{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7MR3O4GYMMUWKEDEQ4XUHCY77F","short_pith_number":"pith:7MR3O4GY","schema_version":"1.0","canonical_sha256":"fb23b770d86329651064872f438b1ff94afa2100cd2e302969e7577099bf79d8","source":{"kind":"arxiv","id":"2311.04015","version":1},"attestation_state":"computed","paper":{"title":"Expressivity of ReLU-Networks under Convex Relaxations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mark Niklas M\\\"uller, Martin Vechev, Maximilian Baader, Yuhao Mao","submitted_at":"2023-11-07T14:14:15Z","abstract_excerpt":"Convex relaxations are a key component of training and certifying provably safe neural networks. However, despite substantial progress, a wide and poorly understood accuracy gap to standard networks remains, raising the question of whether this is due to fundamental limitations of convex relaxations. Initial work investigating this question focused on the simple and widely used IBP relaxation. It revealed that some univariate, convex, continuous piecewise linear (CPWL) functions cannot be encoded by any ReLU network such that its IBP-analysis is precise. To explore whether this limitation is s"},"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":"2311.04015","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-07T14:14:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"065e9f85e2f1f2204e3b59211eb670c490713be5dd5ba97e0195c2c2c303d32d","abstract_canon_sha256":"40137d995705d59dc8fb4b5eb11fda7a6f538cce446f9ff14d8796918164955b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:09.740877Z","signature_b64":"lBhENZUUSLrvA8QGNRhNBD+G2jVgaC1VLwyVbuhXgR44kFvpMnF0Mkb5zApx6prZw55jgQlhz+IcdNJXO8DzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb23b770d86329651064872f438b1ff94afa2100cd2e302969e7577099bf79d8","last_reissued_at":"2026-07-05T07:10:09.740370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:09.740370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expressivity of ReLU-Networks under Convex Relaxations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mark Niklas M\\\"uller, Martin Vechev, Maximilian Baader, Yuhao Mao","submitted_at":"2023-11-07T14:14:15Z","abstract_excerpt":"Convex relaxations are a key component of training and certifying provably safe neural networks. However, despite substantial progress, a wide and poorly understood accuracy gap to standard networks remains, raising the question of whether this is due to fundamental limitations of convex relaxations. Initial work investigating this question focused on the simple and widely used IBP relaxation. It revealed that some univariate, convex, continuous piecewise linear (CPWL) functions cannot be encoded by any ReLU network such that its IBP-analysis is precise. To explore whether this limitation is s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04015","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/2311.04015/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":"2311.04015","created_at":"2026-07-05T07:10:09.740431+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.04015v1","created_at":"2026-07-05T07:10:09.740431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04015","created_at":"2026-07-05T07:10:09.740431+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MR3O4GYMMUW","created_at":"2026-07-05T07:10:09.740431+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MR3O4GYMMUWKEDE","created_at":"2026-07-05T07:10:09.740431+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MR3O4GY","created_at":"2026-07-05T07:10:09.740431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23587","citing_title":"It's Much Easier for Neural Networks to learn Game of Life Dynamics with the Right Activation Function: Polynomial Kolmogorov-Arnold Networks","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7MR3O4GYMMUWKEDEQ4XUHCY77F","json":"https://pith.science/pith/7MR3O4GYMMUWKEDEQ4XUHCY77F.json","graph_json":"https://pith.science/api/pith-number/7MR3O4GYMMUWKEDEQ4XUHCY77F/graph.json","events_json":"https://pith.science/api/pith-number/7MR3O4GYMMUWKEDEQ4XUHCY77F/events.json","paper":"https://pith.science/paper/7MR3O4GY"},"agent_actions":{"view_html":"https://pith.science/pith/7MR3O4GYMMUWKEDEQ4XUHCY77F","download_json":"https://pith.science/pith/7MR3O4GYMMUWKEDEQ4XUHCY77F.json","view_paper":"https://pith.science/paper/7MR3O4GY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.04015&json=true","fetch_graph":"https://pith.science/api/pith-number/7MR3O4GYMMUWKEDEQ4XUHCY77F/graph.json","fetch_events":"https://pith.science/api/pith-number/7MR3O4GYMMUWKEDEQ4XUHCY77F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MR3O4GYMMUWKEDEQ4XUHCY77F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MR3O4GYMMUWKEDEQ4XUHCY77F/action/storage_attestation","attest_author":"https://pith.science/pith/7MR3O4GYMMUWKEDEQ4XUHCY77F/action/author_attestation","sign_citation":"https://pith.science/pith/7MR3O4GYMMUWKEDEQ4XUHCY77F/action/citation_signature","submit_replication":"https://pith.science/pith/7MR3O4GYMMUWKEDEQ4XUHCY77F/action/replication_record"}},"created_at":"2026-07-05T07:10:09.740431+00:00","updated_at":"2026-07-05T07:10:09.740431+00:00"}