{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:56STNILHMD5HPPSV76Z5NUJSWM","short_pith_number":"pith:56STNILH","canonical_record":{"source":{"id":"2205.14189","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-05-27T18:35:48Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"3775b04e4d461e170f2f4ff4ffbe8f12ea37bfc0de60a1482fe3ab59bbd140b4","abstract_canon_sha256":"36d3c399201d42c75e0f8783344128c1611f46b047aa456e1c17ae91a0c1a4a7"},"schema_version":"1.0"},"canonical_sha256":"efa536a16760fa77be55ffb3d6d132b3019645877c39100b8c041e39d35d7705","source":{"kind":"arxiv","id":"2205.14189","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14189","created_at":"2026-07-05T04:29:13Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14189v2","created_at":"2026-07-05T04:29:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14189","created_at":"2026-07-05T04:29:13Z"},{"alias_kind":"pith_short_12","alias_value":"56STNILHMD5H","created_at":"2026-07-05T04:29:13Z"},{"alias_kind":"pith_short_16","alias_value":"56STNILHMD5HPPSV","created_at":"2026-07-05T04:29:13Z"},{"alias_kind":"pith_short_8","alias_value":"56STNILH","created_at":"2026-07-05T04:29:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:56STNILHMD5HPPSV76Z5NUJSWM","target":"record","payload":{"canonical_record":{"source":{"id":"2205.14189","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-05-27T18:35:48Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"3775b04e4d461e170f2f4ff4ffbe8f12ea37bfc0de60a1482fe3ab59bbd140b4","abstract_canon_sha256":"36d3c399201d42c75e0f8783344128c1611f46b047aa456e1c17ae91a0c1a4a7"},"schema_version":"1.0"},"canonical_sha256":"efa536a16760fa77be55ffb3d6d132b3019645877c39100b8c041e39d35d7705","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:13.950334Z","signature_b64":"meUprh1csgWZRM2lJQY+zdmkKGzqnaSdORzR7wVq216h+xddbBW2regjwtYSVtu0JHaPlAg7/R6w87MGxG9kAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efa536a16760fa77be55ffb3d6d132b3019645877c39100b8c041e39d35d7705","last_reissued_at":"2026-07-05T04:29:13.949887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:13.949887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.14189","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":"2026-07-05T04:29:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lO2RG7cEecItTbisPFRkQ+5Xq6IDI02YzdeHTQDR9E1a87mJ6s2mHui/9wTCaiQ0/Qk01DFED4SH4alI9PgmCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:56:43.983274Z"},"content_sha256":"55e50d509004ca8d7a5f6ed13403af028beb79db0b04ebcd18677841e98f1efc","schema_version":"1.0","event_id":"sha256:55e50d509004ca8d7a5f6ed13403af028beb79db0b04ebcd18677841e98f1efc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:56STNILHMD5HPPSV76Z5NUJSWM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Objective Functions from Trained ReLU Neural Networks via Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Asterios Tsiourvas, Georgia Perakis","submitted_at":"2022-05-27T18:35:48Z","abstract_excerpt":"This paper introduces scalable, sampling-based algorithms that optimize trained neural networks with ReLU activations. We first propose an iterative algorithm that takes advantage of the piecewise linear structure of ReLU neural networks and reduces the initial mixed-integer optimization problem (MIP) into multiple easy-to-solve linear optimization problems (LPs) through sampling. Subsequently, we extend this approach by searching around the neighborhood of the LP solution computed at each iteration. This scheme allows us to devise a second, enhanced algorithm that reduces the initial MIP prob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14189","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/2205.14189/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":"2026-07-05T04:29:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p7z8PJTKAGImN/4I7FRKDAFWhnYwoT8hZaGNvMRF8P+9uJzz0byQopECANdBflFyDUSD3Imyd8OQN9c4FE0rCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:56:43.983656Z"},"content_sha256":"519936ad9a9a29253fd87f49f5fe3c5221271e89753470b8213d8ed685d05f38","schema_version":"1.0","event_id":"sha256:519936ad9a9a29253fd87f49f5fe3c5221271e89753470b8213d8ed685d05f38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/56STNILHMD5HPPSV76Z5NUJSWM/bundle.json","state_url":"https://pith