{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E663YUJQWJMVOP4GGTW6DGOB3W","short_pith_number":"pith:E663YUJQ","schema_version":"1.0","canonical_sha256":"27bdbc5130b259573f8634ede199c1dd90436ec6ce21485b9832df94c42258a9","source":{"kind":"arxiv","id":"2604.27011","version":2},"attestation_state":"computed","paper":{"title":"Automatic Causal Fairness Analysis with LLM-Generated Reporting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"FairMind automates fairness checks on training datasets by computing causal effects from counterfactual queries and using LLMs to generate the reports.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandro Antonucci, Alessia Berarducci, Eric Rossetto, Marco Zaffalon","submitted_at":"2026-04-29T10:31:38Z","abstract_excerpt":"AutoML, intended as the process of automating the application of machine learning to real-world problems, is a key step for AI popularisation. Most AutoML frameworks are not accounting for the potential lack of fairness in the training data and in the corresponding predictions. We introduce \\textsc{FairMind}, a software prototype aiming to automatise fairness analysis at the dataset level. We achieve that by resorting to the assumptions of the \\emph{standard fairness model}, recently proposed by Ple\\v{c}ko and Bareinboim. This allows for a sound fairness evaluation in terms of causal effects, "},"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":"2604.27011","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-29T10:31:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"580618c423561b01fedfa40f43f38f6888ddc8a2810fdb9ad2339a201c4f4ab8","abstract_canon_sha256":"f2c966fa227a61c87e2f720f54d63ad69a66319f1b287b8565b3de3c8ae1c0e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:05.950978Z","signature_b64":"sGsC3a+f6UtgxVepCG+qXhq+9bnH19sicwZOPe9/oQb5wt36wIwNj7BRRtVL1vrMeKvSwj5C8bT46a9KkYg+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27bdbc5130b259573f8634ede199c1dd90436ec6ce21485b9832df94c42258a9","last_reissued_at":"2026-06-08T01:04:05.950070Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:05.950070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Causal Fairness Analysis with LLM-Generated Reporting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"FairMind automates fairness checks on training datasets by computing causal effects from counterfactual queries and using LLMs to generate the reports.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandro Antonucci, Alessia Berarducci, Eric Rossetto, Marco Zaffalon","submitted_at":"2026-04-29T10:31:38Z","abstract_excerpt":"AutoML, intended as the process of automating the application of machine learning to real-world problems, is a key step for AI popularisation. Most AutoML frameworks are not accounting for the potential lack of fairness in the training data and in the corresponding predictions. We introduce \\textsc{FairMind}, a software prototype aiming to automatise fairness analysis at the dataset level. We achieve that by resorting to the assumptions of the \\emph{standard fairness model}, recently proposed by Ple\\v{c}ko and Bareinboim. This allows for a sound fairness evaluation in terms of causal effects, "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We introduce FairMind, a software prototype aiming to automatise fairness analysis at the dataset level. We achieve that by resorting to the assumptions of the standard fairness model... After the necessary data preprocessing, the tool implements a closed-form computation of the effects. LLMs are consequently exploited to generate accurate reports on the fairness levels detected in the training dataset. We achieve that in a zero-shot setup and show by examples the expected advantages with respect to a direct analysis performed by the LLM.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumptions of the standard fairness model proposed by Plečko and Bareinboim allow a sound fairness evaluation in terms of causal effects based on counterfactual queries, and that LLMs can generate accurate reports on fairness levels in a zero-shot setup without additional training or verification.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FairMind automates dataset-level causal fairness analysis with closed-form counterfactual computations and zero-shot LLM-generated reports, plus extensions for ordinal and continuous variables.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"FairMind automates fairness checks on training datasets by computing causal effects from counterfactual queries and using LLMs to generate the reports.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c86e21650ea4a768f0d8ac29fb9eef3329935e5de8a01919b6852f96a6dbc8e5"},"source":{"id":"2604.27011","kind":"arxiv","version":2},"verdict":{"id":"d5605db3-f328-47fb-8519-c4441a9631e1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T13:25:22.079045Z","strongest_claim":"We introduce FairMind, a software prototype aiming to automatise fairness analysis at the dataset level. We achieve that by resorting to the assumptions of the standard fairness model... After the necessary data preprocessing, the tool implements a closed-form computation of the effects. LLMs are consequently exploited to generate accurate reports on the fairness levels detected in the training dataset. We achieve that in a zero-shot setup and show by examples the expected advantages with respect to a direct analysis performed by the LLM.","one_line_summary":"FairMind automates dataset-level causal fairness analysis with closed-form counterfactual computations and zero-shot LLM-generated reports, plus extensions for ordinal and continuous variables.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumptions of the standard fairness model proposed by Plečko and Bareinboim allow a sound fairness evaluation in terms of causal effects based on counterfactual queries, and that LLMs can generate accurate reports on fairness levels in a zero-shot setup without additional training or verification.","pith_extraction_headline":"FairMind automates fairness checks on training datasets by computing causal effects from counterfactual queries and using LLMs to generate the reports."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.27011/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T00:33:53.796495Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T20:03:44.846473Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"27aaea288d890a4612e554a707f926817055250a55850b2473cba105ca110464"},"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":"2604.27011","created_at":"2026-06-08T01:04:05.950407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.27011v2","created_at":"2026-06-08T01:04:05.950407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27011","created_at":"2026-06-08T01:04:05.950407+00:00"},{"alias_kind":"pith_short_12","alias_value":"E663YUJQWJMV","created_at":"2026-06-08T01:04:05.950407+00:00"},{"alias_kind":"pith_short_16","alias_value":"E663YUJQWJMVOP4G","created_at":"2026-06-08T01:04:05.950407+00:00"},{"alias_kind":"pith_short_8","alias_value":"E663YUJQ","created_at":"2026-06-08T01:04:05.950407+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/E663YUJQWJMVOP4GGTW6DGOB3W","json":"https://pith.science/pith/E663YUJQWJMVOP4GGTW6DGOB3W.json","graph_json":"https://pith.science/api/pith-number/E663YUJQWJMVOP4GGTW6DGOB3W/graph.json","events_json":"https://pith.science/api/pith-number/E663YUJQWJMVOP4GGTW6DGOB3W/events.json","paper":"https://pith.science/paper/E663YUJQ"},"agent_actions":{"view_html":"https://pith.science/pith/E663YUJQWJMVOP4GGTW6DGOB3W","download_json":"https://pith.science/pith/E663YUJQWJMVOP4GGTW6DGOB3W.json","view_paper":"https://pith.science/paper/E663YUJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.27011&json=true","fetch_graph":"https://pith.science/api/pith-number/E663YUJQWJMVOP4GGTW6DGOB3W/graph.json","fetch_events":"https://pith.science/api/pith-number/E663YUJQWJMVOP4GGTW6DGOB3W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E663YUJQWJMVOP4GGTW6DGOB3W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E663YUJQWJMVOP4GGTW6DGOB3W/action/storage_attestation","attest_author":"https://pith.science/pith/E663YUJQWJMVOP4GGTW6DGOB3W/action/author_attestation","sign_citation":"https://pith.science/pith/E663YUJQWJMVOP4GGTW6DGOB3W/action/citation_signature","submit_replication":"https://pith.science/pith/E663YUJQWJMVOP4GGTW6DGOB3W/action/replication_record"}},"created_at":"2026-06-08T01:04:05.950407+00:00","updated_at":"2026-06-08T01:04:05.950407+00:00"}