{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZK5WAHH5KVSSLDH3BODHSH42F7","short_pith_number":"pith:ZK5WAHH5","schema_version":"1.0","canonical_sha256":"cabb601cfd5565258cfb0b86791f9a2fedbbc7f40c89b3a799fdf74e4e1b65a5","source":{"kind":"arxiv","id":"2605.26029","version":1},"attestation_state":"computed","paper":{"title":"CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Aniket Vashishtha, Chenhao Tan, Dylan Zhang, Hao Peng, Jing Shi, Junlin Yang, Qirun Dai, Xiangchen Song, Xiao Liu, Yuen Chen","submitted_at":"2026-05-25T16:57:06Z","abstract_excerpt":"We introduce CausaLab, a scalable environment for evaluating interactive causal discovery by LLM agents. Unlike prior evaluations, CausaLab evaluates both whether an agent can solve a problem using causal evidence and whether its answer is supported by a correct hypothesis about the underlying causal mechanism. Each episode places an agent in a synthetic laboratory: it receives prior measurement records, intervenes on a manipulator crystal, and predicts the resonance frequency of a held-out reactor crystal governed by the same mechanism. The hidden data-generating process is a randomly sampled"},"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":"2605.26029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-25T16:57:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c5b8c811b8912d6f1b078ec8bb55f01baba5726128fb7bd26a90800e5433d584","abstract_canon_sha256":"0c50125d774016bf1063c035c72f11d9516aa233fcf75349e3c1e182511ad80c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:24.127993Z","signature_b64":"pIZPazhUiR1ItkzK7hQkUM0HQVIx9BdGhSBP9s6htyTeXX7iZiOCUol7vPk2xQQ4jzDDjZz7JL6DXoWFsTkHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cabb601cfd5565258cfb0b86791f9a2fedbbc7f40c89b3a799fdf74e4e1b65a5","last_reissued_at":"2026-05-26T02:05:24.127361Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:24.127361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Aniket Vashishtha, Chenhao Tan, Dylan Zhang, Hao Peng, Jing Shi, Junlin Yang, Qirun Dai, Xiangchen Song, Xiao Liu, Yuen Chen","submitted_at":"2026-05-25T16:57:06Z","abstract_excerpt":"We introduce CausaLab, a scalable environment for evaluating interactive causal discovery by LLM agents. Unlike prior evaluations, CausaLab evaluates both whether an agent can solve a problem using causal evidence and whether its answer is supported by a correct hypothesis about the underlying causal mechanism. Each episode places an agent in a synthetic laboratory: it receives prior measurement records, intervenes on a manipulator crystal, and predicts the resonance frequency of a held-out reactor crystal governed by the same mechanism. The hidden data-generating process is a randomly sampled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26029","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/2605.26029/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":"2605.26029","created_at":"2026-05-26T02:05:24.127471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26029v1","created_at":"2026-05-26T02:05:24.127471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26029","created_at":"2026-05-26T02:05:24.127471+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZK5WAHH5KVSS","created_at":"2026-05-26T02:05:24.127471+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZK5WAHH5KVSSLDH3","created_at":"2026-05-26T02:05:24.127471+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZK5WAHH5","created_at":"2026-05-26T02:05:24.127471+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/ZK5WAHH5KVSSLDH3BODHSH42F7","json":"https://pith.science/pith/ZK5WAHH5KVSSLDH3BODHSH42F7.json","graph_json":"https://pith.science/api/pith-number/ZK5WAHH5KVSSLDH3BODHSH42F7/graph.json","events_json":"https://pith.science/api/pith-number/ZK5WAHH5KVSSLDH3BODHSH42F7/events.json","paper":"https://pith.science/paper/ZK5WAHH5"},"agent_actions":{"view_html":"https://pith.science/pith/ZK5WAHH5KVSSLDH3BODHSH42F7","download_json":"https://pith.science/pith/ZK5WAHH5KVSSLDH3BODHSH42F7.json","view_paper":"https://pith.science/paper/ZK5WAHH5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26029&json=true","fetch_graph":"https://pith.science/api/pith-number/ZK5WAHH5KVSSLDH3BODHSH42F7/graph.json","fetch_events":"https://pith.science/api/pith-number/ZK5WAHH5KVSSLDH3BODHSH42F7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZK5WAHH5KVSSLDH3BODHSH42F7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZK5WAHH5KVSSLDH3BODHSH42F7/action/storage_attestation","attest_author":"https://pith.science/pith/ZK5WAHH5KVSSLDH3BODHSH42F7/action/author_attestation","sign_citation":"https://pith.science/pith/ZK5WAHH5KVSSLDH3BODHSH42F7/action/citation_signature","submit_replication":"https://pith.science/pith/ZK5WAHH5KVSSLDH3BODHSH42F7/action/replication_record"}},"created_at":"2026-05-26T02:05:24.127471+00:00","updated_at":"2026-05-26T02:05:24.127471+00:00"}