{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VOK4QAPU3ZVQEFIBW55TLR6QOJ","short_pith_number":"pith:VOK4QAPU","canonical_record":{"source":{"id":"2411.00722","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T16:36:14Z","cross_cats_sorted":[],"title_canon_sha256":"637b9b1ce6f640a692a977242946def64928d26782ff87172384b927bc3ff56a","abstract_canon_sha256":"0e79b6e7b7c982ca17396ef4b7698e3a12e9cc630902d3b47d40b3309dd88151"},"schema_version":"1.0"},"canonical_sha256":"ab95c801f4de6b021501b77b35c7d0727d2505153c3650a8863ea21b96288661","source":{"kind":"arxiv","id":"2411.00722","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00722","created_at":"2026-07-05T09:29:47Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00722v1","created_at":"2026-07-05T09:29:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00722","created_at":"2026-07-05T09:29:47Z"},{"alias_kind":"pith_short_12","alias_value":"VOK4QAPU3ZVQ","created_at":"2026-07-05T09:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"VOK4QAPU3ZVQEFIB","created_at":"2026-07-05T09:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"VOK4QAPU","created_at":"2026-07-05T09:29:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VOK4QAPU3ZVQEFIBW55TLR6QOJ","target":"record","payload":{"canonical_record":{"source":{"id":"2411.00722","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T16:36:14Z","cross_cats_sorted":[],"title_canon_sha256":"637b9b1ce6f640a692a977242946def64928d26782ff87172384b927bc3ff56a","abstract_canon_sha256":"0e79b6e7b7c982ca17396ef4b7698e3a12e9cc630902d3b47d40b3309dd88151"},"schema_version":"1.0"},"canonical_sha256":"ab95c801f4de6b021501b77b35c7d0727d2505153c3650a8863ea21b96288661","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:47.226523Z","signature_b64":"QfxexQXk2QANy8QOT87Ghr0+Xk8hkxvagBzwvhGkmH+VgEywXObRUP3acgtUiBZeqd8LCUWRwRLMIhsjCMKBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab95c801f4de6b021501b77b35c7d0727d2505153c3650a8863ea21b96288661","last_reissued_at":"2026-07-05T09:29:47.226043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:47.226043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.00722","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":"2026-07-05T09:29:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VcS0qKz9t0FrHDXi4JEKYcvOwUdtmnVRntW121o7A2CSvbIJMueiARHHOxzomETZjHi3tF+aaihZOHfcnlS4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:59:12.080785Z"},"content_sha256":"8ea0b4bbde245554e2e3503d39653a6e762aeb4928d5012a013f6d45e95955bf","schema_version":"1.0","event_id":"sha256:8ea0b4bbde245554e2e3503d39653a6e762aeb4928d5012a013f6d45e95955bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VOK4QAPU3ZVQEFIBW55TLR6QOJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Token-level Proximal Policy Optimization for Query Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bochen Pang, Chenghua Huang, Dongmei Zhang, Fangkai Yang, Feng Sun, Hao Sun, Jianfeng Liu, Lu Wang, Pu Zhao, Qingwei Lin, Qi Zhang, Saravan Rajmohan, Weiwei Deng, Yaming Yang, Yichen Ouyang, Yuefeng Zhan","submitted_at":"2024-11-01T16:36:14Z","abstract_excerpt":"Query generation is a critical task for web search engines (e.g. Google, Bing) and recommendation systems. Recently, state-of-the-art query generation methods leverage Large Language Models (LLMs) for their strong capabilities in context understanding and text generation. However, they still face challenges in generating high-quality queries in terms of inferring user intent based on their web search interaction history. In this paper, we propose Token-level Proximal Policy Optimization (TPPO), a noval approach designed to empower LLMs perform better in query generation through fine-tuning. TP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00722","kind":"arxiv","version":1},"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/2411.00722/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:29:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7BqjIF6DBtTyJYLKkmqc6hctLUmEEfHLsSe3yqvjQRW9g0m7Ldnq5fvH5Ib3vVbWdJ4Vit5oPFQOc0bIz7XoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:59:12.081668Z"},"content_sha256":"7def1f35d144fa815ee14347f24d4e5cf8dddb482bbb0aabc8737589d4e849ef","schema_version":"1.0","event_id":"sha256:7def1f35d144fa815ee14347f24d4e5cf8dddb482bbb0aabc8737589d4e849ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VOK4QAPU3ZVQEFIBW55TLR6QOJ/bundle.json","state_url":"https://pith.science/pith/