{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QOQAVYY43YPYNKHKKZWIYBHJLV","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":"b057d46bd46226285775af30661f89963b9652bb9a3ef8661d75363266f42e15","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-17T05:03:24Z","title_canon_sha256":"c31592c0b5e6642281f93c4b001ef43594e0eac7f39013260bcc93ae2580591f"},"schema_version":"1.0","source":{"id":"2605.17261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17261","created_at":"2026-05-20T00:03:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17261v1","created_at":"2026-05-20T00:03:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17261","created_at":"2026-05-20T00:03:48Z"},{"alias_kind":"pith_short_12","alias_value":"QOQAVYY43YPY","created_at":"2026-05-20T00:03:48Z"},{"alias_kind":"pith_short_16","alias_value":"QOQAVYY43YPYNKHK","created_at":"2026-05-20T00:03:48Z"},{"alias_kind":"pith_short_8","alias_value":"QOQAVYY4","created_at":"2026-05-20T00:03:48Z"}],"graph_snapshots":[{"event_id":"sha256:3bcb93779775143196dbfd087b79241d00e0b45e302bea52edcb483d8cf8f1a2","target":"graph","created_at":"2026-05-20T00:03:48Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Extensive evaluations on both In-Distribution and diverse biological OOD benchmarks demonstrate that 2D-ProteinRAG consistently achieves state-of-the-art performance, outperforming fine-tuned baselines and other RAG methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the proposed horizontal fine-grained attribute alignment and vertical homology-based semantic denoising steps, when applied after BLAST retrieval, will reliably extract high-quality information from noisy contexts and generalize to novel proteins without introducing new errors."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"2D-ProteinRAG is a dual-dimensional RAG framework that incorporates BLAST workflows plus horizontal attribute alignment and vertical homology denoising to improve protein-text QA on both in-distribution and out-of-distribution cases."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"2D-ProteinRAG embeds LLMs in BLAST workflows with dual filtering to handle novel proteins in question answering"}],"snapshot_sha256":"5f6ddd98eff7249e03553299847d84de8db40366a40456015a569ce169c0cbd4"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"2280aeb9f0ab83793726399ba71a2669d64c9c4e7a04468bb425bf121b8aea47"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T23:31:20.257647Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T23:31:05.313423Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T22:01:57.849591Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.784016Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.17261/integrity.json","findings":[],"snapshot_sha256":"7e8f7d884be65662258863fc3d81c503b781f7b6afa997208b009b5e9129ca8b","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Protein-Text Question Answering (QA) is crucial for interpreting biological sequences through natural language. The integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) that efficiently leverages biological databases and facilitates reasoning offers a potent approach for it. However, constrained by the standard RAG pipeline, these models often rely on curated, static datasets instead of expert-proven biological workflows, lacking the fine-grained information processing and struggling to generalize to novel (OOD) proteins. To bridge this gap, we propose 2D-Prote","authors_text":"Chen Huang, Duanyu Feng, Li Ding, See-kiong Ng, Wenqiang Lei, Yang Li, Yangshuai Wang","cross_cats":[],"headline":"2D-ProteinRAG embeds LLMs in BLAST workflows with dual filtering to handle novel proteins in question answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-17T05:03:24Z","title":"Unlocking Biological Workflows for Robust Protein-Text Question Answering: A Dual-Dimensional RAG Framework"},"references":{"count":38,"internal_anchors":4,"resolved_work":38,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"S F Altschul, W Gish, W Miller, E W Myers, and D J Lipman. 1990. Basic local alignment search tool.J. Mol. Biol.215, 3 (Oct. 1990), 403–410","work_id":"813b4ae7-7b1d-4ebf-8d62-7ff7859783c9","year":1990},{"cited_arxiv_id":"2507.06261","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","work_id":"008df105-2fdd-45d8-857a-8e35868aecb6","year":2025},{"cited_arxiv_id":"","doi":"10.1093/nar/gkae1010","is_internal_anchor":false,"ref_index":3,"title":"The UniProt Consortium. 2024. UniProt: the Universal Pro- tein Knowledgebase in 2025.Nucleic Acids Research53, D1 (11 2024), D609–D617. arXiv:https://academic.oup.com/nar/article- pdf/53/D1/D609/60719","work_id":"dbdc78a3-ee26-47ca-892c-66b69b43dbae","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"D Devos and A Valencia. 2000. Practical limits of function prediction.Proteins 41, 1 (Oct. 2000), 98–107","work_id":"7977ae4f-abfc-4c04-8527-e39412efcaab","year":2000},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"arXiv preprint arXiv:2501.10282 (2025)","work_id":"82aa0ed8-bab7-4c7b-9892-2eac426c3055","year":2025}],"snapshot_sha256":"a9f8197e1000ef29d95947269b20f08506372b4942e6472771458152f24c75e2"},"source":{"id":"2605.17261","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T23:27:10.897126Z","id":"85851c50-52de-4533-b42f-4428cd84c4e6","model_set":{"reader":"grok-4.3"},"one_line_summary":"2D-ProteinRAG is a dual-dimensional RAG framework that incorporates BLAST workflows plus horizontal attribute alignment and vertical homology denoising to improve protein-text QA on both in-distribution and out-of-distribution cases.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"2D-ProteinRAG embeds LLMs in BLAST workflows with dual filtering to handle novel proteins in question answering","strongest_claim":"Extensive evaluations on both In-Distribution and diverse biological OOD benchmarks demonstrate that 2D-ProteinRAG consistently achieves state-of-the-art performance, outperforming fine-tuned baselines and other RAG methods.","weakest_assumption":"That the proposed horizontal fine-grained attribute alignment and vertical homology-based semantic denoising steps, when applied after BLAST retrieval, will reliably extract high-quality information from noisy contexts and generalize to novel proteins without introducing new errors."}},"verdict_id":"85851c50-52de-4533-b42f-4428cd84c4e6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6f40290a309c63ba5f51240c03f6ed8a2decbf82752d013654e8ef5ff28b8498","target":"record","created_at":"2026-05-20T00:03:48Z","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":"b057d46bd46226285775af30661f89963b9652bb9a3ef8661d75363266f42e15","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-17T05:03:24Z","title_canon_sha256":"c31592c0b5e6642281f93c4b001ef43594e0eac7f39013260bcc93ae2580591f"},"schema_version":"1.0","source":{"id":"2605.17261","kind":"arxiv","version":1}},"canonical_sha256":"83a00ae31cde1f86a8ea566c8c04e95d654531184adaea6006f9a4ffe0cafb51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83a00ae31cde1f86a8ea566c8c04e95d654531184adaea6006f9a4ffe0cafb51","first_computed_at":"2026-05-20T00:03:48.299779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:48.299779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hxvBbZ3d8KMNDAzvsHn6Z11mbdAlhbYCBELa1GZDEFe797Hk26PzE6o/IJ4jh6yMA/0iL8PfKhT+4icfxxtPBg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:48.300619Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f40290a309c63ba5f51240c03f6ed8a2decbf82752d013654e8ef5ff28b8498","sha256:3bcb93779775143196dbfd087b79241d00e0b45e302bea52edcb483d8cf8f1a2"],"state_sha256":"733346e59563f3aec58904132e473a6dbb717607b92df5022e24c9a159b63901"}