{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DLVOFUUKUKFP7GND3545E4KTRY","short_pith_number":"pith:DLVOFUUK","schema_version":"1.0","canonical_sha256":"1aeae2d28aa28aff99a3df79d271538e23cfc2a80fc01450d5e898a90311ec84","source":{"kind":"arxiv","id":"2506.11603","version":2},"attestation_state":"computed","paper":{"title":"TongSearch-QR: Reinforced Query Reasoning for Retrieval","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jiaqi Li, Jun Bai, Xubo Qin, Zilong Zheng, Zixia Jia","submitted_at":"2025-06-13T09:17:36Z","abstract_excerpt":"Traditional information retrieval (IR) methods excel at textual and semantic matching but struggle in reasoning-intensive retrieval tasks that require multi-hop inference or complex semantic understanding between queries and documents. One promising solution is to explicitly rewrite or augment queries using large language models (LLMs) to elicit reasoning-relevant content prior to retrieval. However, the widespread use of large-scale language models like GPT-4 or LLaMA3-70B remains impractical due to their high inference cost and limited deployability in real-world systems. In this work, we in"},"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":"2506.11603","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-13T09:17:36Z","cross_cats_sorted":[],"title_canon_sha256":"72c776ffb514cecb35150aa34e92025a00d36244b66a3004e0ba153e49f5b321","abstract_canon_sha256":"0e776f4f861ae01e2ced6efd9f508ea873f3e841418bfe159ab80589497df68a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:49.997727Z","signature_b64":"jSRnnzFukCQC8FZN+ws0AwLkXcDQ4z+Y89Re0R3OSP+SzNXGDJc0TFDPYB4kaz4HJsRux6LkGIt3rc+Dx/Z8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1aeae2d28aa28aff99a3df79d271538e23cfc2a80fc01450d5e898a90311ec84","last_reissued_at":"2026-07-05T11:21:49.997298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:49.997298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TongSearch-QR: Reinforced Query Reasoning for Retrieval","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jiaqi Li, Jun Bai, Xubo Qin, Zilong Zheng, Zixia Jia","submitted_at":"2025-06-13T09:17:36Z","abstract_excerpt":"Traditional information retrieval (IR) methods excel at textual and semantic matching but struggle in reasoning-intensive retrieval tasks that require multi-hop inference or complex semantic understanding between queries and documents. One promising solution is to explicitly rewrite or augment queries using large language models (LLMs) to elicit reasoning-relevant content prior to retrieval. However, the widespread use of large-scale language models like GPT-4 or LLaMA3-70B remains impractical due to their high inference cost and limited deployability in real-world systems. In this work, we in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11603","kind":"arxiv","version":2},"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/2506.11603/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":"2506.11603","created_at":"2026-07-05T11:21:49.997363+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11603v2","created_at":"2026-07-05T11:21:49.997363+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11603","created_at":"2026-07-05T11:21:49.997363+00:00"},{"alias_kind":"pith_short_12","alias_value":"DLVOFUUKUKFP","created_at":"2026-07-05T11:21:49.997363+00:00"},{"alias_kind":"pith_short_16","alias_value":"DLVOFUUKUKFP7GND","created_at":"2026-07-05T11:21:49.997363+00:00"},{"alias_kind":"pith_short_8","alias_value":"DLVOFUUK","created_at":"2026-07-05T11:21:49.997363+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26352","citing_title":"RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29507","citing_title":"Xetrieval: Mechanistically Explaining Dense Retrieval","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2511.11653","citing_title":"GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DLVOFUUKUKFP7GND3545E4KTRY","json":"https://pith.science/pith/DLVOFUUKUKFP7GND3545E4KTRY.json","graph_json":"https://pith.science/api/pith-number/DLVOFUUKUKFP7GND3545E4KTRY/graph.json","events_json":"https://pith.science/api/pith-number/DLVOFUUKUKFP7GND3545E4KTRY/events.json","paper":"https://pith.science/paper/DLVOFUUK"},"agent_actions":{"view_html":"https://pith.science/pith/DLVOFUUKUKFP7GND3545E4KTRY","download_json":"https://pith.science/pith/DLVOFUUKUKFP7GND3545E4KTRY.json","view_paper":"https://pith.science/paper/DLVOFUUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11603&json=true","fetch_graph":"https://pith.science/api/pith-number/DLVOFUUKUKFP7GND3545E4KTRY/graph.json","fetch_events":"https://pith.science/api/pith-number/DLVOFUUKUKFP7GND3545E4KTRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DLVOFUUKUKFP7GND3545E4KTRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DLVOFUUKUKFP7GND3545E4KTRY/action/storage_attestation","attest_author":"https://pith.science/pith/DLVOFUUKUKFP7GND3545E4KTRY/action/author_attestation","sign_citation":"https://pith.science/pith/DLVOFUUKUKFP7GND3545E4KTRY/action/citation_signature","submit_replication":"https://pith.science/pith/DLVOFUUKUKFP7GND3545E4KTRY/action/replication_record"}},"created_at":"2026-07-05T11:21:49.997363+00:00","updated_at":"2026-07-05T11:21:49.997363+00:00"}