{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JUO6GTVURNRCRLSPWBNRUYT7E6","short_pith_number":"pith:JUO6GTVU","schema_version":"1.0","canonical_sha256":"4d1de34eb48b6228ae4fb05b1a627f278c6373f11e9b08af016fb3ae7b8d1b5f","source":{"kind":"arxiv","id":"2605.12995","version":1},"attestation_state":"computed","paper":{"title":"F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"F-GRPO lets one LLM jointly generate candidates and rank them by factorizing policy optimization into separate phases with distinct advantages.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bowen Jin, Gagan Mundada, Jiawei Han, Jingbo Shang, Julian McAuley, Junda Wu, Ritwik Sinha, Rohan Surana, Sizhe Zhou, Tong Yu, Xintong Li, Yizhu Jiao","submitted_at":"2026-05-13T04:52:33Z","abstract_excerpt":"Traditional retrieval pipelines optimize utility through stages of candidate retrieval and reranking, where ranking operates over a predefined candidate set. Large Language Models (LLMs) broaden this into a generative process: given a candidate pool, an LLM can generate a subset and order it within a single autoregressive pass. However, this flexibility introduces a new optimization challenge: the model must search a combinatorial output space while receiving utility feedback only after the full ranked list is generated. Because this feedback is defined over the completed sequence, it cannot d"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.12995","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T04:52:33Z","cross_cats_sorted":[],"title_canon_sha256":"be1d84642db727b9fd0a96430a0139d17bd727ead19e033275c85103a0863336","abstract_canon_sha256":"d2216fd17bd931574c3fd6cab14a6aec7f5ce6e1e6086a96e8b28c009824c5db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:00.498140Z","signature_b64":"N2hfVYRG3PZB1Zg21j3rM4yX+Cid5KTw7fQkfs9Pl33GAbSgEoVjQDsU+F8CJ+Uc0tk4IPng6Bes/b6k3qN2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d1de34eb48b6228ae4fb05b1a627f278c6373f11e9b08af016fb3ae7b8d1b5f","last_reissued_at":"2026-05-18T03:09:00.497587Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:00.497587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"F-GRPO lets one LLM jointly generate candidates and rank them by factorizing policy optimization into separate phases with distinct advantages.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bowen Jin, Gagan Mundada, Jiawei Han, Jingbo Shang, Julian McAuley, Junda Wu, Ritwik Sinha, Rohan Surana, Sizhe Zhou, Tong Yu, Xintong Li, Yizhu Jiao","submitted_at":"2026-05-13T04:52:33Z","abstract_excerpt":"Traditional retrieval pipelines optimize utility through stages of candidate retrieval and reranking, where ranking operates over a predefined candidate set. Large Language Models (LLMs) broaden this into a generative process: given a candidate pool, an LLM can generate a subset and order it within a single autoregressive pass. However, this flexibility introduces a new optimization challenge: the model must search a combinatorial output space while receiving utility feedback only after the full ranked list is generated. Because this feedback is defined over the completed sequence, it cannot d"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"F-GRPO improves top-ranked performance over GRPO and decoupled baselines, outperforms supervised alternatives, and remains competitive with strong zero-shot rerankers, with no architectural changes at inference time.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The phase-specific credit assignment problem can be resolved by applying separate group-relative advantages to generation and ranking inside a two-phase sequence-level objective while sharing a single LLM backbone.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"F-GRPO factorizes group-relative policy optimization into generation and ranking phases within one autoregressive sequence, using order-invariant coverage and position-aware utility rewards to improve top-ranked performance on recommendation and multi-hop QA tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"F-GRPO lets one LLM jointly generate candidates and rank them by factorizing policy optimization into separate phases with distinct advantages.