{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RNLCU7BBR3CCJW7R27LMDIXRMS","short_pith_number":"pith:RNLCU7BB","schema_version":"1.0","canonical_sha256":"8b562a7c218ec424dbf1d7d6c1a2f1649a36901f1df8223c49df510a4434dc3e","source":{"kind":"arxiv","id":"2503.08569","version":1},"attestation_state":"computed","paper":{"title":"DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Linyi Yang, Minjun Zhu, Yixuan Weng, Yue Zhang","submitted_at":"2025-03-11T15:59:43Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly utilized in scientific research assessment, particularly in automated paper review. However, existing LLM-based review systems face significant challenges, including limited domain expertise, hallucinated reasoning, and a lack of structured evaluation. To address these limitations, we introduce DeepReview, a multi-stage framework designed to emulate expert reviewers by incorporating structured analysis, literature retrieval, and evidence-based argumentation. Using DeepReview-13K, a curated dataset with structured annotations, we train DeepReviewer-"},"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":"2503.08569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T15:59:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8cfa33e98b3d9e00f14aeacaa1fe493731eec91eaf3f43f4093ae03b5839cd9e","abstract_canon_sha256":"4321f9726810d8dd7d1a79a6d883fae6e2814c767c73a902293d8238a77de1c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:02.484240Z","signature_b64":"5yqCcGaKInE7cXphOAjYdZMTpPV3vSyZDEOQdttzUBwBuVCtBs9gyxDLCId6sFXH9Kg0afksJTquMqSHYoClDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b562a7c218ec424dbf1d7d6c1a2f1649a36901f1df8223c49df510a4434dc3e","last_reissued_at":"2026-07-05T10:29:02.483088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:02.483088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Linyi Yang, Minjun Zhu, Yixuan Weng, Yue Zhang","submitted_at":"2025-03-11T15:59:43Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly utilized in scientific research assessment, particularly in automated paper review. However, existing LLM-based review systems face significant challenges, including limited domain expertise, hallucinated reasoning, and a lack of structured evaluation. To address these limitations, we introduce DeepReview, a multi-stage framework designed to emulate expert reviewers by incorporating structured analysis, literature retrieval, and evidence-based argumentation. Using DeepReview-13K, a curated dataset with structured annotations, we train DeepReviewer-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08569","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/2503.08569/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":"2503.08569","created_at":"2026-07-05T10:29:02.483240+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08569v1","created_at":"2026-07-05T10:29:02.483240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08569","created_at":"2026-07-05T10:29:02.483240+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNLCU7BBR3CC","created_at":"2026-07-05T10:29:02.483240+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNLCU7BBR3CCJW7R","created_at":"2026-07-05T10:29:02.483240+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNLCU7BB","created_at":"2026-07-05T10:29:02.483240+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25057","citing_title":"LLM-Based Scientific Peer Review: Methods, Benchmarks, and Reliability Challenges","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21035","citing_title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","ref_index":166,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":269,"is_internal_anchor":false},{"citing_arxiv_id":"2509.13400","citing_title":"Justice in Judgment: Unveiling (Hidden) Bias in LLM-assisted Peer Reviews","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27725","citing_title":"AgentEconomist: An End-to-end Agentic System Translating Economic Intuitions into Executable Computational Experiments","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26506","citing_title":"SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RNLCU7BBR3CCJW7R27LMDIXRMS","json":"https://pith.science/pith/RNLCU7BBR3CCJW7R27LMDIXRMS.json","graph_json":"https://pith.science/api/pith-number/RNLCU7BBR3CCJW7R27LMDIXRMS/graph.json","events_json":"https://pith.science/api/pith-number/RNLCU7BBR3CCJW7R27LMDIXRMS/events.json","paper":"https://pith.science/paper/RNLCU7BB"},"agent_actions":{"view_html":"https://pith.science/pith/RNLCU7BBR3CCJW7R27LMDIXRMS","download_json":"https://pith.science/pith/RNLCU7BBR3CCJW7R27LMDIXRMS.json","view_paper":"https://pith.science/paper/RNLCU7BB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08569&json=true","fetch_graph":"https://pith.science/api/pith-number/RNLCU7BBR3CCJW7R27LMDIXRMS/graph.json","fetch_events":"https://pith.science/api/pith-number/RNLCU7BBR3CCJW7R27LMDIXRMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNLCU7BBR3CCJW7R27LMDIXRMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNLCU7BBR3CCJW7R27LMDIXRMS/action/storage_attestation","attest_author":"https://pith.science/pith/RNLCU7BBR3CCJW7R27LMDIXRMS/action/author_attestation","sign_citation":"https://pith.science/pith/RNLCU7BBR3CCJW7R27LMDIXRMS/action/citation_signature","submit_replication":"https://pith.science/pith/RNLCU7BBR3CCJW7R27LMDIXRMS/action/replication_record"}},"created_at":"2026-07-05T10:29:02.483240+00:00","updated_at":"2026-07-05T10:29:02.483240+00:00"}