{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZU2Y5F6BHIT4UHFAK6L7AZ72VP","short_pith_number":"pith:ZU2Y5F6B","canonical_record":{"source":{"id":"2508.17445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-24T16:52:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"36adbca1dd0761f7af141be1cff02afe16fc3a1575557a00f9401583f9fd6b22","abstract_canon_sha256":"d988675c28f314ec8e4ffbcb31278a402427f5ecd7a4952691be402b39956301"},"schema_version":"1.0"},"canonical_sha256":"cd358e97c13a27ca1ca05797f067faabf1915e30f6cf33165105b4226ed7ea1c","source":{"kind":"arxiv","id":"2508.17445","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17445","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17445v1","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17445","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZU2Y5F6BHIT4","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZU2Y5F6BHIT4UHFA","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZU2Y5F6B","created_at":"2026-07-05T11:58:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZU2Y5F6BHIT4UHFAK6L7AZ72VP","target":"record","payload":{"canonical_record":{"source":{"id":"2508.17445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-24T16:52:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"36adbca1dd0761f7af141be1cff02afe16fc3a1575557a00f9401583f9fd6b22","abstract_canon_sha256":"d988675c28f314ec8e4ffbcb31278a402427f5ecd7a4952691be402b39956301"},"schema_version":"1.0"},"canonical_sha256":"cd358e97c13a27ca1ca05797f067faabf1915e30f6cf33165105b4226ed7ea1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:41.654105Z","signature_b64":"w8DBBg8EU7fcZ6LK4RtsIWFpR8wH0jedPKCrTYgcyDxA2Ic+LCxoNC+SaLPCy9PCYXFSxRLwRbVnM+iq4eMDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd358e97c13a27ca1ca05797f067faabf1915e30f6cf33165105b4226ed7ea1c","last_reissued_at":"2026-07-05T11:58:41.653627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:41.653627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.17445","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":"2026-07-05T11:58:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sXvZeUCUCUIpAgPu0FpOHp2cVqAuL6hcNbqoT32l7/jCHbD/wTMLJfyHz9H4AByumpyCs2NJ0uJmT9rQw0u6Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:36:05.187793Z"},"content_sha256":"ced64f0448896a1d6356176550bba9337b76c41f1d62df2857564afdb4c67bd5","schema_version":"1.0","event_id":"sha256:ced64f0448896a1d6356176550bba9337b76c41f1d62df2857564afdb4c67bd5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZU2Y5F6BHIT4UHFAK6L7AZ72VP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Chenghua Lin, Ge Zhang, Jian Yang, Qian Liu, Qingshui Gu, Shuyue Guo, Tianshun Xing, Tianyu Zheng, Wangchunshu Zhou, Wei Shen, Wenhao Huang, Xingwei Qu, Xin Zhou, Yizhi Li, Zheng Zhang, Zhoufutu Wen, Ziniu Li","submitted_at":"2025-08-24T16:52:37Z","abstract_excerpt":"Recent advancements in aligning large language models via reinforcement learning have achieved remarkable gains in solving complex reasoning problems, but at the cost of expensive on-policy rollouts and limited exploration of diverse reasoning paths. In this work, we introduce TreePO, involving a self-guided rollout algorithm that views sequence generation as a tree-structured searching process. Composed of dynamic tree sampling policy and fixed-length segment decoding, TreePO leverages local uncertainty to warrant additional branches. By amortizing computation across common prefixes and pruni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17445","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/2508.17445/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":"2026-07-05T11:58:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q0TLs8DvoURrV0SBWwxTSu6p/z5X1DVOydTeeTKZ7872OHi62J2c0rbVybUlbnNF1TbrdGSCrYssep2N1C6pDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:36:05.188400Z"},"content_sha256":"b7bb2291b84bcb21b1d4d13157a1bdd843448915fb26d52339d579ba62b38e09","schema_version":"1.0","event_id":"sha256:b7bb2291b84bcb21b1d4d13157a1bdd843448915fb26d52339d579ba62b38e09"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZU2Y5F6BHIT4UHFAK6L7AZ72VP/bundle.json","state_url":"https://pith.science/pith/