{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DKQPLDWICYA7H6YRJZHARNKIVI","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":"ac3a7479fc1728b4840964102ed5691f4b482cb8cb9bcf9d2219c17bf45d4125","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-03T08:22:45Z","title_canon_sha256":"5b3021e52ce1a6ce6c379d229649c6c50327249f66c2e263f64fd508dbdd54de"},"schema_version":"1.0","source":{"id":"2502.01142","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01142","created_at":"2026-07-05T11:17:40Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01142v2","created_at":"2026-07-05T11:17:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01142","created_at":"2026-07-05T11:17:40Z"},{"alias_kind":"pith_short_12","alias_value":"DKQPLDWICYA7","created_at":"2026-07-05T11:17:40Z"},{"alias_kind":"pith_short_16","alias_value":"DKQPLDWICYA7H6YR","created_at":"2026-07-05T11:17:40Z"},{"alias_kind":"pith_short_8","alias_value":"DKQPLDWI","created_at":"2026-07-05T11:17:40Z"}],"graph_snapshots":[{"event_id":"sha256:02195921c61b19527057d78dcd2fbc83d99c6457c9bac7a1e6c8e2e4f66cf3e0","target":"graph","created_at":"2026-07-05T11:17:40Z","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/2502.01142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown remarkable reasoning capabilities, while their practical applications are limited by severe factual hallucinations due to limitations in the timeliness, accuracy, and comprehensiveness of their parametric knowledge. Meanwhile, enhancing retrieval-augmented generation (RAG) with reasoning remains challenging due to ineffective task decomposition and redundant retrieval, which can introduce noise and degrade response quality. In this paper, we propose DeepRAG, a framework that models retrieval-augmented reasoning as a Markov Decision Process (MDP), enablin","authors_text":"Chunlei Xin, Fandong Meng, Hongyu Lin, Jiali Zeng, Jie Zhou, Le Sun, Xianpei Han, Xinyan Guan, Yaojie Lu","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-03T08:22:45Z","title":"DeepRAG: Thinking to Retrieve Step by Step for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01142","kind":"arxiv","version":2},"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":"sha256:1d58c76d73f5365f6c0814e0dc1bcf9e0cd32b90418561d359de03f05a058ef9","target":"record","created_at":"2026-07-05T11:17:40Z","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":"ac3a7479fc1728b4840964102ed5691f4b482cb8cb9bcf9d2219c17bf45d4125","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-03T08:22:45Z","title_canon_sha256":"5b3021e52ce1a6ce6c379d229649c6c50327249f66c2e263f64fd508dbdd54de"},"schema_version":"1.0","source":{"id":"2502.01142","kind":"arxiv","version":2}},"canonical_sha256":"1aa0f58ec81601f3fb114e4e08b548aa048ce40c33a4dcdc398cf7cccce98efe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1aa0f58ec81601f3fb114e4e08b548aa048ce40c33a4dcdc398cf7cccce98efe","first_computed_at":"2026-07-05T11:17:40.475799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:40.475799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ohJAMkgaj+8PKi4kmUMeTGoN/dMk6GDQDmMgoE4MpMvcJkCu8xRdw8NusrYL6qD/FrGzQK0oCF34BG9w6ZGEAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:40.476530Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01142","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d58c76d73f5365f6c0814e0dc1bcf9e0cd32b90418561d359de03f05a058ef9","sha256:02195921c61b19527057d78dcd2fbc83d99c6457c9bac7a1e6c8e2e4f66cf3e0"],"state_sha256":"189b99e6c7a9f831f3e152e4be49fe2d17515dd2667abf36ba6d980a658b9225"}