{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6EYLTQM7OJUHA4ZDIXQMVUCPS3","short_pith_number":"pith:6EYLTQM7","schema_version":"1.0","canonical_sha256":"f130b9c19f726870732345e0cad04f96c9b3b5a8ddece79b9ce11f4742240f05","source":{"kind":"arxiv","id":"2402.06697","version":1},"attestation_state":"computed","paper":{"title":"Feed-Forward Neural Networks as a Mixed-Integer Program","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Fatemeh Mahroo, Navid Aftabi, Nima Moradi","submitted_at":"2024-02-09T02:23:37Z","abstract_excerpt":"Deep neural networks (DNNs) are widely studied in various applications. A DNN consists of layers of neurons that compute affine combinations, apply nonlinear operations, and produce corresponding activations. The rectified linear unit (ReLU) is a typical nonlinear operator, outputting the max of its input and zero. In scenarios like max pooling, where multiple input values are involved, a fixed-parameter DNN can be modeled as a mixed-integer program (MIP). This formulation, with continuous variables representing unit outputs and binary variables for ReLU activation, finds applications across d"},"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":"2402.06697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-09T02:23:37Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"139fa2c5ffb3c85da9a22a72b463fc28e1db3ef74220d96671f37ac3c1d068d4","abstract_canon_sha256":"3f2384a30493f1315f8c8f527b207c0821374079fd03fc8297d75992af32993f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:37.161539Z","signature_b64":"j1U0KG8mbo2JRB/CTGoREvFwjAf62NBJa0i4eFgtubjRw9tiOWGvmhXqkzr89oB6Ll1CgY3ok2fsc+kvYdqJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f130b9c19f726870732345e0cad04f96c9b3b5a8ddece79b9ce11f4742240f05","last_reissued_at":"2026-07-05T07:43:37.161093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:37.161093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feed-Forward Neural Networks as a Mixed-Integer Program","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Fatemeh Mahroo, Navid Aftabi, Nima Moradi","submitted_at":"2024-02-09T02:23:37Z","abstract_excerpt":"Deep neural networks (DNNs) are widely studied in various applications. A DNN consists of layers of neurons that compute affine combinations, apply nonlinear operations, and produce corresponding activations. The rectified linear unit (ReLU) is a typical nonlinear operator, outputting the max of its input and zero. In scenarios like max pooling, where multiple input values are involved, a fixed-parameter DNN can be modeled as a mixed-integer program (MIP). This formulation, with continuous variables representing unit outputs and binary variables for ReLU activation, finds applications across d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06697","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/2402.06697/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":"2402.06697","created_at":"2026-07-05T07:43:37.161151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.06697v1","created_at":"2026-07-05T07:43:37.161151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06697","created_at":"2026-07-05T07:43:37.161151+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EYLTQM7OJUH","created_at":"2026-07-05T07:43:37.161151+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EYLTQM7OJUHA4ZD","created_at":"2026-07-05T07:43:37.161151+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EYLTQM7","created_at":"2026-07-05T07:43:37.161151+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22249","citing_title":"On the Expressive Power of Weight Quantization in Large Language Models","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6EYLTQM7OJUHA4ZDIXQMVUCPS3","json":"https://pith.science/pith/6EYLTQM7OJUHA4ZDIXQMVUCPS3.json","graph_json":"https://pith.science/api/pith-number/6EYLTQM7OJUHA4ZDIXQMVUCPS3/graph.json","events_json":"https://pith.science/api/pith-number/6EYLTQM7OJUHA4ZDIXQMVUCPS3/events.json","paper":"https://pith.science/paper/6EYLTQM7"},"agent_actions":{"view_html":"https://pith.science/pith/6EYLTQM7OJUHA4ZDIXQMVUCPS3","download_json":"https://pith.science/pith/6EYLTQM7OJUHA4ZDIXQMVUCPS3.json","view_paper":"https://pith.science/paper/6EYLTQM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.06697&json=true","fetch_graph":"https://pith.science/api/pith-number/6EYLTQM7OJUHA4ZDIXQMVUCPS3/graph.json","fetch_events":"https://pith.science/api/pith-number/6EYLTQM7OJUHA4ZDIXQMVUCPS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EYLTQM7OJUHA4ZDIXQMVUCPS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EYLTQM7OJUHA4ZDIXQMVUCPS3/action/storage_attestation","attest_author":"https://pith.science/pith/6EYLTQM7OJUHA4ZDIXQMVUCPS3/action/author_attestation","sign_citation":"https://pith.science/pith/6EYLTQM7OJUHA4ZDIXQMVUCPS3/action/citation_signature","submit_replication":"https://pith.science/pith/6EYLTQM7OJUHA4ZDIXQMVUCPS3/action/replication_record"}},"created_at":"2026-07-05T07:43:37.161151+00:00","updated_at":"2026-07-05T07:43:37.161151+00:00"}