ZU2Y5F6BHIT4UHFAK6L7AZ72VP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZU2Y5F6BHIT4UHFAK6L7AZ72VP/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":"2026-08-05T12:36:05Z","links":{"resolver":"https://pith.science/pith/ZU2Y5F6BHIT4UHFAK6L7AZ72VP","bundle":"https://pith.science/pith/ZU2Y5F6BHIT4UHFAK6L7AZ72VP/bundle.json","state":"https://pith.science/pith/ZU2Y5F6BHIT4UHFAK6L7AZ72VP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZU2Y5F6BHIT4UHFAK6L7AZ72VP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZU2Y5F6BHIT4UHFAK6L7AZ72VP","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":"d988675c28f314ec8e4ffbcb31278a402427f5ecd7a4952691be402b39956301","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-24T16:52:37Z","title_canon_sha256":"36adbca1dd0761f7af141be1cff02afe16fc3a1575557a00f9401583f9fd6b22"},"schema_version":"1.0","source":{"id":"2508.17445","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17445","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17445v1","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17445","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZU2Y5F6BHIT4","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZU2Y5F6BHIT4UHFA","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZU2Y5F6B","created_at":"2026-07-05T11:58:41Z"}],"graph_snapshots":[{"event_id":"sha256:b7bb2291b84bcb21b1d4d13157a1bdd843448915fb26d52339d579ba62b38e09","target":"graph","created_at":"2026-07-05T11:58:41Z","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/2508.17445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in aligning large language models via reinforcement learning have achieved remarkable gains in solving complex reasoning problems, but at the cost of expensive on-policy rollouts and limited exploration of diverse reasoning paths. In this work, we introduce TreePO, involving a self-guided rollout algorithm that views sequence generation as a tree-structured searching process. Composed of dynamic tree sampling policy and fixed-length segment decoding, TreePO leverages local uncertainty to warrant additional branches. By amortizing computation across common prefixes and pruni","authors_text":"Chenghua Lin, Ge Zhang, Jian Yang, Qian Liu, Qingshui Gu, Shuyue Guo, Tianshun Xing, Tianyu Zheng, Wangchunshu Zhou, Wei Shen, Wenhao Huang, Xingwei Qu, Xin Zhou, Yizhi Li, Zheng Zhang, Zhoufutu Wen, Ziniu Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-24T16:52:37Z","title":"TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17445","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:ced64f0448896a1d6356176550bba9337b76c41f1d62df2857564afdb4c67bd5","target":"record","created_at":"2026-07-05T11:58:41Z","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":"d988675c28f314ec8e4ffbcb31278a402427f5ecd7a4952691be402b39956301","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-24T16:52:37Z","title_canon_sha256":"36adbca1dd0761f7af141be1cff02afe16fc3a1575557a00f9401583f9fd6b22"},"schema_version":"1.0","source":{"id":"2508.17445","kind":"arxiv","version":1}},"canonical_sha256":"cd358e97c13a27ca1ca05797f067faabf1915e30f6cf33165105b4226ed7ea1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd358e97c13a27ca1ca05797f067faabf1915e30f6cf33165105b4226ed7ea1c","first_computed_at":"2026-07-05T11:58:41.653627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:41.653627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w8DBBg8EU7fcZ6LK4RtsIWFpR8wH0jedPKCrTYgcyDxA2Ic+LCxoNC+SaLPCy9PCYXFSxRLwRbVnM+iq4eMDDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:41.654105Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.17445","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ced64f0448896a1d6356176550bba9337b76c41f1d62df2857564afdb4c67bd5","sha256:b7bb2291b84bcb21b1d4d13157a1bdd843448915fb26d52339d579ba62b38e09"],"state_sha256":"0ee8519f17af84869f210cb593418e66cdd685dc2d450eafcada2f7353c06d23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cx28N6IAlKbaSfYLruTBGNjtol1wzi/sdZ7NJVQ8PYjJjfjZbHGtrBeYYTA4sHykwajWeraD9PzrLXLhNIvgDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:36:05.194394Z","bundle_sha256":"3bca514279de61037fbce859168763c8f9a6491f90567b53600691f9e287e5f5"}}