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0dbd9a6a253db09894895d4c13d27b6bc4e53f14e637762b3f01342e8dd2c1a6"},"source":{"id":"2605.12995","kind":"arxiv","version":1},"verdict":{"id":"d459ee2b-4a28-4298-8c4a-93e7cced2add","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:48:31.789661Z","strongest_claim":"F-GRPO improves top-ranked performance over GRPO and decoupled baselines, outperforms supervised alternatives, and remains competitive with strong zero-shot rerankers, with no architectural changes at inference time.","one_line_summary":"F-GRPO factorizes group-relative policy optimization into generation and ranking phases within one autoregressive sequence, using order-invariant coverage and position-aware utility rewards to improve top-ranked performance on recommendation and multi-hop QA tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The phase-specific credit assignment problem can be resolved by applying separate group-relative advantages to generation and ranking inside a two-phase sequence-level objective while sharing a single LLM backbone.","pith_extraction_headline":"F-GRPO lets one LLM jointly generate candidates and rank them by factorizing policy optimization into separate phases with distinct advantages."},"references":{"count":76,"sample":[{"doi":"","year":2011,"title":"Ellis, Brian Whitman, and Paul Lamere","work_id":"3fbb6e4b-5eaa-4672-b118-27365be53cc8","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Autoregressive search engines: Generating substrings as document identifiers","work_id":"c548f215-b75f-4910-848d-3fe1c6887e1d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1145/3539597.3570412","year":2023,"title":"Generative slate recommendation with reinforcement learning","work_id":"77c5c94e-635e-4641-b5d7-67678c66e18e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Chang, Claire Cardie, Kianté Brantley, and Thorsten Joachim","work_id":"6a5e62e2-6e43-4821-b297-5869267b9c03","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/2022.naacl-main.194","year":2022,"title":"URL https://doi.org/10.18653/v1/2022.naa cl-main.194","work_id":"57971df4-d73b-49da-9f92-43d0c13f54c9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":76,"snapshot_sha256":"aff0f130a45adbc22583b2d53d98501c106a20ed972a6a0cc81c55469c4a8199","internal_anchors":7},"formal_canon":{"evidence_count":2,"snapshot_sha256":"53636b18e9bedcc33a89fcdfd91754292b351dd370df35424c9ff5fcdf84d34f"},"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":"2605.12995","created_at":"2026-05-18T03:09:00.497670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12995v1","created_at":"2026-05-18T03:09:00.497670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12995","created_at":"2026-05-18T03:09:00.497670+00:00"},{"alias_kind":"pith_short_12","alias_value":"JUO6GTVURNRC","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"JUO6GTVURNRCRLSP","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"JUO6GTVU","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JUO6GTVURNRCRLSPWBNRUYT7E6","json":"https://pith.science/pith/JUO6GTVURNRCRLSPWBNRUYT7E6.json","graph_json":"https://pith.science/api/pith-number/JUO6GTVURNRCRLSPWBNRUYT7E6/graph.json","events_json":"https://pith.science/api/pith-number/JUO6GTVURNRCRLSPWBNRUYT7E6/events.json","paper":"https://pith.science/paper/JUO6GTVU"},"agent_actions":{"view_html":"https://pith.science/pith/JUO6GTVURNRCRLSPWBNRUYT7E6","download_json":"https://pith.science/pith/JUO6GTVURNRCRLSPWBNRUYT7E6.json","view_paper":"https://pith.science/paper/JUO6GTVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12995&json=true","fetch_graph":"https://pith.science/api/pith-number/JUO6GTVURNRCRLSPWBNRUYT7E6/graph.json","fetch_events":"https://pith.science/api/pith-number/JUO6GTVURNRCRLSPWBNRUYT7E6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JUO6GTVURNRCRLSPWBNRUYT7E6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JUO6GTVURNRCRLSPWBNRUYT7E6/action/storage_attestation","attest_author":"https://pith.science/pith/JUO6GTVURNRCRLSPWBNRUYT7E6/action/author_attestation","sign_citation":"https://pith.science/pith/JUO6GTVURNRCRLSPWBNRUYT7E6/action/citation_signature","submit_replication":"https://pith.science/pith/JUO6GTVURNRCRLSPWBNRUYT7E6/action/replication_record"}},"created_at":"2026-05-18T03:09:00.497670+00:00","updated_at":"2026-05-18T03:09:00.497670+00:00"}