{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IGCPYRLPGWEM6PYW3X7NGVIGKT","short_pith_number":"pith:IGCPYRLP","schema_version":"1.0","canonical_sha256":"4184fc456f3588cf3f16ddfed3550654eaf2deb7729978e65c43b3c540522c1e","source":{"kind":"arxiv","id":"2606.09957","version":1},"attestation_state":"computed","paper":{"title":"Data-aware Static Analysis: Improving Detection of Semantic Faults in Machine Learning Code Using Data Characteristics","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"D\\'aniel Varr\\'o, Kristian Sandahl, Willem Meijer","submitted_at":"2026-06-08T11:59:41Z","abstract_excerpt":"Semantic faults specific to the use of machine learning models are a common problem for machine learning developers, causing suboptimal predictions, high computational cost, or incorrect outputs. For example, one may erroneously use unscaled data to train a scale-sensitive model. Machine learning developers detect these faults after training their models and manually analyzing the results, making it an inefficient process. We propose a novel data-aware static analysis approach to detect semantic faults in machine learning code, allowing developers to reveal these bugs while writing code instea"},"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":"2606.09957","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-08T11:59:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8b3085bd06dcb3619b7d260023d0d3ad2132dc9bacf8a71f4eba70f877e41b98","abstract_canon_sha256":"7f3a253f3d468a5f9a34854324562c89dcaebae54c2a26a592e87bdd5a835980"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T00:08:34.808400Z","signature_b64":"A4RbqaEDoc55pM7mUnD2OfQo3Tf/814fv4W9+7HNX9xTOcjOzarLVoZZ4m7L1OA9HTxWNDT6cCzm+7u3OVyiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4184fc456f3588cf3f16ddfed3550654eaf2deb7729978e65c43b3c540522c1e","last_reissued_at":"2026-06-10T00:08:34.807525Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T00:08:34.807525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-aware Static Analysis: Improving Detection of Semantic Faults in Machine Learning Code Using Data Characteristics","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"D\\'aniel Varr\\'o, Kristian Sandahl, Willem Meijer","submitted_at":"2026-06-08T11:59:41Z","abstract_excerpt":"Semantic faults specific to the use of machine learning models are a common problem for machine learning developers, causing suboptimal predictions, high computational cost, or incorrect outputs. For example, one may erroneously use unscaled data to train a scale-sensitive model. Machine learning developers detect these faults after training their models and manually analyzing the results, making it an inefficient process. We propose a novel data-aware static analysis approach to detect semantic faults in machine learning code, allowing developers to reveal these bugs while writing code instea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09957","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/2606.09957/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":"2606.09957","created_at":"2026-06-10T00:08:34.807661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09957v1","created_at":"2026-06-10T00:08:34.807661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09957","created_at":"2026-06-10T00:08:34.807661+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGCPYRLPGWEM","created_at":"2026-06-10T00:08:34.807661+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGCPYRLPGWEM6PYW","created_at":"2026-06-10T00:08:34.807661+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGCPYRLP","created_at":"2026-06-10T00:08:34.807661+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/IGCPYRLPGWEM6PYW3X7NGVIGKT","json":"https://pith.science/pith/IGCPYRLPGWEM6PYW3X7NGVIGKT.json","graph_json":"https://pith.science/api/pith-number/IGCPYRLPGWEM6PYW3X7NGVIGKT/graph.json","events_json":"https://pith.science/api/pith-number/IGCPYRLPGWEM6PYW3X7NGVIGKT/events.json","paper":"https://pith.science/paper/IGCPYRLP"},"agent_actions":{"view_html":"https://pith.science/pith/IGCPYRLPGWEM6PYW3X7NGVIGKT","download_json":"https://pith.science/pith/IGCPYRLPGWEM6PYW3X7NGVIGKT.json","view_paper":"https://pith.science/paper/IGCPYRLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09957&json=true","fetch_graph":"https://pith.science/api/pith-number/IGCPYRLPGWEM6PYW3X7NGVIGKT/graph.json","fetch_events":"https://pith.science/api/pith-number/IGCPYRLPGWEM6PYW3X7NGVIGKT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGCPYRLPGWEM6PYW3X7NGVIGKT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGCPYRLPGWEM6PYW3X7NGVIGKT/action/storage_attestation","attest_author":"https://pith.science/pith/IGCPYRLPGWEM6PYW3X7NGVIGKT/action/author_attestation","sign_citation":"https://pith.science/pith/IGCPYRLPGWEM6PYW3X7NGVIGKT/action/citation_signature","submit_replication":"https://pith.science/pith/IGCPYRLPGWEM6PYW3X7NGVIGKT/action/replication_record"}},"created_at":"2026-06-10T00:08:34.807661+00:00","updated_at":"2026-06-10T00:08:34.807661+00:00"}