{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:D4ELULO7PN27R7ATJL5LXPPLVP","short_pith_number":"pith:D4ELULO7","schema_version":"1.0","canonical_sha256":"1f08ba2ddf7b75f8fc134afabbbdebabc3e17315b949460a534ac87800d56ca5","source":{"kind":"arxiv","id":"2605.28612","version":1},"attestation_state":"computed","paper":{"title":"Learning High-Dimensional Parity Functions with Product Networks using Gradient Descent","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"France), France (2) T\\'el\\'ecom Paris, Ghaya Rekaya (2) ((1) Orange Research, Guillaume Larue (1), Hadi Ghauch (2), Institut Polytechnique de Paris, Louis-Adrien Dufr\\`ene (1), Meylan, Palaiseau, Quentin Lampin (1)","submitted_at":"2026-05-27T15:26:16Z","abstract_excerpt":"Parity functions are fundamental Boolean operations with critical applications across machine learning, cryptography, and error correction. Yet, learning high-dimensional parity functions poses significant challenges: in a general setting, standard neural network architectures typically require exponential sample complexity, making gradient-based optimization intractable for large number of inputs $N$. We demonstrate that compact product-based neural architectures combined with stochastic data sparsity (Bernoulli inputs with $p_e \\leq 1/N$) and appropriate hyperparameter choice enable efficien"},"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":"2605.28612","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T15:26:16Z","cross_cats_sorted":[],"title_canon_sha256":"0ac747da9a8b2b03e0af64525bbecfa46686d4a8a1910f86c05112315375bc0c","abstract_canon_sha256":"6eb4092c0333ca5398066e1b271103e4e56a867151a924f6c7e076c02b503c36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:57.772018Z","signature_b64":"2eVJvBUgHf1uN9QA1KCwgJpLelWNkcJJWi9KnN25OV0EiFJgKNZQG9zaGfmpt6Tw2YruMU9RJ/wB5cPbixaiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f08ba2ddf7b75f8fc134afabbbdebabc3e17315b949460a534ac87800d56ca5","last_reissued_at":"2026-05-28T02:04:57.771609Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:57.771609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning High-Dimensional Parity Functions with Product Networks using Gradient Descent","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"France), France (2) T\\'el\\'ecom Paris, Ghaya Rekaya (2) ((1) Orange Research, Guillaume Larue (1), Hadi Ghauch (2), Institut Polytechnique de Paris, Louis-Adrien Dufr\\`ene (1), Meylan, Palaiseau, Quentin Lampin (1)","submitted_at":"2026-05-27T15:26:16Z","abstract_excerpt":"Parity functions are fundamental Boolean operations with critical applications across machine learning, cryptography, and error correction. Yet, learning high-dimensional parity functions poses significant challenges: in a general setting, standard neural network architectures typically require exponential sample complexity, making gradient-based optimization intractable for large number of inputs $N$. We demonstrate that compact product-based neural architectures combined with stochastic data sparsity (Bernoulli inputs with $p_e \\leq 1/N$) and appropriate hyperparameter choice enable efficien"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28612","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/2605.28612/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":"2605.28612","created_at":"2026-05-28T02:04:57.771668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28612v1","created_at":"2026-05-28T02:04:57.771668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28612","created_at":"2026-05-28T02:04:57.771668+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4ELULO7PN27","created_at":"2026-05-28T02:04:57.771668+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4ELULO7PN27R7AT","created_at":"2026-05-28T02:04:57.771668+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4ELULO7","created_at":"2026-05-28T02:04:57.771668+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/D4ELULO7PN27R7ATJL5LXPPLVP","json":"https://pith.science/pith/D4ELULO7PN27R7ATJL5LXPPLVP.json","graph_json":"https://pith.science/api/pith-number/D4ELULO7PN27R7ATJL5LXPPLVP/graph.json","events_json":"https://pith.science/api/pith-number/D4ELULO7PN27R7ATJL5LXPPLVP/events.json","paper":"https://pith.science/paper/D4ELULO7"},"agent_actions":{"view_html":"https://pith.science/pith/D4ELULO7PN27R7ATJL5LXPPLVP","download_json":"https://pith.science/pith/D4ELULO7PN27R7ATJL5LXPPLVP.json","view_paper":"https://pith.science/paper/D4ELULO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28612&json=true","fetch_graph":"https://pith.science/api/pith-number/D4ELULO7PN27R7ATJL5LXPPLVP/graph.json","fetch_events":"https://pith.science/api/pith-number/D4ELULO7PN27R7ATJL5LXPPLVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4ELULO7PN27R7ATJL5LXPPLVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4ELULO7PN27R7ATJL5LXPPLVP/action/storage_attestation","attest_author":"https://pith.science/pith/D4ELULO7PN27R7ATJL5LXPPLVP/action/author_attestation","sign_citation":"https://pith.science/pith/D4ELULO7PN27R7ATJL5LXPPLVP/action/citation_signature","submit_replication":"https://pith.science/pith/D4ELULO7PN27R7ATJL5LXPPLVP/action/replication_record"}},"created_at":"2026-05-28T02:04:57.771668+00:00","updated_at":"2026-05-28T02:04:57.771668+00:00"}