{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:I3K5EXLFJFQFM2LV4RG4SZCRB2","short_pith_number":"pith:I3K5EXLF","schema_version":"1.0","canonical_sha256":"46d5d25d654960566975e44dc964510ebe272e1b52f490c94d4396d4230ac9a2","source":{"kind":"arxiv","id":"2607.22511","version":1},"attestation_state":"computed","paper":{"title":"CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","econ.EM"],"primary_cat":"stat.ML","authors_text":"Jiyuan Tan, Vasilis Syrgkanis","submitted_at":"2026-07-24T17:32:35Z","abstract_excerpt":"Automating theoretical research is constrained not only by the generation of candidate results, but also by their reliable evaluation. A common approach is to close the research loop with a large language model (LLM) reviewer. However, such reviewers remain empirically unreliable: they may accept fabricated papers and detect them at rates close to chance (Bad Scientist, 2025). We present CausalForge, a framework for automated theoretical research in causal inference grounded in the Lean proof assistant. CausalForge combines Causalean, a foundational Lean library for causal inference containing"},"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":"2607.22511","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-07-24T17:32:35Z","cross_cats_sorted":["cs.AI","cs.LG","econ.EM"],"title_canon_sha256":"2faf2ff15119095d6b260e6f1312ea8c9bc1d92333a75d2ecb7d83e21b8f3eae","abstract_canon_sha256":"16f48884e326993d638fcd116e4036f9faeed7753f68924a73b34b26dacfc95e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:21:31.323417Z","signature_b64":"PFUT9kqs4epzlSTbvRw/73CGxKKU6TWPFWbE3t1RiRLQ4Dfw5KBtzE2teYsjk0jiDUgnAtoQ+LP9mo4hpJsrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46d5d25d654960566975e44dc964510ebe272e1b52f490c94d4396d4230ac9a2","last_reissued_at":"2026-07-27T01:21:31.322672Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:21:31.322672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","econ.EM"],"primary_cat":"stat.ML","authors_text":"Jiyuan Tan, Vasilis Syrgkanis","submitted_at":"2026-07-24T17:32:35Z","abstract_excerpt":"Automating theoretical research is constrained not only by the generation of candidate results, but also by their reliable evaluation. A common approach is to close the research loop with a large language model (LLM) reviewer. However, such reviewers remain empirically unreliable: they may accept fabricated papers and detect them at rates close to chance (Bad Scientist, 2025). We present CausalForge, a framework for automated theoretical research in causal inference grounded in the Lean proof assistant. CausalForge combines Causalean, a foundational Lean library for causal inference containing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22511","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/2607.22511/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":"2607.22511","created_at":"2026-07-27T01:21:31.323077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22511v1","created_at":"2026-07-27T01:21:31.323077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22511","created_at":"2026-07-27T01:21:31.323077+00:00"},{"alias_kind":"pith_short_12","alias_value":"I3K5EXLFJFQF","created_at":"2026-07-27T01:21:31.323077+00:00"},{"alias_kind":"pith_short_16","alias_value":"I3K5EXLFJFQFM2LV","created_at":"2026-07-27T01:21:31.323077+00:00"},{"alias_kind":"pith_short_8","alias_value":"I3K5EXLF","created_at":"2026-07-27T01:21:31.323077+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/I3K5EXLFJFQFM2LV4RG4SZCRB2","json":"https://pith.science/pith/I3K5EXLFJFQFM2LV4RG4SZCRB2.json","graph_json":"https://pith.science/api/pith-number/I3K5EXLFJFQFM2LV4RG4SZCRB2/graph.json","events_json":"https://pith.science/api/pith-number/I3K5EXLFJFQFM2LV4RG4SZCRB2/events.json","paper":"https://pith.science/paper/I3K5EXLF"},"agent_actions":{"view_html":"https://pith.science/pith/I3K5EXLFJFQFM2LV4RG4SZCRB2","download_json":"https://pith.science/pith/I3K5EXLFJFQFM2LV4RG4SZCRB2.json","view_paper":"https://pith.science/paper/I3K5EXLF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22511&json=true","fetch_graph":"https://pith.science/api/pith-number/I3K5EXLFJFQFM2LV4RG4SZCRB2/graph.json","fetch_events":"https://pith.science/api/pith-number/I3K5EXLFJFQFM2LV4RG4SZCRB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I3K5EXLFJFQFM2LV4RG4SZCRB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I3K5EXLFJFQFM2LV4RG4SZCRB2/action/storage_attestation","attest_author":"https://pith.science/pith/I3K5EXLFJFQFM2LV4RG4SZCRB2/action/author_attestation","sign_citation":"https://pith.science/pith/I3K5EXLFJFQFM2LV4RG4SZCRB2/action/citation_signature","submit_replication":"https://pith.science/pith/I3K5EXLFJFQFM2LV4RG4SZCRB2/action/replication_record"}},"created_at":"2026-07-27T01:21:31.323077+00:00","updated_at":"2026-07-27T01:21:31.323077+00:00"}