{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S6N4QQHGUBTQN7K6E3GMQFDX7K","short_pith_number":"pith:S6N4QQHG","schema_version":"1.0","canonical_sha256":"979bc840e6a06706fd5e26ccc81477fabf51c10ace43c250ccbb6428d540a433","source":{"kind":"arxiv","id":"2506.16114","version":3},"attestation_state":"computed","paper":{"title":"GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bo Zheng, Chuan Yu, Feng Li, Jian Xu, Jinyu Lu, Pengjie Wang, Qidong Liu, Shengyu Zhou, Wenlin Zhang, Xiangyu Zhao, Xinhang Li, Yejing Wang","submitted_at":"2025-06-19T08:04:31Z","abstract_excerpt":"Generative recommendations (GR), which usually include item tokenizers and generative Large Language Models (LLMs), have demonstrated remarkable success across a wide range of scenarios. The majority of existing research efforts primarily concentrate on developing powerful item tokenizers or advancing LLM decoding strategies to attain superior performance. However, the critical fine-tuning step in GR frameworks, which is essential for adapting LLMs to recommendation data, remains largely unexplored. Current approaches predominantly rely on either the next-token prediction loss of supervised fi"},"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":"2506.16114","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-19T08:04:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cf68956917c7f7254d8b9ef7b9c6fe7c8859ba44ea9ef904fb48e803951deecf","abstract_canon_sha256":"000c2dba0ab99d8f2bb2399fea9823aa58115610fe19311a634f696e60c0cc86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:33.067883Z","signature_b64":"ptOcw8/T9qphD4EYi7mpanVWA0E6KzubadRoHImyvZ0DMu+7UghcItgl+Sv/tpo9+S8OSeD/QNiu+z6xGNbODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"979bc840e6a06706fd5e26ccc81477fabf51c10ace43c250ccbb6428d540a433","last_reissued_at":"2026-06-02T03:04:33.067409Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:33.067409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bo Zheng, Chuan Yu, Feng Li, Jian Xu, Jinyu Lu, Pengjie Wang, Qidong Liu, Shengyu Zhou, Wenlin Zhang, Xiangyu Zhao, Xinhang Li, Yejing Wang","submitted_at":"2025-06-19T08:04:31Z","abstract_excerpt":"Generative recommendations (GR), which usually include item tokenizers and generative Large Language Models (LLMs), have demonstrated remarkable success across a wide range of scenarios. The majority of existing research efforts primarily concentrate on developing powerful item tokenizers or advancing LLM decoding strategies to attain superior performance. However, the critical fine-tuning step in GR frameworks, which is essential for adapting LLMs to recommendation data, remains largely unexplored. Current approaches predominantly rely on either the next-token prediction loss of supervised fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16114","kind":"arxiv","version":3},"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/2506.16114/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":"2506.16114","created_at":"2026-06-02T03:04:33.067470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16114v3","created_at":"2026-06-02T03:04:33.067470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16114","created_at":"2026-06-02T03:04:33.067470+00:00"},{"alias_kind":"pith_short_12","alias_value":"S6N4QQHGUBTQ","created_at":"2026-06-02T03:04:33.067470+00:00"},{"alias_kind":"pith_short_16","alias_value":"S6N4QQHGUBTQN7K6","created_at":"2026-06-02T03:04:33.067470+00:00"},{"alias_kind":"pith_short_8","alias_value":"S6N4QQHG","created_at":"2026-06-02T03:04:33.067470+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.23156","citing_title":"Birds of a Feather Cluster Nearby: a Proximity-Aware Geo-Codebook for Local Service Recommendation","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S6N4QQHGUBTQN7K6E3GMQFDX7K","json":"https://pith.science/pith/S6N4QQHGUBTQN7K6E3GMQFDX7K.json","graph_json":"https://pith.science/api/pith-number/S6N4QQHGUBTQN7K6E3GMQFDX7K/graph.json","events_json":"https://pith.science/api/pith-number/S6N4QQHGUBTQN7K6E3GMQFDX7K/events.json","paper":"https://pith.science/paper/S6N4QQHG"},"agent_actions":{"view_html":"https://pith.science/pith/S6N4QQHGUBTQN7K6E3GMQFDX7K","download_json":"https://pith.science/pith/S6N4QQHGUBTQN7K6E3GMQFDX7K.json","view_paper":"https://pith.science/paper/S6N4QQHG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16114&json=true","fetch_graph":"https://pith.science/api/pith-number/S6N4QQHGUBTQN7K6E3GMQFDX7K/graph.json","fetch_events":"https://pith.science/api/pith-number/S6N4QQHGUBTQN7K6E3GMQFDX7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S6N4QQHGUBTQN7K6E3GMQFDX7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S6N4QQHGUBTQN7K6E3GMQFDX7K/action/storage_attestation","attest_author":"https://pith.science/pith/S6N4QQHGUBTQN7K6E3GMQFDX7K/action/author_attestation","sign_citation":"https://pith.science/pith/S6N4QQHGUBTQN7K6E3GMQFDX7K/action/citation_signature","submit_replication":"https://pith.science/pith/S6N4QQHGUBTQN7K6E3GMQFDX7K/action/replication_record"}},"created_at":"2026-06-02T03:04:33.067470+00:00","updated_at":"2026-06-02T03:04:33.067470+00:00"}