{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3IRT7TCSXLU5WRAMD7DFIYNS4U","short_pith_number":"pith:3IRT7TCS","schema_version":"1.0","canonical_sha256":"da233fcc52bae9db440c1fc65461b2e5001a80d67f50d19e8581a27828d87805","source":{"kind":"arxiv","id":"2410.06717","version":4},"attestation_state":"computed","paper":{"title":"Exact full-RSB SAT/UNSAT transition in infinitely wide two-layer neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"cond-mat.dis-nn","authors_text":"Brandon L. Annesi, Enrico M. Malatesta, Francesco Zamponi","submitted_at":"2024-10-09T09:41:28Z","abstract_excerpt":"We analyze the problem of storing random pattern-label associations using two classes of continuous non-convex weights models, namely the perceptron with negative margin and an infinite-width two-layer neural network with non-overlapping receptive fields and generic activation function. Using a full-RSB ansatz we compute the exact value of the SAT/UNSAT transition. Furthermore, in the case of the negative perceptron we show that the overlap distribution of typical states displays an overlap gap (a disconnected support) in certain regions of the phase diagram defined by the value of the margin "},"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":"2410.06717","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2024-10-09T09:41:28Z","cross_cats_sorted":["cs.LG","math.PR"],"title_canon_sha256":"9e3a9c1fe78c71ee48c96ad171322c6496c7340b2c12145a646304f9c2396458","abstract_canon_sha256":"c74f22656395cf05c42450c1af5491cf95dab105329e72592a7554c19dd06c27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:37.860993Z","signature_b64":"UGnGf80akxqfZb8NXs5ylSO+3eZgim5kU/hEqQ5k0boMk1jI0ort6PStwU/FtHLLmOGYw/WasfeTm972Uy+GAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da233fcc52bae9db440c1fc65461b2e5001a80d67f50d19e8581a27828d87805","last_reissued_at":"2026-07-05T10:42:37.860525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:37.860525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exact full-RSB SAT/UNSAT transition in infinitely wide two-layer neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"cond-mat.dis-nn","authors_text":"Brandon L. Annesi, Enrico M. Malatesta, Francesco Zamponi","submitted_at":"2024-10-09T09:41:28Z","abstract_excerpt":"We analyze the problem of storing random pattern-label associations using two classes of continuous non-convex weights models, namely the perceptron with negative margin and an infinite-width two-layer neural network with non-overlapping receptive fields and generic activation function. Using a full-RSB ansatz we compute the exact value of the SAT/UNSAT transition. Furthermore, in the case of the negative perceptron we show that the overlap distribution of typical states displays an overlap gap (a disconnected support) in certain regions of the phase diagram defined by the value of the margin "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06717","kind":"arxiv","version":4},"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/2410.06717/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":"2410.06717","created_at":"2026-07-05T10:42:37.860581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06717v4","created_at":"2026-07-05T10:42:37.860581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06717","created_at":"2026-07-05T10:42:37.860581+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IRT7TCSXLU5","created_at":"2026-07-05T10:42:37.860581+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IRT7TCSXLU5WRAM","created_at":"2026-07-05T10:42:37.860581+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IRT7TCS","created_at":"2026-07-05T10:42:37.860581+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19677","citing_title":"Deep ReLU networks -- injectivity capacity upper bounds","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3IRT7TCSXLU5WRAMD7DFIYNS4U","json":"https://pith.science/pith/3IRT7TCSXLU5WRAMD7DFIYNS4U.json","graph_json":"https://pith.science/api/pith-number/3IRT7TCSXLU5WRAMD7DFIYNS4U/graph.json","events_json":"https://pith.science/api/pith-number/3IRT7TCSXLU5WRAMD7DFIYNS4U/events.json","paper":"https://pith.science/paper/3IRT7TCS"},"agent_actions":{"view_html":"https://pith.science/pith/3IRT7TCSXLU5WRAMD7DFIYNS4U","download_json":"https://pith.science/pith/3IRT7TCSXLU5WRAMD7DFIYNS4U.json","view_paper":"https://pith.science/paper/3IRT7TCS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06717&json=true","fetch_graph":"https://pith.science/api/pith-number/3IRT7TCSXLU5WRAMD7DFIYNS4U/graph.json","fetch_events":"https://pith.science/api/pith-number/3IRT7TCSXLU5WRAMD7DFIYNS4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IRT7TCSXLU5WRAMD7DFIYNS4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IRT7TCSXLU5WRAMD7DFIYNS4U/action/storage_attestation","attest_author":"https://pith.science/pith/3IRT7TCSXLU5WRAMD7DFIYNS4U/action/author_attestation","sign_citation":"https://pith.science/pith/3IRT7TCSXLU5WRAMD7DFIYNS4U/action/citation_signature","submit_replication":"https://pith.science/pith/3IRT7TCSXLU5WRAMD7DFIYNS4U/action/replication_record"}},"created_at":"2026-07-05T10:42:37.860581+00:00","updated_at":"2026-07-05T10:42:37.860581+00:00"}