{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZMV3QECY7VERYFR2UDZELYAOCA","short_pith_number":"pith:ZMV3QECY","schema_version":"1.0","canonical_sha256":"cb2bb81058fd491c163aa0f245e00e1008bc38aef54db209e54a585b0163f883","source":{"kind":"arxiv","id":"1706.07351","version":1},"attestation_state":"computed","paper":{"title":"An approach to reachability analysis for feed-forward ReLU neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Alessio Lomuscio, Lalit Maganti","submitted_at":"2017-06-22T14:59:49Z","abstract_excerpt":"We study the reachability problem for systems implemented as feed-forward neural networks whose activation function is implemented via ReLU functions. We draw a correspondence between establishing whether some arbitrary output can ever be outputed by a neural system and linear problems characterising a neural system of interest. We present a methodology to solve cases of practical interest by means of a state-of-the-art linear programs solver. We evaluate the technique presented by discussing the experimental results obtained by analysing reachability properties for a number of benchmarks in t"},"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":"1706.07351","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-22T14:59:49Z","cross_cats_sorted":["cs.LG","cs.LO"],"title_canon_sha256":"f6aea7f547e424859919355f18579fcecc5b977c73dc160b2b5ddc26064e0342","abstract_canon_sha256":"9ea040109e71aaf694c2c795431704fa011ac3f464672fa866ad09b248ac06cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:51.920870Z","signature_b64":"q0vbwjlhkNhcNfqsuWDh71rnzmR2rWcvskuc+MqbkpHTeJ53BRxV2OzljqknWg4RFi+1U5QJP9awUaDZTpeNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb2bb81058fd491c163aa0f245e00e1008bc38aef54db209e54a585b0163f883","last_reissued_at":"2026-05-18T00:41:51.920422Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:51.920422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An approach to reachability analysis for feed-forward ReLU neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Alessio Lomuscio, Lalit Maganti","submitted_at":"2017-06-22T14:59:49Z","abstract_excerpt":"We study the reachability problem for systems implemented as feed-forward neural networks whose activation function is implemented via ReLU functions. We draw a correspondence between establishing whether some arbitrary output can ever be outputed by a neural system and linear problems characterising a neural system of interest. We present a methodology to solve cases of practical interest by means of a state-of-the-art linear programs solver. We evaluate the technique presented by discussing the experimental results obtained by analysing reachability properties for a number of benchmarks in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.07351","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":""},"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":"1706.07351","created_at":"2026-05-18T00:41:51.920491+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.07351v1","created_at":"2026-05-18T00:41:51.920491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.07351","created_at":"2026-05-18T00:41:51.920491+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZMV3QECY7VER","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZMV3QECY7VERYFR2","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZMV3QECY","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2512.00164","citing_title":"Faster Verified Explanations for Neural Networks","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2512.07750","citing_title":"A Performance Analyzer for a Public Cloud's ML-Augmented VM Allocator","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22746","citing_title":"Relaxation-Informed Training of Neural Network Surrogate Models","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZMV3QECY7VERYFR2UDZELYAOCA","json":"https://pith.science/pith/ZMV3QECY7VERYFR2UDZELYAOCA.json","graph_json":"https://pith.science/api/pith-number/ZMV3QECY7VERYFR2UDZELYAOCA/graph.json","events_json":"https://pith.science/api/pith-number/ZMV3QECY7VERYFR2UDZELYAOCA/events.json","paper":"https://pith.science/paper/ZMV3QECY"},"agent_actions":{"view_html":"https://pith.science/pith/ZMV3QECY7VERYFR2UDZELYAOCA","download_json":"https://pith.science/pith/ZMV3QECY7VERYFR2UDZELYAOCA.json","view_paper":"https://pith.science/paper/ZMV3QECY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.07351&json=true","fetch_graph":"https://pith.science/api/pith-number/ZMV3QECY7VERYFR2UDZELYAOCA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZMV3QECY7VERYFR2UDZELYAOCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZMV3QECY7VERYFR2UDZELYAOCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZMV3QECY7VERYFR2UDZELYAOCA/action/storage_attestation","attest_author":"https://pith.science/pith/ZMV3QECY7VERYFR2UDZELYAOCA/action/author_attestation","sign_citation":"https://pith.science/pith/ZMV3QECY7VERYFR2UDZELYAOCA/action/citation_signature","submit_replication":"https://pith.science/pith/ZMV3QECY7VERYFR2UDZELYAOCA/action/replication_record"}},"created_at":"2026-05-18T00:41:51.920491+00:00","updated_at":"2026-05-18T00:41:51.920491+00:00"}