{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XTIA2GLUMJ6QIUZJGPS3RVRWKJ","short_pith_number":"pith:XTIA2GLU","canonical_record":{"source":{"id":"2201.00723","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-03T15:53:51Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"0b406a0d6bf32d9ccf9d76a7037da7d48f9567ef94008cbbc7ba34a1eec91b18","abstract_canon_sha256":"44a464d9f69928735fb8fc88803149e4fbeef7848791f1aa034526314313a23a"},"schema_version":"1.0"},"canonical_sha256":"bcd00d1974627d04532933e5b8d6365255f84b5d019bf1f7be083ef68b9f31e4","source":{"kind":"arxiv","id":"2201.00723","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.00723","created_at":"2026-07-05T04:34:27Z"},{"alias_kind":"arxiv_version","alias_value":"2201.00723v2","created_at":"2026-07-05T04:34:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.00723","created_at":"2026-07-05T04:34:27Z"},{"alias_kind":"pith_short_12","alias_value":"XTIA2GLUMJ6Q","created_at":"2026-07-05T04:34:27Z"},{"alias_kind":"pith_short_16","alias_value":"XTIA2GLUMJ6QIUZJ","created_at":"2026-07-05T04:34:27Z"},{"alias_kind":"pith_short_8","alias_value":"XTIA2GLU","created_at":"2026-07-05T04:34:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XTIA2GLUMJ6QIUZJGPS3RVRWKJ","target":"record","payload":{"canonical_record":{"source":{"id":"2201.00723","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-03T15:53:51Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"0b406a0d6bf32d9ccf9d76a7037da7d48f9567ef94008cbbc7ba34a1eec91b18","abstract_canon_sha256":"44a464d9f69928735fb8fc88803149e4fbeef7848791f1aa034526314313a23a"},"schema_version":"1.0"},"canonical_sha256":"bcd00d1974627d04532933e5b8d6365255f84b5d019bf1f7be083ef68b9f31e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:27.503161Z","signature_b64":"12s8QmI6bN5wY7dU7GCEEB0zvaXF1/ig2jf59xKNsjIdwai92uBftDrZeYGs1qvtcn8GrauFejgvnEhZOD3bAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcd00d1974627d04532933e5b8d6365255f84b5d019bf1f7be083ef68b9f31e4","last_reissued_at":"2026-07-05T04:34:27.502696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:27.502696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.00723","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:34:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"REREB5P3EZAVSFF5V62gxoIOGucWZB6+JlBUdro1mXUvnlCGFbgrjtMqo4KaHwlz6Ass10VytHi3B/N3yvTGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T20:42:30.130752Z"},"content_sha256":"44e116f2c5c77ffe73c28b14b637be69c4eb5a29451448574dddb70e13153bea","schema_version":"1.0","event_id":"sha256:44e116f2c5c77ffe73c28b14b637be69c4eb5a29451448574dddb70e13153bea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XTIA2GLUMJ6QIUZJGPS3RVRWKJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Mixed-Integer Programming Approach to Training Dense Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Vrishabh Patil, Yonatan Mintz","submitted_at":"2022-01-03T15:53:51Z","abstract_excerpt":"Artificial Neural Networks (ANNs) are prevalent machine learning models that are applied across various real-world classification tasks. However, training ANNs is time-consuming and the resulting models take a lot of memory to deploy. In order to train more parsimonious ANNs, we propose a novel mixed-integer programming (MIP) formulation for training fully-connected ANNs. Our formulations can account for both binary and rectified linear unit (ReLU) activations, and for the use of a log-likelihood loss. We present numerical experiments comparing our MIP-based methods against existing approaches"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.00723","kind":"arxiv","version":2},"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/2201.00723/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:34:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PeHsXIdaIlwEO43rk3I8XkircjdmqkRxRjSLljZv+q6U8WWiQXYeK1IHL/SgDa3+HBG9dqQNGl6hFQIbSiNjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T20:42:30.131293Z"},"content_sha256":"445b80c03bdf7295807b40c7cab75910d77fe0db8e30d4e207616e920ac41935","schema_version":"1.0","event_id":"sha256:445b80c03bdf7295807b40c7cab75910d77fe0db8e30d4e207616e920ac41935"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XTIA2GLUMJ6QIUZJGPS3RVRWKJ/bundle.json","state_url