{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:L3TA26Y6ATPUXBRCJ2QQX6FTKG","short_pith_number":"pith:L3TA26Y6","schema_version":"1.0","canonical_sha256":"5ee60d7b1e04df4b86224ea10bf8b35191f8d0176a5536ef38c8069fcd3b1a8e","source":{"kind":"arxiv","id":"2103.00124","version":1},"attestation_state":"computed","paper":{"title":"NEUROSPF: A tool for the Symbolic Analysis of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Corina Pasareanu, Divya Gopinath, Muhammad Usman, Yannic Noller, Youcheng Sun","submitted_at":"2021-02-27T04:28:11Z","abstract_excerpt":"This paper presents NEUROSPF, a tool for the symbolic analysis of neural networks. Given a trained neural network model, the tool extracts the architecture and model parameters and translates them into a Java representation that is amenable for analysis using the Symbolic PathFinder symbolic execution tool. Notably, NEUROSPF encodes specialized peer classes for parsing the model's parameters, thereby enabling efficient analysis. With NEUROSPF the user has the flexibility to specify either the inputs or the network internal parameters as symbolic, promoting the application of program analysis a"},"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":"2103.00124","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T04:28:11Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"6ed68b3f15584183dd0b2b8ed85505f5cc454ce2d239838bdd6ac24d340ae732","abstract_canon_sha256":"70da4bb24685c05baa1e3a7a7ee6d228f8a5388bd7b1351a5931e2412f4fe3b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:19:02.615959Z","signature_b64":"7or8tW2QRNrGwZ/goPEecqB91iTm9QfPxHnSyBctkI/y1cD7j24dR1R6coi+qPP2oTgGIQDrb6yf8h9bH/kSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ee60d7b1e04df4b86224ea10bf8b35191f8d0176a5536ef38c8069fcd3b1a8e","last_reissued_at":"2026-07-05T02:19:02.615603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:19:02.615603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NEUROSPF: A tool for the Symbolic Analysis of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Corina Pasareanu, Divya Gopinath, Muhammad Usman, Yannic Noller, Youcheng Sun","submitted_at":"2021-02-27T04:28:11Z","abstract_excerpt":"This paper presents NEUROSPF, a tool for the symbolic analysis of neural networks. Given a trained neural network model, the tool extracts the architecture and model parameters and translates them into a Java representation that is amenable for analysis using the Symbolic PathFinder symbolic execution tool. Notably, NEUROSPF encodes specialized peer classes for parsing the model's parameters, thereby enabling efficient analysis. With NEUROSPF the user has the flexibility to specify either the inputs or the network internal parameters as symbolic, promoting the application of program analysis a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00124","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/2103.00124/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":"2103.00124","created_at":"2026-07-05T02:19:02.615665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.00124v1","created_at":"2026-07-05T02:19:02.615665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00124","created_at":"2026-07-05T02:19:02.615665+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3TA26Y6ATPU","created_at":"2026-07-05T02:19:02.615665+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3TA26Y6ATPUXBRC","created_at":"2026-07-05T02:19:02.615665+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3TA26Y6","created_at":"2026-07-05T02:19:02.615665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L3TA26Y6ATPUXBRCJ2QQX6FTKG","json":"https://pith.science/pith/L3TA26Y6ATPUXBRCJ2QQX6FTKG.json","graph_json":"https://pith.science/api/pith-number/L3TA26Y6ATPUXBRCJ2QQX6FTKG/graph.json","events_json":"https://pith.science/api/pith-number/L3TA26Y6ATPUXBRCJ2QQX6FTKG/events.json","paper":"https://pith.science/paper/L3TA26Y6"},"agent_actions":{"view_html":"https://pith.science/pith/L3TA26Y6ATPUXBRCJ2QQX6FTKG","download_json":"https://pith.science/pith/L3TA26Y6ATPUXBRCJ2QQX6FTKG.json","view_paper":"https://pith.science/paper/L3TA26Y6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.00124&json=true","fetch_graph":"https://pith.science/api/pith-number/L3TA26Y6ATPUXBRCJ2QQX6FTKG/graph.json","fetch_events":"https://pith.science/api/pith-number/L3TA26Y6ATPUXBRCJ2QQX6FTKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3TA26Y6ATPUXBRCJ2QQX6FTKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3TA26Y6ATPUXBRCJ2QQX6FTKG/action/storage_attestation","attest_author":"https://pith.science/pith/L3TA26Y6ATPUXBRCJ2QQX6FTKG/action/author_attestation","sign_citation":"https://pith.science/pith/L3TA26Y6ATPUXBRCJ2QQX6FTKG/action/citation_signature","submit_replication":"https://pith.science/pith/L3TA26Y6ATPUXBRCJ2QQX6FTKG/action/replication_record"}},"created_at":"2026-07-05T02:19:02.615665+00:00","updated_at":"2026-07-05T02:19:02.615665+00:00"}