{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DC67C3DAVLQJWMVAH52PVRY4ME","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1ad59a862370439fc1815e40c1f0a0a50840974390019b42a8bf0c502b888c82","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-06T19:03:11Z","title_canon_sha256":"d357eb3e9168b3e6251cc583e24cceb3691310b6d545d79ab719e2ca5280e400"},"schema_version":"1.0","source":{"id":"2605.21491","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21491","created_at":"2026-05-22T00:02:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21491v1","created_at":"2026-05-22T00:02:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21491","created_at":"2026-05-22T00:02:26Z"},{"alias_kind":"pith_short_12","alias_value":"DC67C3DAVLQJ","created_at":"2026-05-22T00:02:26Z"},{"alias_kind":"pith_short_16","alias_value":"DC67C3DAVLQJWMVA","created_at":"2026-05-22T00:02:26Z"},{"alias_kind":"pith_short_8","alias_value":"DC67C3DA","created_at":"2026-05-22T00:02:26Z"}],"graph_snapshots":[{"event_id":"sha256:e3755c26662d696e8c5f54b4f7ffff578ea6df722296dd935d262347f48d52f5","target":"graph","created_at":"2026-05-22T00:02:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.21491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As language models accelerate scientific research by automating hypothesis generation and implementation, a new bottleneck emerges: evaluating and filtering hundreds of AI-generated ideas without exhaustive experimentation. We ask whether LMs can learn to forecast the empirical success of research ideas before any experiments are run. We study comparative empirical forecasting: given a benchmark-specific research goal and two candidate ideas, predict which will achieve better benchmark performance. We construct a dataset of 11,488 idea pairs grounded in objective outcomes from PapersWithCode. ","authors_text":"Aniketh Garikaparthi, Manasi Patwardhan, Srujan P Mule","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-06T19:03:11Z","title":"Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21491","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fafec0a30471672c8e1ad4c6de238a1db075ba48be1641a1933bd285761f38ac","target":"record","created_at":"2026-05-22T00:02:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1ad59a862370439fc1815e40c1f0a0a50840974390019b42a8bf0c502b888c82","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-06T19:03:11Z","title_canon_sha256":"d357eb3e9168b3e6251cc583e24cceb3691310b6d545d79ab719e2ca5280e400"},"schema_version":"1.0","source":{"id":"2605.21491","kind":"arxiv","version":1}},"canonical_sha256":"18bdf16c60aae09b32a03f74fac71c6138c49eb7866e695233a1e2cac8a2ed5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18bdf16c60aae09b32a03f74fac71c6138c49eb7866e695233a1e2cac8a2ed5e","first_computed_at":"2026-05-22T00:02:26.809910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T00:02:26.809910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pbYeDrvxqxuhlFCFYfpWW2MpBWqtfRNsqolUuBLAL2zpGgoZSkBgIZDCZl7i/qNQh5aNsmFOvYoUcAiJh/DiBg==","signature_status":"signed_v1","signed_at":"2026-05-22T00:02:26.810415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21491","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fafec0a30471672c8e1ad4c6de238a1db075ba48be1641a1933bd285761f38ac","sha256:e3755c26662d696e8c5f54b4f7ffff578ea6df722296dd935d262347f48d52f5"],"state_sha256":"5329f091364857ae34cece1c25a56aeb5275a0867be4a507a4827106e5b99522"}