{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FGVQHKXRGMA4LKCEWI2UZN7HD6","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":"5f3de702bfa139efad6757c6699f50421b0499de007ff72515a3c3a9d54966f6","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T01:50:52Z","title_canon_sha256":"fb72c69f29d6e4d63604d8028a561b976132d813948d16b19ee31523a4f2253b"},"schema_version":"1.0","source":{"id":"2605.29234","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29234","created_at":"2026-05-29T01:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29234v1","created_at":"2026-05-29T01:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29234","created_at":"2026-05-29T01:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"FGVQHKXRGMA4","created_at":"2026-05-29T01:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"FGVQHKXRGMA4LKCE","created_at":"2026-05-29T01:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"FGVQHKXR","created_at":"2026-05-29T01:05:26Z"}],"graph_snapshots":[{"event_id":"sha256:6dc66f11e0bcafbce83e2d539642c717a15d2db10d7552d3e5933084ea158acf","target":"graph","created_at":"2026-05-29T01:05:26Z","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/2605.29234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study large-scale literature search from two complementary angles: improving the retrieval pipeline, and stress-testing the human reference list as an evaluation target. First, we implement a Deep Research pipeline that processes the full query paper and expands the retrieved results breadth-first along their bibliographies, and show that it substantially outperforms vanilla API-only search, raising recall on RollingEval-Jun25 (a 250-paper literature-search benchmark) from below 20% to above 80%. Second, we use a neutral LLM-as-a-judge to determine if human references are sound ground truth","authors_text":"Christopher Pal, Gaurav Sahu, Laurent Charlin","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T01:50:52Z","title":"Rethinking Literature Search Evaluation: Deep Research Helps, and Human Citation Lists Are Not a Ground Truth"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29234","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":"sha256:46c20fa3d162e11eb2f8c1a76bb06265fd9b69a06a357ea21e75552479c2f497","target":"record","created_at":"2026-05-29T01:05:26Z","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":"5f3de702bfa139efad6757c6699f50421b0499de007ff72515a3c3a9d54966f6","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T01:50:52Z","title_canon_sha256":"fb72c69f29d6e4d63604d8028a561b976132d813948d16b19ee31523a4f2253b"},"schema_version":"1.0","source":{"id":"2605.29234","kind":"arxiv","version":1}},"canonical_sha256":"29ab03aaf13301c5a844b2354cb7e71f831d8e7ffae5493721480a26e3809ff6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29ab03aaf13301c5a844b2354cb7e71f831d8e7ffae5493721480a26e3809ff6","first_computed_at":"2026-05-29T01:05:26.326728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:26.326728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wl+AKvwV+1/j4ZW+cMD8ot1EdZzJP+cIqJPdgyEL+SDmhTGed+Dmvc9vzWPpZwbHjmFLuadA6gapN40+wzzEBQ==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:26.327501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29234","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46c20fa3d162e11eb2f8c1a76bb06265fd9b69a06a357ea21e75552479c2f497","sha256:6dc66f11e0bcafbce83e2d539642c717a15d2db10d7552d3e5933084ea158acf"],"state_sha256":"0e5cb069fdb94cc77e533c2ed5436e03ed7746ba0a65884696a54632904b735f"}