{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FDYNDTQFKSCSCDML2DZKKNIDKV","short_pith_number":"pith:FDYNDTQF","schema_version":"1.0","canonical_sha256":"28f0d1ce055485210d8bd0f2a535035552f9a1a5b4181d23d712fbcb10453839","source":{"kind":"arxiv","id":"2302.02261","version":3},"attestation_state":"computed","paper":{"title":"NeuRI: Diversifying DNN Generation via Inductive Rule Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Jiawei Liu, Jinjun Peng, Lingming Zhang, Yuyao Wang","submitted_at":"2023-02-04T23:42:07Z","abstract_excerpt":"Deep Learning (DL) is prevalently used in various industries to improve decision-making and automate processes, driven by the ever-evolving DL libraries and compilers. The correctness of DL systems is crucial for trust in DL applications. As such, the recent wave of research has been studying the automated synthesis of test-cases (i.e., DNN models and their inputs) for fuzzing DL systems. However, existing model generators only subsume a limited number of operators, lacking the ability to pervasively model operator constraints. To address this challenge, we propose NeuRI, a fully automated app"},"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":"2302.02261","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-02-04T23:42:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9f205984402d64041d26cd2b9358af0e8681d579ba08f3eea51a9a4543ce58d1","abstract_canon_sha256":"aed29c9538f8d22128b971a132e699332f2eb8e6d6f7d9aa84d240d3f7032b68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:17.743962Z","signature_b64":"PK6vZwNgGLa77P1sh5TAMsN3piUfgo2IXItCE7MoJY2J1AYBiM6u8UPF/TyBje/AZZXtO6mraMjvIqVCwklMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28f0d1ce055485210d8bd0f2a535035552f9a1a5b4181d23d712fbcb10453839","last_reissued_at":"2026-07-05T06:47:17.743438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:17.743438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeuRI: Diversifying DNN Generation via Inductive Rule Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Jiawei Liu, Jinjun Peng, Lingming Zhang, Yuyao Wang","submitted_at":"2023-02-04T23:42:07Z","abstract_excerpt":"Deep Learning (DL) is prevalently used in various industries to improve decision-making and automate processes, driven by the ever-evolving DL libraries and compilers. The correctness of DL systems is crucial for trust in DL applications. As such, the recent wave of research has been studying the automated synthesis of test-cases (i.e., DNN models and their inputs) for fuzzing DL systems. However, existing model generators only subsume a limited number of operators, lacking the ability to pervasively model operator constraints. To address this challenge, we propose NeuRI, a fully automated app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02261","kind":"arxiv","version":3},"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/2302.02261/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":"2302.02261","created_at":"2026-07-05T06:47:17.743503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.02261v3","created_at":"2026-07-05T06:47:17.743503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02261","created_at":"2026-07-05T06:47:17.743503+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDYNDTQFKSCS","created_at":"2026-07-05T06:47:17.743503+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDYNDTQFKSCSCDML","created_at":"2026-07-05T06:47:17.743503+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDYNDTQF","created_at":"2026-07-05T06:47:17.743503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08720","citing_title":"Demystifying the Silence of Correctness Bugs in PyTorch Compiler","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDYNDTQFKSCSCDML2DZKKNIDKV","json":"https://pith.science/pith/FDYNDTQFKSCSCDML2DZKKNIDKV.json","graph_json":"https://pith.science/api/pith-number/FDYNDTQFKSCSCDML2DZKKNIDKV/graph.json","events_json":"https://pith.science/api/pith-number/FDYNDTQFKSCSCDML2DZKKNIDKV/events.json","paper":"https://pith.science/paper/FDYNDTQF"},"agent_actions":{"view_html":"https://pith.science/pith/FDYNDTQFKSCSCDML2DZKKNIDKV","download_json":"https://pith.science/pith/FDYNDTQFKSCSCDML2DZKKNIDKV.json","view_paper":"https://pith.science/paper/FDYNDTQF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.02261&json=true","fetch_graph":"https://pith.science/api/pith-number/FDYNDTQFKSCSCDML2DZKKNIDKV/graph.json","fetch_events":"https://pith.science/api/pith-number/FDYNDTQFKSCSCDML2DZKKNIDKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDYNDTQFKSCSCDML2DZKKNIDKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDYNDTQFKSCSCDML2DZKKNIDKV/action/storage_attestation","attest_author":"https://pith.science/pith/FDYNDTQFKSCSCDML2DZKKNIDKV/action/author_attestation","sign_citation":"https://pith.science/pith/FDYNDTQFKSCSCDML2DZKKNIDKV/action/citation_signature","submit_replication":"https://pith.science/pith/FDYNDTQFKSCSCDML2DZKKNIDKV/action/replication_record"}},"created_at":"2026-07-05T06:47:17.743503+00:00","updated_at":"2026-07-05T06:47:17.743503+00:00"}