{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OQDKP4VRK4SJ5V7ABRC7GUJ3MW","short_pith_number":"pith:OQDKP4VR","schema_version":"1.0","canonical_sha256":"7406a7f2b157249ed7e00c45f3513b658447f0bd4e9217f8af7860396dc072e0","source":{"kind":"arxiv","id":"2505.00555","version":1},"attestation_state":"computed","paper":{"title":"On the Mechanistic Interpretability of Neural Networks for Causality in Bio-statistics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"stat.AP","authors_text":"Jean-Baptiste A. Conan","submitted_at":"2025-05-01T14:30:34Z","abstract_excerpt":"Interpretable insights from predictive models remain critical in bio-statistics, particularly when assessing causality, where classical statistical and machine learning methods often provide inherent clarity. While Neural Networks (NNs) offer powerful capabilities for modeling complex biological data, their traditional \"black-box\" nature presents challenges for validation and trust in high-stakes health applications. Recent advances in Mechanistic Interpretability (MI) aim to decipher the internal computations learned by these networks. This work investigates the application of MI techniques t"},"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":"2505.00555","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2025-05-01T14:30:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"63b5425777f4bc7fb21bb42e98dc2be56df45f9ffbb17543b34af8cf35b598bc","abstract_canon_sha256":"5103ab12e9bb8edc56ffa6e5dca7890e11aa19b1b9ccb2f302411f77e9281637"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:22.048226Z","signature_b64":"xejVk3qF9m4xoKeeHHl63Xwfl40lunz0QBKZkJdGM6p1B8lOmb9cDQnPdnKgQ5HnqwU1yWV4niskqa5T/s99CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7406a7f2b157249ed7e00c45f3513b658447f0bd4e9217f8af7860396dc072e0","last_reissued_at":"2026-07-05T10:57:22.047727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:22.047727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Mechanistic Interpretability of Neural Networks for Causality in Bio-statistics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"stat.AP","authors_text":"Jean-Baptiste A. Conan","submitted_at":"2025-05-01T14:30:34Z","abstract_excerpt":"Interpretable insights from predictive models remain critical in bio-statistics, particularly when assessing causality, where classical statistical and machine learning methods often provide inherent clarity. While Neural Networks (NNs) offer powerful capabilities for modeling complex biological data, their traditional \"black-box\" nature presents challenges for validation and trust in high-stakes health applications. Recent advances in Mechanistic Interpretability (MI) aim to decipher the internal computations learned by these networks. This work investigates the application of MI techniques t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00555","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/2505.00555/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":"2505.00555","created_at":"2026-07-05T10:57:22.047788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00555v1","created_at":"2026-07-05T10:57:22.047788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00555","created_at":"2026-07-05T10:57:22.047788+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQDKP4VRK4SJ","created_at":"2026-07-05T10:57:22.047788+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQDKP4VRK4SJ5V7A","created_at":"2026-07-05T10:57:22.047788+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQDKP4VR","created_at":"2026-07-05T10:57:22.047788+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/OQDKP4VRK4SJ5V7ABRC7GUJ3MW","json":"https://pith.science/pith/OQDKP4VRK4SJ5V7ABRC7GUJ3MW.json","graph_json":"https://pith.science/api/pith-number/OQDKP4VRK4SJ5V7ABRC7GUJ3MW/graph.json","events_json":"https://pith.science/api/pith-number/OQDKP4VRK4SJ5V7ABRC7GUJ3MW/events.json","paper":"https://pith.science/paper/OQDKP4VR"},"agent_actions":{"view_html":"https://pith.science/pith/OQDKP4VRK4SJ5V7ABRC7GUJ3MW","download_json":"https://pith.science/pith/OQDKP4VRK4SJ5V7ABRC7GUJ3MW.json","view_paper":"https://pith.science/paper/OQDKP4VR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00555&json=true","fetch_graph":"https://pith.science/api/pith-number/OQDKP4VRK4SJ5V7ABRC7GUJ3MW/graph.json","fetch_events":"https://pith.science/api/pith-number/OQDKP4VRK4SJ5V7ABRC7GUJ3MW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQDKP4VRK4SJ5V7ABRC7GUJ3MW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQDKP4VRK4SJ5V7ABRC7GUJ3MW/action/storage_attestation","attest_author":"https://pith.science/pith/OQDKP4VRK4SJ5V7ABRC7GUJ3MW/action/author_attestation","sign_citation":"https://pith.science/pith/OQDKP4VRK4SJ5V7ABRC7GUJ3MW/action/citation_signature","submit_replication":"https://pith.science/pith/OQDKP4VRK4SJ5V7ABRC7GUJ3MW/action/replication_record"}},"created_at":"2026-07-05T10:57:22.047788+00:00","updated_at":"2026-07-05T10:57:22.047788+00:00"}