{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WAVLMHJXBPMWKEY7PYJ5YSDEMC","short_pith_number":"pith:WAVLMHJX","schema_version":"1.0","canonical_sha256":"b02ab61d370bd965131f7e13dc486460802ffa1821df78834ba017b4e03c8bcd","source":{"kind":"arxiv","id":"2504.02606","version":1},"attestation_state":"computed","paper":{"title":"Improving Counterfactual Truthfulness for Molecular Property Prediction through Uncertainty Quantification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Annika Leinweber, Jonas Teufel, Pascal Friederich","submitted_at":"2025-04-03T14:07:30Z","abstract_excerpt":"Explainable AI (xAI) interventions aim to improve interpretability for complex black-box models, not only to improve user trust but also as a means to extract scientific insights from high-performing predictive systems. In molecular property prediction, counterfactual explanations offer a way to understand predictive behavior by highlighting which minimal perturbations in the input molecular structure cause the greatest deviation in the predicted property. However, such explanations only allow for meaningful scientific insights if they reflect the distribution of the true underlying property -"},"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":"2504.02606","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-03T14:07:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4b2e5b0515bf85cdd506cd765aa7fffa37469a22cf8ad2c4addebb723c6dc783","abstract_canon_sha256":"56ca212e7b53eaf3e1095e8dea2f221426573af8a398fcaf7ca3fc2a6c19c940"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:59.776814Z","signature_b64":"EXuJj7oNIM0brMUUVGk3MsJP8QaaFrTd1vTn2vyn3RgSfzKFbXdDPJ1z/nkLbxEIaL4rOshcvDTpB7ZyH2o8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b02ab61d370bd965131f7e13dc486460802ffa1821df78834ba017b4e03c8bcd","last_reissued_at":"2026-07-05T10:43:59.776388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:59.776388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Counterfactual Truthfulness for Molecular Property Prediction through Uncertainty Quantification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Annika Leinweber, Jonas Teufel, Pascal Friederich","submitted_at":"2025-04-03T14:07:30Z","abstract_excerpt":"Explainable AI (xAI) interventions aim to improve interpretability for complex black-box models, not only to improve user trust but also as a means to extract scientific insights from high-performing predictive systems. In molecular property prediction, counterfactual explanations offer a way to understand predictive behavior by highlighting which minimal perturbations in the input molecular structure cause the greatest deviation in the predicted property. However, such explanations only allow for meaningful scientific insights if they reflect the distribution of the true underlying property -"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02606","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/2504.02606/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":"2504.02606","created_at":"2026-07-05T10:43:59.776448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02606v1","created_at":"2026-07-05T10:43:59.776448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02606","created_at":"2026-07-05T10:43:59.776448+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAVLMHJXBPMW","created_at":"2026-07-05T10:43:59.776448+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAVLMHJXBPMWKEY7","created_at":"2026-07-05T10:43:59.776448+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAVLMHJX","created_at":"2026-07-05T10:43:59.776448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13824","citing_title":"Can Hallucinations Help? Boosting LLMs for Drug Discovery","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WAVLMHJXBPMWKEY7PYJ5YSDEMC","json":"https://pith.science/pith/WAVLMHJXBPMWKEY7PYJ5YSDEMC.json","graph_json":"https://pith.science/api/pith-number/WAVLMHJXBPMWKEY7PYJ5YSDEMC/graph.json","events_json":"https://pith.science/api/pith-number/WAVLMHJXBPMWKEY7PYJ5YSDEMC/events.json","paper":"https://pith.science/paper/WAVLMHJX"},"agent_actions":{"view_html":"https://pith.science/pith/WAVLMHJXBPMWKEY7PYJ5YSDEMC","download_json":"https://pith.science/pith/WAVLMHJXBPMWKEY7PYJ5YSDEMC.json","view_paper":"https://pith.science/paper/WAVLMHJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02606&json=true","fetch_graph":"https://pith.science/api/pith-number/WAVLMHJXBPMWKEY7PYJ5YSDEMC/graph.json","fetch_events":"https://pith.science/api/pith-number/WAVLMHJXBPMWKEY7PYJ5YSDEMC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAVLMHJXBPMWKEY7PYJ5YSDEMC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAVLMHJXBPMWKEY7PYJ5YSDEMC/action/storage_attestation","attest_author":"https://pith.science/pith/WAVLMHJXBPMWKEY7PYJ5YSDEMC/action/author_attestation","sign_citation":"https://pith.science/pith/WAVLMHJXBPMWKEY7PYJ5YSDEMC/action/citation_signature","submit_replication":"https://pith.science/pith/WAVLMHJXBPMWKEY7PYJ5YSDEMC/action/replication_record"}},"created_at":"2026-07-05T10:43:59.776448+00:00","updated_at":"2026-07-05T10:43:59.776448+00:00"}