.science/paper/LJLC77WZ"},"agent_actions":{"view_html":"https://pith.science/pith/LJLC77WZOETFWQISRWRAWHC72V","download_json":"https://pith.science/pith/LJLC77WZOETFWQISRWRAWHC72V.json","view_paper":"https://pith.science/paper/LJLC77WZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24608&json=true","fetch_graph":"https://pith.science/api/pith-number/LJLC77WZOETFWQISRWRAWHC72V/graph.json","fetch_events":"https://pith.science/api/pith-number/LJLC77WZOETFWQISRWRAWHC72V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJLC77WZOETFWQISRWRAWHC72V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJLC77WZOETFWQISRWRAWHC72V/action/storage_attestation","attest_author":"https://pith.science/pith/LJLC77WZOETFWQISRWRAWHC72V/action/author_attestation","sign_citation":"https://pith.science/pith/LJLC77WZOETFWQISRWRAWHC72V/action/citation_signature","submit_replication":"https://pith.science/pith/LJLC77WZOETFWQISRWRAWHC72V/action/replication_record"}},"created_at":"2026-05-26T01:03:48.690498+00:00","updated_at":"2026-05-26T01:03:48.690498+00:00"}