{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RMA5X627D2DFKSS32UFE4KKR24","short_pith_number":"pith:RMA5X627","schema_version":"1.0","canonical_sha256":"8b01dbfb5f1e86554a5bd50a4e2951d70ec45bedc0fdd3ccaccb4281dba37b93","source":{"kind":"arxiv","id":"2404.04662","version":4},"attestation_state":"computed","paper":{"title":"Learning Minimal Neural Specifications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.LG","authors_text":"Chuqin Geng, Haolin Ye, Xujie Si, Zhaoyue Wang","submitted_at":"2024-04-06T15:31:20Z","abstract_excerpt":"Formal verification is only as good as the specification of a system, which is also true for neural network verification. Existing specifications follow the paradigm of data as specification, where the local neighborhood around a reference data point is considered correct or robust. While these specifications provide a fair testbed for assessing model robustness, they are too restrictive for verifying any unseen test data points, a challenging task with significant real-world implications. Recent work shows great promise through a new paradigm, neural representation as specification, which use"},"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":"2404.04662","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-06T15:31:20Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"6ed68565ff523223c07e9d3c534e79a27b3fadf67331dfe77b3a415301a0cb82","abstract_canon_sha256":"004810fbb92c904376510c7fc4794f69b6fe0dff7151b35e26a2891929c8817d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:22.688383Z","signature_b64":"IYjRGMDCh+HtieCN7JweDY1CQZgJU//u3PCa5x7HTTuUQjE5KPDnDDZ6bbf5y3V3Wz5IOYY8z55gu8uc8CdVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b01dbfb5f1e86554a5bd50a4e2951d70ec45bedc0fdd3ccaccb4281dba37b93","last_reissued_at":"2026-07-05T10:31:22.687749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:22.687749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Minimal Neural Specifications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.LG","authors_text":"Chuqin Geng, Haolin Ye, Xujie Si, Zhaoyue Wang","submitted_at":"2024-04-06T15:31:20Z","abstract_excerpt":"Formal verification is only as good as the specification of a system, which is also true for neural network verification. Existing specifications follow the paradigm of data as specification, where the local neighborhood around a reference data point is considered correct or robust. While these specifications provide a fair testbed for assessing model robustness, they are too restrictive for verifying any unseen test data points, a challenging task with significant real-world implications. Recent work shows great promise through a new paradigm, neural representation as specification, which use"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04662","kind":"arxiv","version":4},"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/2404.04662/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":"2404.04662","created_at":"2026-07-05T10:31:22.687820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04662v4","created_at":"2026-07-05T10:31:22.687820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04662","created_at":"2026-07-05T10:31:22.687820+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMA5X627D2DF","created_at":"2026-07-05T10:31:22.687820+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMA5X627D2DFKSS3","created_at":"2026-07-05T10:31:22.687820+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMA5X627","created_at":"2026-07-05T10:31:22.687820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17475","citing_title":"Event-B Agent: Towards LLM Agent for Formal Model Synthesis and Repair","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RMA5X627D2DFKSS32UFE4KKR24","json":"https://pith.science/pith/RMA5X627D2DFKSS32UFE4KKR24.json","graph_json":"https://pith.science/api/pith-number/RMA5X627D2DFKSS32UFE4KKR24/graph.json","events_json":"https://pith.science/api/pith-number/RMA5X627D2DFKSS32UFE4KKR24/events.json","paper":"https://pith.science/paper/RMA5X627"},"agent_actions":{"view_html":"https://pith.science/pith/RMA5X627D2DFKSS32UFE4KKR24","download_json":"https://pith.science/pith/RMA5X627D2DFKSS32UFE4KKR24.json","view_paper":"https://pith.science/paper/RMA5X627","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04662&json=true","fetch_graph":"https://pith.science/api/pith-number/RMA5X627D2DFKSS32UFE4KKR24/graph.json","fetch_events":"https://pith.science/api/pith-number/RMA5X627D2DFKSS32UFE4KKR24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMA5X627D2DFKSS32UFE4KKR24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMA5X627D2DFKSS32UFE4KKR24/action/storage_attestation","attest_author":"https://pith.science/pith/RMA5X627D2DFKSS32UFE4KKR24/action/author_attestation","sign_citation":"https://pith.science/pith/RMA5X627D2DFKSS32UFE4KKR24/action/citation_signature","submit_replication":"https://pith.science/pith/RMA5X627D2DFKSS32UFE4KKR24/action/replication_record"}},"created_at":"2026-07-05T10:31:22.687820+00:00","updated_at":"2026-07-05T10:31:22.687820+00:00"}