{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RCMNCOS5JDEJ6E2532PRET7E76","short_pith_number":"pith:RCMNCOS5","schema_version":"1.0","canonical_sha256":"8898d13a5d48c89f135dde9f124fe4ffa314687a89b53b17c7e39d19c35a1b0e","source":{"kind":"arxiv","id":"2605.29631","version":1},"attestation_state":"computed","paper":{"title":"Predicting Causal Effects from Natural Language Queries using Structured Representations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abelardo Carlos Martinez Lorenzo, Arianna Legovini, Giuliano Martinelli, Jasmin Baier, Linxi Wang, Piriyakorn Piriyatamwong, Riccardo Orlando, Samuel Fraiberger, Satvik Garg, Sharif Kazemi","submitted_at":"2026-05-28T09:04:07Z","abstract_excerpt":"Randomized controlled trials are a cornerstone of medicine and the social sciences as they enable reliable estimates of causal effects. However, they are costly and time-consuming to conduct, motivating interest in predicting causal effects from existing experimental evidence. Recent advances in large language models (LLMs) have demonstrated strong performance on knowledge-intensive tasks, raising the question of whether these models can be used for forecasting causal effect sizes. To investigate this, we introduce Query2Effect, a new large-scale benchmark consisting of more than 72,000 natura"},"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":"2605.29631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T09:04:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"afb07a1a3ea0f01f4b8a0932b84d05948e5b2a7d3ea9017f237fa53676784551","abstract_canon_sha256":"e16a657916b795ea22b5d3cf5e940283e390136f22f47ff1c97348c902dbda8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:51.960693Z","signature_b64":"odViLkO93ljKzuEdtyK7J/106nmJGgJwV75Aq9xgdd9kr7k35/ZBI9g8yjC4/pvwaGnKlZHlbSWxx6ZTu+RoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8898d13a5d48c89f135dde9f124fe4ffa314687a89b53b17c7e39d19c35a1b0e","last_reissued_at":"2026-05-29T01:05:51.960011Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:51.960011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting Causal Effects from Natural Language Queries using Structured Representations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abelardo Carlos Martinez Lorenzo, Arianna Legovini, Giuliano Martinelli, Jasmin Baier, Linxi Wang, Piriyakorn Piriyatamwong, Riccardo Orlando, Samuel Fraiberger, Satvik Garg, Sharif Kazemi","submitted_at":"2026-05-28T09:04:07Z","abstract_excerpt":"Randomized controlled trials are a cornerstone of medicine and the social sciences as they enable reliable estimates of causal effects. However, they are costly and time-consuming to conduct, motivating interest in predicting causal effects from existing experimental evidence. Recent advances in large language models (LLMs) have demonstrated strong performance on knowledge-intensive tasks, raising the question of whether these models can be used for forecasting causal effect sizes. To investigate this, we introduce Query2Effect, a new large-scale benchmark consisting of more than 72,000 natura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29631","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/2605.29631/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":"2605.29631","created_at":"2026-05-29T01:05:51.960114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29631v1","created_at":"2026-05-29T01:05:51.960114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29631","created_at":"2026-05-29T01:05:51.960114+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCMNCOS5JDEJ","created_at":"2026-05-29T01:05:51.960114+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCMNCOS5JDEJ6E25","created_at":"2026-05-29T01:05:51.960114+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCMNCOS5","created_at":"2026-05-29T01:05:51.960114+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/RCMNCOS5JDEJ6E2532PRET7E76","json":"https://pith.science/pith/RCMNCOS5JDEJ6E2532PRET7E76.json","graph_json":"https://pith.science/api/pith-number/RCMNCOS5JDEJ6E2532PRET7E76/graph.json","events_json":"https://pith.science/api/pith-number/RCMNCOS5JDEJ6E2532PRET7E76/events.json","paper":"https://pith.science/paper/RCMNCOS5"},"agent_actions":{"view_html":"https://pith.science/pith/RCMNCOS5JDEJ6E2532PRET7E76","download_json":"https://pith.science/pith/RCMNCOS5JDEJ6E2532PRET7E76.json","view_paper":"https://pith.science/paper/RCMNCOS5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29631&json=true","fetch_graph":"https://pith.science/api/pith-number/RCMNCOS5JDEJ6E2532PRET7E76/graph.json","fetch_events":"https://pith.science/api/pith-number/RCMNCOS5JDEJ6E2532PRET7E76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCMNCOS5JDEJ6E2532PRET7E76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCMNCOS5JDEJ6E2532PRET7E76/action/storage_attestation","attest_author":"https://pith.science/pith/RCMNCOS5JDEJ6E2532PRET7E76/action/author_attestation","sign_citation":"https://pith.science/pith/RCMNCOS5JDEJ6E2532PRET7E76/action/citation_signature","submit_replication":"https://pith.science/pith/RCMNCOS5JDEJ6E2532PRET7E76/action/replication_record"}},"created_at":"2026-05-29T01:05:51.960114+00:00","updated_at":"2026-05-29T01:05:51.960114+00:00"}