":"https://pith.science/pith/XTIA2GLUMJ6QIUZJGPS3RVRWKJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XTIA2GLUMJ6QIUZJGPS3RVRWKJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-22T20:42:30Z","links":{"resolver":"https://pith.science/pith/XTIA2GLUMJ6QIUZJGPS3RVRWKJ","bundle":"https://pith.science/pith/XTIA2GLUMJ6QIUZJGPS3RVRWKJ/bundle.json","state":"https://pith.science/pith/XTIA2GLUMJ6QIUZJGPS3RVRWKJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XTIA2GLUMJ6QIUZJGPS3RVRWKJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XTIA2GLUMJ6QIUZJGPS3RVRWKJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"44a464d9f69928735fb8fc88803149e4fbeef7848791f1aa034526314313a23a","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-03T15:53:51Z","title_canon_sha256":"0b406a0d6bf32d9ccf9d76a7037da7d48f9567ef94008cbbc7ba34a1eec91b18"},"schema_version":"1.0","source":{"id":"2201.00723","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.00723","created_at":"2026-07-05T04:34:27Z"},{"alias_kind":"arxiv_version","alias_value":"2201.00723v2","created_at":"2026-07-05T04:34:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.00723","created_at":"2026-07-05T04:34:27Z"},{"alias_kind":"pith_short_12","alias_value":"XTIA2GLUMJ6Q","created_at":"2026-07-05T04:34:27Z"},{"alias_kind":"pith_short_16","alias_value":"XTIA2GLUMJ6QIUZJ","created_at":"2026-07-05T04:34:27Z"},{"alias_kind":"pith_short_8","alias_value":"XTIA2GLU","created_at":"2026-07-05T04:34:27Z"}],"graph_snapshots":[{"event_id":"sha256:445b80c03bdf7295807b40c7cab75910d77fe0db8e30d4e207616e920ac41935","target":"graph","created_at":"2026-07-05T04:34:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2201.00723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Artificial Neural Networks (ANNs) are prevalent machine learning models that are applied across various real-world classification tasks. However, training ANNs is time-consuming and the resulting models take a lot of memory to deploy. In order to train more parsimonious ANNs, we propose a novel mixed-integer programming (MIP) formulation for training fully-connected ANNs. Our formulations can account for both binary and rectified linear unit (ReLU) activations, and for the use of a log-likelihood loss. We present numerical experiments comparing our MIP-based methods against existing approaches","authors_text":"Vrishabh Patil, Yonatan Mintz","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-03T15:53:51Z","title":"A Mixed-Integer Programming Approach to Training Dense Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.00723","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:44e116f2c5c77ffe73c28b14b637be69c4eb5a29451448574dddb70e13153bea","target":"record","created_at":"2026-07-05T04:34:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"44a464d9f69928735fb8fc88803149e4fbeef7848791f1aa034526314313a23a","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-03T15:53:51Z","title_canon_sha256":"0b406a0d6bf32d9ccf9d76a7037da7d48f9567ef94008cbbc7ba34a1eec91b18"},"schema_version":"1.0","source":{"id":"2201.00723","kind":"arxiv","version":2}},"canonical_sha256":"bcd00d1974627d04532933e5b8d6365255f84b5d019bf1f7be083ef68b9f31e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcd00d1974627d04532933e5b8d6365255f84b5d019bf1f7be083ef68b9f31e4","first_computed_at":"2026-07-05T04:34:27.502696Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:34:27.502696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"12s8QmI6bN5wY7dU7GCEEB0zvaXF1/ig2jf59xKNsjIdwai92uBftDrZeYGs1qvtcn8GrauFejgvnEhZOD3bAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:34:27.503161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.00723","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44e116f2c5c77ffe73c28b14b637be69c4eb5a29451448574dddb70e13153bea","sha256:445b80c03bdf7295807b40c7cab75910d77fe0db8e30d4e207616e920ac41935"],"state_sha256":"2e526f91e6bc987963575a08051945c19bd11f51d96fbeb12ae2392ee89b04c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IEvMfRalAOd63yfZ2yQcXa144iKM6LKx1Cgqk7fKMdk/QY5Z8iBuDYrzF6rhKYqTTVuU5I4NsWuD7H2PE0buAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T20:42:30.136615Z","bundle_sha256":"e21ea1c3f13fb51a4dc9aad74a9a437d6f46d9df45569408c2e1b1226e7a307a"}}