{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JUO6GTVURNRCRLSPWBNRUYT7E6","short_pith_number":"pith:JUO6GTVU","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"},"canonical_sha256":"4d1de34eb48b6228ae4fb05b1a627f278c6373f11e9b08af016fb3ae7b8d1b5f","source":{"kind":"arxiv","id":"2605.12995","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12995","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12995v1","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12995","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"JUO6GTVURNRC","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"JUO6GTVURNRCRLSP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"JUO6GTVU","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JUO6GTVURNRCRLSPWBNRUYT7E6","target":"record","payload":{"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"},"canonical_sha256":"4d1de34eb48b6228ae4fb05b1a627f278c6373f11e9b08af016fb3ae7b8d1b5f","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"},"source_kind":"arxiv","source_id":"2605.12995","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F8O6u0KoLW+BYKjooRI6KAICpCF1kEFGQzHTr2OZfUELyMxaTl8m4Q+QXloK5cmyfW4VyZo6q01FFwWQroFFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:27:15.660170Z"},"content_sha256":"72a97978e0e5d13ed14ea0ec693344df30cb8db3e37f6ac222232683703656f6","schema_version":"1.0","event_id":"sha256:72a97978e0e5d13ed14ea0ec693344df30cb8db3e37f6ac222232683703656f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JUO6GTVURNRCRLSPWBNRUYT7E6","target":"graph","payload":{"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"},"verdict_id":"d459ee2b-4a28-4298-8c4a-93e7cced2add"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xeH0rE0nNhBQOFrBDYn35A5Z9I2LwAeVWFrGnDIj6PpuvV04rW5jBMAFPw3x01PciB6YjdsreJqZC0lBKy2hCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:27:15.661048Z"},"content_sha256":"292897bf5d2ebc9d6572ca6758387a9ba4167116bf72a7d2679e2af34114954b","schema_version":"1.0","event_id":"sha256:292897bf5d2ebc9d6572ca6758387a9ba4167116bf72a7d2679e2af34114954b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JUO6GTVURNRCRLSPWBNRUYT7E6/bundle.json","state_url":"https://pith.science/pith/JUO6GTVURNRCRLSPWBNRUYT7E6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JUO6GTVURNRCRLSPWBNRUYT7E6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T13:27:15Z","links":{"resolver":"https://pith.science/pith/JUO6GTVURNRCRLSPWBNRUYT7E6","bundle":"https://pith.science/pith/JUO6GTVURNRCRLSPWBNRUYT7E6/bundle.json","state":"https://pith.science/pith/JUO6GTVURNRCRLSPWBNRUYT7E6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JUO6GTVURNRCRLSPWBNRUYT7E6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JUO6GTVURNRCRLSPWBNRUYT7E6","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":"d2216fd17bd931574c3fd6cab14a6aec7f5ce6e1e6086a96e8b28c009824c5db","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T04:52:33Z","title_canon_sha256":"be1d84642db727b9fd0a96430a0139d17bd727ead19e033275c85103a0863336"},"schema_version":"1.0","source":{"id":"2605.12995","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12995","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12995v1","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12995","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"JUO6GTVURNRC","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"JUO6GTVURNRCRLSP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"JUO6GTVU","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:292897bf5d2ebc9d6572ca6758387a9ba4167116bf72a7d2679e2af34114954b","target":"graph","created_at":"2026-05-18T03:09:00Z","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":"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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"F-GRPO lets one LLM jointly generate candidates and rank them by factorizing policy optimization into separate phases with distinct advantages."}],"snapshot_sha256":"0dbd9a6a253db09894895d4c13d27b6bc4e53f14e637762b3f01342e8dd2c1a6"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"53636b18e9bedcc33a89fcdfd91754292b351dd370df35424c9ff5fcdf84d34f"},"paper":{"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","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","cross_cats":[],"headline":"F-GRPO lets one LLM jointly generate candidates and rank them by factorizing policy optimization into separate phases with distinct advantages.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T04:52:33Z","title":"F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking"},"references":{"count":76,"internal_anchors":7,"resolved_work":76,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Ellis, Brian Whitman, and Paul Lamere","work_id":"3fbb6e4b-5eaa-4672-b118-27365be53cc8","year":2011},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Autoregressive search engines: Generating substrings as document identifiers","work_id":"c548f215-b75f-4910-848d-3fe1c6887e1d","year":2022},{"cited_arxiv_id":"","doi":"10.1145/3539597.3570412","is_internal_anchor":false,"ref_index":3,"title":"Generative slate recommendation with reinforcement learning","work_id":"77c5c94e-635e-4641-b5d7-67678c66e18e","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Chang, Claire Cardie, Kianté Brantley, and Thorsten Joachim","work_id":"6a5e62e2-6e43-4821-b297-5869267b9c03","year":2024},{"cited_arxiv_id":"","doi":"10.18653/v1/2022.naacl-main.194","is_internal_anchor":false,"ref_index":5,"title":"URL https://doi.org/10.18653/v1/2022.naa cl-main.194","work_id":"57971df4-d73b-49da-9f92-43d0c13f54c9","year":2022}],"snapshot_sha256":"aff0f130a45adbc22583b2d53d98501c106a20ed972a6a0cc81c55469c4a8199"},"source":{"id":"2605.12995","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:48:31.789661Z","id":"d459ee2b-4a28-4298-8c4a-93e7cced2add","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"F-GRPO lets one LLM jointly generate candidates and rank them by factorizing policy optimization into separate phases with distinct advantages.","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.","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."}},"verdict_id":"d459ee2b-4a28-4298-8c4a-93e7cced2add"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:72a97978e0e5d13ed14ea0ec693344df30cb8db3e37f6ac222232683703656f6","target":"record","created_at":"2026-05-18T03:09:00Z","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":"d2216fd17bd931574c3fd6cab14a6aec7f5ce6e1e6086a96e8b28c009824c5db","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T04:52:33Z","title_canon_sha256":"be1d84642db727b9fd0a96430a0139d17bd727ead19e033275c85103a0863336"},"schema_version":"1.0","source":{"id":"2605.12995","kind":"arxiv","version":1}},"canonical_sha256":"4d1de34eb48b6228ae4fb05b1a627f278c6373f11e9b08af016fb3ae7b8d1b5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d1de34eb48b6228ae4fb05b1a627f278c6373f11e9b08af016fb3ae7b8d1b5f","first_computed_at":"2026-05-18T03:09:00.497587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:00.497587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N2hfVYRG3PZB1Zg21j3rM4yX+Cid5KTw7fQkfs9Pl33GAbSgEoVjQDsU+F8CJ+Uc0tk4IPng6Bes/b6k3qN2BA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:00.498140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12995","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72a97978e0e5d13ed14ea0ec693344df30cb8db3e37f6ac222232683703656f6","sha256:292897bf5d2ebc9d6572ca6758387a9ba4167116bf72a7d2679e2af34114954b"],"state_sha256":"a26da987d05d04dce8d13d1185d855ab4ad34e2e73206f039c8569b13d413958"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"65Aa1+DLH4SHPh3uUbMHjtyLEFf5SDLjnH1DXDXSxaPyFg0GRdvWMEKPBbItNxyCOILpZT48V7bujSHYYChQDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T13:27:15.664695Z","bundle_sha256":"c4ade63276a5893de9c219fb95edd50749707ef05bd682ce5538ecce9b435e8a"}}