{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OCOY53PCM4BJUS3GBIKST4JJ6L","short_pith_number":"pith:OCOY53PC","schema_version":"1.0","canonical_sha256":"709d8eede267029a4b660a1529f129f2f11c3109728f55a315e17fc4842fa6b0","source":{"kind":"arxiv","id":"2503.03158","version":1},"attestation_state":"computed","paper":{"title":"A Systematic Survey on Debugging Techniques for Machine Learning Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Bach Le, Haoye Tian, Patanamon Thongtanunam, Shane McIntosh, Thanh-Dat Nguyen","submitted_at":"2025-03-05T03:57:20Z","abstract_excerpt":"Debugging ML software (i.e., the detection, localization and fixing of faults) poses unique challenges compared to traditional software largely due to the probabilistic nature and heterogeneity of its development process. Various methods have been proposed for testing, diagnosing, and repairing ML systems. However, the big picture informing important research directions that really address the dire needs of developers is yet to unfold, leaving several key questions unaddressed: (1) What faults have been targeted in the ML debugging research that fulfill developers needs in practice? (2) How ar"},"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":"2503.03158","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-05T03:57:20Z","cross_cats_sorted":[],"title_canon_sha256":"21b97d98de150f02722fc94ba7fb3d84912f0f39c129cf2ee2c2b167f081b76d","abstract_canon_sha256":"bf21cca4f00459f390814fa061f098b15def3e4d97e5880f5dab5401c1e31b50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:40.254501Z","signature_b64":"Eku6nDGG4BDqhiMbQCksXBzCLiaMuIWPobOJ7T8sXrvbSLpdyIP90AC6/Oo1uxzFx+KUJkdPvVRFK0KA4JeXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"709d8eede267029a4b660a1529f129f2f11c3109728f55a315e17fc4842fa6b0","last_reissued_at":"2026-07-05T10:24:40.254016Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:40.254016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Systematic Survey on Debugging Techniques for Machine Learning Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Bach Le, Haoye Tian, Patanamon Thongtanunam, Shane McIntosh, Thanh-Dat Nguyen","submitted_at":"2025-03-05T03:57:20Z","abstract_excerpt":"Debugging ML software (i.e., the detection, localization and fixing of faults) poses unique challenges compared to traditional software largely due to the probabilistic nature and heterogeneity of its development process. Various methods have been proposed for testing, diagnosing, and repairing ML systems. However, the big picture informing important research directions that really address the dire needs of developers is yet to unfold, leaving several key questions unaddressed: (1) What faults have been targeted in the ML debugging research that fulfill developers needs in practice? (2) How ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03158","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/2503.03158/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":"2503.03158","created_at":"2026-07-05T10:24:40.254085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03158v1","created_at":"2026-07-05T10:24:40.254085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03158","created_at":"2026-07-05T10:24:40.254085+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCOY53PCM4BJ","created_at":"2026-07-05T10:24:40.254085+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCOY53PCM4BJUS3G","created_at":"2026-07-05T10:24:40.254085+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCOY53PC","created_at":"2026-07-05T10:24:40.254085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04478","citing_title":"CCL-D: A High-Precision Diagnostic System for Slow and Hang Anomalies in Large-Scale Model Training","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OCOY53PCM4BJUS3GBIKST4JJ6L","json":"https://pith.science/pith/OCOY53PCM4BJUS3GBIKST4JJ6L.json","graph_json":"https://pith.science/api/pith-number/OCOY53PCM4BJUS3GBIKST4JJ6L/graph.json","events_json":"https://pith.science/api/pith-number/OCOY53PCM4BJUS3GBIKST4JJ6L/events.json","paper":"https://pith.science/paper/OCOY53PC"},"agent_actions":{"view_html":"https://pith.science/pith/OCOY53PCM4BJUS3GBIKST4JJ6L","download_json":"https://pith.science/pith/OCOY53PCM4BJUS3GBIKST4JJ6L.json","view_paper":"https://pith.science/paper/OCOY53PC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03158&json=true","fetch_graph":"https://pith.science/api/pith-number/OCOY53PCM4BJUS3GBIKST4JJ6L/graph.json","fetch_events":"https://pith.science/api/pith-number/OCOY53PCM4BJUS3GBIKST4JJ6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCOY53PCM4BJUS3GBIKST4JJ6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCOY53PCM4BJUS3GBIKST4JJ6L/action/storage_attestation","attest_author":"https://pith.science/pith/OCOY53PCM4BJUS3GBIKST4JJ6L/action/author_attestation","sign_citation":"https://pith.science/pith/OCOY53PCM4BJUS3GBIKST4JJ6L/action/citation_signature","submit_replication":"https://pith.science/pith/OCOY53PCM4BJUS3GBIKST4JJ6L/action/replication_record"}},"created_at":"2026-07-05T10:24:40.254085+00:00","updated_at":"2026-07-05T10:24:40.254085+00:00"}