{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V4DNA5K44ONUU6327YKHHXC67Y","short_pith_number":"pith:V4DNA5K4","schema_version":"1.0","canonical_sha256":"af06d0755ce39b4a7b7afe1473dc5efe3d16ab1e441f9bbdc43b58d6f9b8d107","source":{"kind":"arxiv","id":"2607.21173","version":1},"attestation_state":"computed","paper":{"title":"Automated Synthesis and Adversarial Validation of Executable Causal Research Pipelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dan Zeltzer, Irena Girshovitz, Ran Gilad-Bachrach","submitted_at":"2026-07-23T10:59:16Z","abstract_excerpt":"While automated research systems promise to accelerate empirical analysis, they are prone to silent failures: instances in which analysis code executes successfully yet relies on invalid causal assumptions. We present the Artificial Intelligence (AI)-based Epidemiology Research Assistant (ARA), a framework that makes these failures visible by explicitly encoding causal design principles, study-specific assumptions, and methodological constraints. ARA integrates protocol construction, synthetic data generation, and adversarial validation into a unified pipeline. The framework translates natural"},"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":"2607.21173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T10:59:16Z","cross_cats_sorted":[],"title_canon_sha256":"767afc52e72d21424df04d5c0a0e71fdfb07a0a68d609148779577e54db02556","abstract_canon_sha256":"65202d3a77090ba1ff8fe7ccdb81e0ea214a922efb233222556e669fedfc0882"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:24:17.286089Z","signature_b64":"Uo4BfVThXuS6Au8AdLypF/J5wn5oOMeac7tZSbZRlfB5w1OegaKWbkcWU5cQiziaaG92xUTQ7DM/Q0O5fT/3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af06d0755ce39b4a7b7afe1473dc5efe3d16ab1e441f9bbdc43b58d6f9b8d107","last_reissued_at":"2026-07-24T01:24:17.285050Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:24:17.285050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Synthesis and Adversarial Validation of Executable Causal Research Pipelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dan Zeltzer, Irena Girshovitz, Ran Gilad-Bachrach","submitted_at":"2026-07-23T10:59:16Z","abstract_excerpt":"While automated research systems promise to accelerate empirical analysis, they are prone to silent failures: instances in which analysis code executes successfully yet relies on invalid causal assumptions. We present the Artificial Intelligence (AI)-based Epidemiology Research Assistant (ARA), a framework that makes these failures visible by explicitly encoding causal design principles, study-specific assumptions, and methodological constraints. ARA integrates protocol construction, synthetic data generation, and adversarial validation into a unified pipeline. The framework translates natural"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21173","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/2607.21173/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":"2607.21173","created_at":"2026-07-24T01:24:17.285515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21173v1","created_at":"2026-07-24T01:24:17.285515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21173","created_at":"2026-07-24T01:24:17.285515+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4DNA5K44ONU","created_at":"2026-07-24T01:24:17.285515+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4DNA5K44ONUU632","created_at":"2026-07-24T01:24:17.285515+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4DNA5K4","created_at":"2026-07-24T01:24:17.285515+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/V4DNA5K44ONUU6327YKHHXC67Y","json":"https://pith.science/pith/V4DNA5K44ONUU6327YKHHXC67Y.json","graph_json":"https://pith.science/api/pith-number/V4DNA5K44ONUU6327YKHHXC67Y/graph.json","events_json":"https://pith.science/api/pith-number/V4DNA5K44ONUU6327YKHHXC67Y/events.json","paper":"https://pith.science/paper/V4DNA5K4"},"agent_actions":{"view_html":"https://pith.science/pith/V4DNA5K44ONUU6327YKHHXC67Y","download_json":"https://pith.science/pith/V4DNA5K44ONUU6327YKHHXC67Y.json","view_paper":"https://pith.science/paper/V4DNA5K4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21173&json=true","fetch_graph":"https://pith.science/api/pith-number/V4DNA5K44ONUU6327YKHHXC67Y/graph.json","fetch_events":"https://pith.science/api/pith-number/V4DNA5K44ONUU6327YKHHXC67Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4DNA5K44ONUU6327YKHHXC67Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4DNA5K44ONUU6327YKHHXC67Y/action/storage_attestation","attest_author":"https://pith.science/pith/V4DNA5K44ONUU6327YKHHXC67Y/action/author_attestation","sign_citation":"https://pith.science/pith/V4DNA5K44ONUU6327YKHHXC67Y/action/citation_signature","submit_replication":"https://pith.science/pith/V4DNA5K44ONUU6327YKHHXC67Y/action/replication_record"}},"created_at":"2026-07-24T01:24:17.285515+00:00","updated_at":"2026-07-24T01:24:17.285515+00:00"}