.science/pith/56STNILHMD5HPPSV76Z5NUJSWM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/56STNILHMD5HPPSV76Z5NUJSWM/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":"2026-07-09T03:56:43Z","links":{"resolver":"https://pith.science/pith/56STNILHMD5HPPSV76Z5NUJSWM","bundle":"https://pith.science/pith/56STNILHMD5HPPSV76Z5NUJSWM/bundle.json","state":"https://pith.science/pith/56STNILHMD5HPPSV76Z5NUJSWM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/56STNILHMD5HPPSV76Z5NUJSWM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:56STNILHMD5HPPSV76Z5NUJSWM","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":"36d3c399201d42c75e0f8783344128c1611f46b047aa456e1c17ae91a0c1a4a7","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-05-27T18:35:48Z","title_canon_sha256":"3775b04e4d461e170f2f4ff4ffbe8f12ea37bfc0de60a1482fe3ab59bbd140b4"},"schema_version":"1.0","source":{"id":"2205.14189","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14189","created_at":"2026-07-05T04:29:13Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14189v2","created_at":"2026-07-05T04:29:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14189","created_at":"2026-07-05T04:29:13Z"},{"alias_kind":"pith_short_12","alias_value":"56STNILHMD5H","created_at":"2026-07-05T04:29:13Z"},{"alias_kind":"pith_short_16","alias_value":"56STNILHMD5HPPSV","created_at":"2026-07-05T04:29:13Z"},{"alias_kind":"pith_short_8","alias_value":"56STNILH","created_at":"2026-07-05T04:29:13Z"}],"graph_snapshots":[{"event_id":"sha256:519936ad9a9a29253fd87f49f5fe3c5221271e89753470b8213d8ed685d05f38","target":"graph","created_at":"2026-07-05T04:29:13Z","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/2205.14189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces scalable, sampling-based algorithms that optimize trained neural networks with ReLU activations. We first propose an iterative algorithm that takes advantage of the piecewise linear structure of ReLU neural networks and reduces the initial mixed-integer optimization problem (MIP) into multiple easy-to-solve linear optimization problems (LPs) through sampling. Subsequently, we extend this approach by searching around the neighborhood of the LP solution computed at each iteration. This scheme allows us to devise a second, enhanced algorithm that reduces the initial MIP prob","authors_text":"Asterios Tsiourvas, Georgia Perakis","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-05-27T18:35:48Z","title":"Optimizing Objective Functions from Trained ReLU Neural Networks via Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14189","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":"sha256:55e50d509004ca8d7a5f6ed13403af028beb79db0b04ebcd18677841e98f1efc","target":"record","created_at":"2026-07-05T04:29:13Z","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":"36d3c399201d42c75e0f8783344128c1611f46b047aa456e1c17ae91a0c1a4a7","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-05-27T18:35:48Z","title_canon_sha256":"3775b04e4d461e170f2f4ff4ffbe8f12ea37bfc0de60a1482fe3ab59bbd140b4"},"schema_version":"1.0","source":{"id":"2205.14189","kind":"arxiv","version":2}},"canonical_sha256":"efa536a16760fa77be55ffb3d6d132b3019645877c39100b8c041e39d35d7705","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efa536a16760fa77be55ffb3d6d132b3019645877c39100b8c041e39d35d7705","first_computed_at":"2026-07-05T04:29:13.949887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:29:13.949887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"meUprh1csgWZRM2lJQY+zdmkKGzqnaSdORzR7wVq216h+xddbBW2regjwtYSVtu0JHaPlAg7/R6w87MGxG9kAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:29:13.950334Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.14189","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55e50d509004ca8d7a5f6ed13403af028beb79db0b04ebcd18677841e98f1efc","sha256:519936ad9a9a29253fd87f49f5fe3c5221271e89753470b8213d8ed685d05f38"],"state_sha256":"dc0fd5941d1735b867f0bd70c92a6d2d9b9153190231192f5b453521057bd7e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gBeCivwrOe0+RcthKQxs3O2Z9m3gx13139rCn3g95WWZMvvbCt1F/spZGqSQhvNSWIl3IixWQDRC99kkC4TVAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:56:43.985752Z","bundle_sha256":"6354ee5c13a959c4bcdd38fb43d0b6162616e4cfc8cd34f19045cc90292f63d7"}}