VOK4QAPU3ZVQEFIBW55TLR6QOJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VOK4QAPU3ZVQEFIBW55TLR6QOJ/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":"2026-08-07T10:59:12Z","links":{"resolver":"https://pith.science/pith/VOK4QAPU3ZVQEFIBW55TLR6QOJ","bundle":"https://pith.science/pith/VOK4QAPU3ZVQEFIBW55TLR6QOJ/bundle.json","state":"https://pith.science/pith/VOK4QAPU3ZVQEFIBW55TLR6QOJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VOK4QAPU3ZVQEFIBW55TLR6QOJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VOK4QAPU3ZVQEFIBW55TLR6QOJ","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":"0e79b6e7b7c982ca17396ef4b7698e3a12e9cc630902d3b47d40b3309dd88151","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T16:36:14Z","title_canon_sha256":"637b9b1ce6f640a692a977242946def64928d26782ff87172384b927bc3ff56a"},"schema_version":"1.0","source":{"id":"2411.00722","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00722","created_at":"2026-07-05T09:29:47Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00722v1","created_at":"2026-07-05T09:29:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00722","created_at":"2026-07-05T09:29:47Z"},{"alias_kind":"pith_short_12","alias_value":"VOK4QAPU3ZVQ","created_at":"2026-07-05T09:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"VOK4QAPU3ZVQEFIB","created_at":"2026-07-05T09:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"VOK4QAPU","created_at":"2026-07-05T09:29:47Z"}],"graph_snapshots":[{"event_id":"sha256:7def1f35d144fa815ee14347f24d4e5cf8dddb482bbb0aabc8737589d4e849ef","target":"graph","created_at":"2026-07-05T09:29:47Z","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/2411.00722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Query generation is a critical task for web search engines (e.g. Google, Bing) and recommendation systems. Recently, state-of-the-art query generation methods leverage Large Language Models (LLMs) for their strong capabilities in context understanding and text generation. However, they still face challenges in generating high-quality queries in terms of inferring user intent based on their web search interaction history. In this paper, we propose Token-level Proximal Policy Optimization (TPPO), a noval approach designed to empower LLMs perform better in query generation through fine-tuning. TP","authors_text":"Bochen Pang, Chenghua Huang, Dongmei Zhang, Fangkai Yang, Feng Sun, Hao Sun, Jianfeng Liu, Lu Wang, Pu Zhao, Qingwei Lin, Qi Zhang, Saravan Rajmohan, Weiwei Deng, Yaming Yang, Yichen Ouyang, Yuefeng Zhan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T16:36:14Z","title":"Token-level Proximal Policy Optimization for Query Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00722","kind":"arxiv","version":1},"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":"sha256:8ea0b4bbde245554e2e3503d39653a6e762aeb4928d5012a013f6d45e95955bf","target":"record","created_at":"2026-07-05T09:29:47Z","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":"0e79b6e7b7c982ca17396ef4b7698e3a12e9cc630902d3b47d40b3309dd88151","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T16:36:14Z","title_canon_sha256":"637b9b1ce6f640a692a977242946def64928d26782ff87172384b927bc3ff56a"},"schema_version":"1.0","source":{"id":"2411.00722","kind":"arxiv","version":1}},"canonical_sha256":"ab95c801f4de6b021501b77b35c7d0727d2505153c3650a8863ea21b96288661","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab95c801f4de6b021501b77b35c7d0727d2505153c3650a8863ea21b96288661","first_computed_at":"2026-07-05T09:29:47.226043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:47.226043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QfxexQXk2QANy8QOT87Ghr0+Xk8hkxvagBzwvhGkmH+VgEywXObRUP3acgtUiBZeqd8LCUWRwRLMIhsjCMKBAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:47.226523Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.00722","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ea0b4bbde245554e2e3503d39653a6e762aeb4928d5012a013f6d45e95955bf","sha256:7def1f35d144fa815ee14347f24d4e5cf8dddb482bbb0aabc8737589d4e849ef"],"state_sha256":"79c30e54c6cd3d3097c42429cc0a4bd31299a44ee39d4367b667b7bfdec45507"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RHTOclU4TXoovYXLfYIKU+sRUysC7Y9tI5I8kj82jwJH34RQ1mT1I76GWMyN4YAfnQTgiNqe47htQlwz7AHiDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:59:12.088598Z","bundle_sha256":"9d998f9c7fee06ae9e1a91b67e2a2f1d590318939e4fd93c165f5ec4e62d8b47"}}