{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WY7DPA7QYNOEOIZCE7F47LS6HR","short_pith_number":"pith:WY7DPA7Q","schema_version":"1.0","canonical_sha256":"b63e3783f0c35c47232227cbcfae5e3c79f90fb3f5d863b09193af843744d816","source":{"kind":"arxiv","id":"2307.16851","version":1},"attestation_state":"computed","paper":{"title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haohan Wang, Haoyang Liu, Maheep Chaudhary","submitted_at":"2023-07-31T17:11:35Z","abstract_excerpt":"The trustworthiness of machine learning has emerged as a critical topic in the field, encompassing various applications and research areas such as robustness, security, interpretability, and fairness. The last decade saw the development of numerous methods addressing these challenges. In this survey, we systematically review these advancements from a data-centric perspective, highlighting the shortcomings of traditional empirical risk minimization (ERM) training in handling challenges posed by the data.\n  Interestingly, we observe a convergence of these methods, despite being developed indepen"},"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":"2307.16851","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-31T17:11:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ebbc5ea8b4dd59def1f811bc77726f6738680a90025e5df036b4eaa6dd619d2e","abstract_canon_sha256":"ff0a44921091fa9f5b09dc90098fceaad98169dfa7ff84cb031eea5300c3b92a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:08.929024Z","signature_b64":"Qv0JyfKbdPZDy9V+Xwgn2Xxgj25X2X66c/hvjEK6oU/8iDQ9n8LKEA5MNoWscCeQM0V1w9lpfDS9QI7Tr0uFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b63e3783f0c35c47232227cbcfae5e3c79f90fb3f5d863b09193af843744d816","last_reissued_at":"2026-07-05T06:36:08.928546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:08.928546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haohan Wang, Haoyang Liu, Maheep Chaudhary","submitted_at":"2023-07-31T17:11:35Z","abstract_excerpt":"The trustworthiness of machine learning has emerged as a critical topic in the field, encompassing various applications and research areas such as robustness, security, interpretability, and fairness. The last decade saw the development of numerous methods addressing these challenges. In this survey, we systematically review these advancements from a data-centric perspective, highlighting the shortcomings of traditional empirical risk minimization (ERM) training in handling challenges posed by the data.\n  Interestingly, we observe a convergence of these methods, despite being developed indepen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16851","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/2307.16851/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":"2307.16851","created_at":"2026-07-05T06:36:08.928600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.16851v1","created_at":"2026-07-05T06:36:08.928600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16851","created_at":"2026-07-05T06:36:08.928600+00:00"},{"alias_kind":"pith_short_12","alias_value":"WY7DPA7QYNOE","created_at":"2026-07-05T06:36:08.928600+00:00"},{"alias_kind":"pith_short_16","alias_value":"WY7DPA7QYNOEOIZC","created_at":"2026-07-05T06:36:08.928600+00:00"},{"alias_kind":"pith_short_8","alias_value":"WY7DPA7Q","created_at":"2026-07-05T06:36:08.928600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02640","citing_title":"Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WY7DPA7QYNOEOIZCE7F47LS6HR","json":"https://pith.science/pith/WY7DPA7QYNOEOIZCE7F47LS6HR.json","graph_json":"https://pith.science/api/pith-number/WY7DPA7QYNOEOIZCE7F47LS6HR/graph.json","events_json":"https://pith.science/api/pith-number/WY7DPA7QYNOEOIZCE7F47LS6HR/events.json","paper":"https://pith.science/paper/WY7DPA7Q"},"agent_actions":{"view_html":"https://pith.science/pith/WY7DPA7QYNOEOIZCE7F47LS6HR","download_json":"https://pith.science/pith/WY7DPA7QYNOEOIZCE7F47LS6HR.json","view_paper":"https://pith.science/paper/WY7DPA7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.16851&json=true","fetch_graph":"https://pith.science/api/pith-number/WY7DPA7QYNOEOIZCE7F47LS6HR/graph.json","fetch_events":"https://pith.science/api/pith-number/WY7DPA7QYNOEOIZCE7F47LS6HR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WY7DPA7QYNOEOIZCE7F47LS6HR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WY7DPA7QYNOEOIZCE7F47LS6HR/action/storage_attestation","attest_author":"https://pith.science/pith/WY7DPA7QYNOEOIZCE7F47LS6HR/action/author_attestation","sign_citation":"https://pith.science/pith/WY7DPA7QYNOEOIZCE7F47LS6HR/action/citation_signature","submit_replication":"https://pith.science/pith/WY7DPA7QYNOEOIZCE7F47LS6HR/action/replication_record"}},"created_at":"2026-07-05T06:36:08.928600+00:00","updated_at":"2026-07-05T06:36:08.928600+00:00"}