{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FZD4JUB7R2MZLGSQPNJLKZH475","short_pith_number":"pith:FZD4JUB7","schema_version":"1.0","canonical_sha256":"2e47c4d03f8e99959a507b52b564fcff7fb67210d33402f99eb137d9e1ae0f0c","source":{"kind":"arxiv","id":"2606.12071","version":1},"attestation_state":"computed","paper":{"title":"On the Limits of LLM-as-Judge for Scientific Novelty Assessment","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DL","authors_text":"Navonil Majumder, Soujanya Poria, Soumitra Sinhahajari","submitted_at":"2026-06-10T13:34:38Z","abstract_excerpt":"LLMs are increasingly used to generate and judge scientific ideas. This makes novelty evaluation a central problem. Full idea evaluation is difficult because it often requires judging a method, its feasibility, and its empirical promise. We therefore study a cleaner upstream object: the research question (RQ). RQ generation is a prerequisite for scientific ideation, and RQs can be compared against questions pursued in real papers. We introduce RQ-Bench, a benchmark built from recent arXiv papers. For each paper, we reconstruct author-anchored RQs from its cited background, gaps, and contributi"},"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":"2606.12071","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2026-06-10T13:34:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"566c6b7fe9ea6653a14d69fc5930d34b4f54e303286f80c12eabce1c4f79c854","abstract_canon_sha256":"77a435255c389481877cc9c6867315f5d4b843daf5d5a55952dafe30199902ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:46.113062Z","signature_b64":"mGifkyqrd8/jY3RyLd3qaIYZOnNI4Kyc6kPY5xUqB7keJXAemeHEaggcHvp1DjrIegnVxkI4ADOQ+HrzRXazDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e47c4d03f8e99959a507b52b564fcff7fb67210d33402f99eb137d9e1ae0f0c","last_reissued_at":"2026-06-11T01:10:46.112246Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:46.112246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Limits of LLM-as-Judge for Scientific Novelty Assessment","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DL","authors_text":"Navonil Majumder, Soujanya Poria, Soumitra Sinhahajari","submitted_at":"2026-06-10T13:34:38Z","abstract_excerpt":"LLMs are increasingly used to generate and judge scientific ideas. This makes novelty evaluation a central problem. Full idea evaluation is difficult because it often requires judging a method, its feasibility, and its empirical promise. We therefore study a cleaner upstream object: the research question (RQ). RQ generation is a prerequisite for scientific ideation, and RQs can be compared against questions pursued in real papers. We introduce RQ-Bench, a benchmark built from recent arXiv papers. For each paper, we reconstruct author-anchored RQs from its cited background, gaps, and contributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12071","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/2606.12071/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":"2606.12071","created_at":"2026-06-11T01:10:46.112385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12071v1","created_at":"2026-06-11T01:10:46.112385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12071","created_at":"2026-06-11T01:10:46.112385+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZD4JUB7R2MZ","created_at":"2026-06-11T01:10:46.112385+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZD4JUB7R2MZLGSQ","created_at":"2026-06-11T01:10:46.112385+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZD4JUB7","created_at":"2026-06-11T01:10:46.112385+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/FZD4JUB7R2MZLGSQPNJLKZH475","json":"https://pith.science/pith/FZD4JUB7R2MZLGSQPNJLKZH475.json","graph_json":"https://pith.science/api/pith-number/FZD4JUB7R2MZLGSQPNJLKZH475/graph.json","events_json":"https://pith.science/api/pith-number/FZD4JUB7R2MZLGSQPNJLKZH475/events.json","paper":"https://pith.science/paper/FZD4JUB7"},"agent_actions":{"view_html":"https://pith.science/pith/FZD4JUB7R2MZLGSQPNJLKZH475","download_json":"https://pith.science/pith/FZD4JUB7R2MZLGSQPNJLKZH475.json","view_paper":"https://pith.science/paper/FZD4JUB7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12071&json=true","fetch_graph":"https://pith.science/api/pith-number/FZD4JUB7R2MZLGSQPNJLKZH475/graph.json","fetch_events":"https://pith.science/api/pith-number/FZD4JUB7R2MZLGSQPNJLKZH475/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZD4JUB7R2MZLGSQPNJLKZH475/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZD4JUB7R2MZLGSQPNJLKZH475/action/storage_attestation","attest_author":"https://pith.science/pith/FZD4JUB7R2MZLGSQPNJLKZH475/action/author_attestation","sign_citation":"https://pith.science/pith/FZD4JUB7R2MZLGSQPNJLKZH475/action/citation_signature","submit_replication":"https://pith.science/pith/FZD4JUB7R2MZLGSQPNJLKZH475/action/replication_record"}},"created_at":"2026-06-11T01:10:46.112385+00:00","updated_at":"2026-06-11T01:10:46.112385+00:00"}