{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XWL5W5Q5M32NN5GEQQ6LMIT66U","short_pith_number":"pith:XWL5W5Q5","canonical_record":{"source":{"id":"2508.03018","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-05T02:56:58Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"8fc51b292e4451d57979e7f266c436b0d7bf814602865f078b18e606a5177e08","abstract_canon_sha256":"688341a0cc9ea03b9ff4dddd6a36a27e8e43b96c70f5cdf3524056419f0b5706"},"schema_version":"1.0"},"canonical_sha256":"bd97db761d66f4d6f4c4843cb6227ef50cf13be6518942107a71c344f88ec947","source":{"kind":"arxiv","id":"2508.03018","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.03018","created_at":"2026-05-20T00:02:52Z"},{"alias_kind":"arxiv_version","alias_value":"2508.03018v2","created_at":"2026-05-20T00:02:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03018","created_at":"2026-05-20T00:02:52Z"},{"alias_kind":"pith_short_12","alias_value":"XWL5W5Q5M32N","created_at":"2026-05-20T00:02:52Z"},{"alias_kind":"pith_short_16","alias_value":"XWL5W5Q5M32NN5GE","created_at":"2026-05-20T00:02:52Z"},{"alias_kind":"pith_short_8","alias_value":"XWL5W5Q5","created_at":"2026-05-20T00:02:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XWL5W5Q5M32NN5GEQQ6LMIT66U","target":"record","payload":{"canonical_record":{"source":{"id":"2508.03018","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-05T02:56:58Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"8fc51b292e4451d57979e7f266c436b0d7bf814602865f078b18e606a5177e08","abstract_canon_sha256":"688341a0cc9ea03b9ff4dddd6a36a27e8e43b96c70f5cdf3524056419f0b5706"},"schema_version":"1.0"},"canonical_sha256":"bd97db761d66f4d6f4c4843cb6227ef50cf13be6518942107a71c344f88ec947","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:52.496039Z","signature_b64":"lxxucz69RDCa2l2dqn8tgQ5VL+9q8G+WszBO8jBdMG3mvAD7ilm0/thycfyEk0sFWJMsrIgBo92g9MZbFvdFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd97db761d66f4d6f4c4843cb6227ef50cf13be6518942107a71c344f88ec947","last_reissued_at":"2026-05-20T00:02:52.494958Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:52.494958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.03018","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SQJmSfHEG8F2WfsWaXpKSkIFthGjBeDwTrHS54fAhdlicQM/ZHGmdShDUCaOLDGDohuCKRgmH4tDKA9a2LF5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:29:19.793907Z"},"content_sha256":"952fe1fd5bba8bf2fe38c6377576683575c95e61e163de26c937c103fc439a36","schema_version":"1.0","event_id":"sha256:952fe1fd5bba8bf2fe38c6377576683575c95e61e163de26c937c103fc439a36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XWL5W5Q5M32NN5GEQQ6LMIT66U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Baolong Bi, Guillaume Sartoretti, Kaixin Li, Pengliang Ji, Tao Feng, Yutong Wang","submitted_at":"2025-08-05T02:56:58Z","abstract_excerpt":"Large Language Reasoning Models have demonstrated remarkable success on static tasks, yet their application to multi-round agentic planning in interactive environments faces two fundamental challenges. First, the intractable credit assignment problem renders conventional reinforcement learning ineffective in sparse-reward settings. Second, the computational overhead of verbose, step-by-step reasoning histories is prohibitive. To address these challenges, we propose BPO, a three-stage framework (bootstrapping, extrapolation, and refinement) that establishes a self-improving data flywheel to dev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03018","kind":"arxiv","version":2},"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/2508.03018/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":"2026-05-20T00:02:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vkb4erEM6J3Qh9DVFrtxsKFJXgZ4A6tAvLE3Ypm4fvoJkxOPyGYAYQE62niQMInyS6jzVBvNufASvdilXzWvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:29:19.794696Z"},"content_sha256":"8b0ae44a79c8aca72f559a948127e2615f3d20b2d56bb86be640403f116af5aa","schema_version":"1.0","event_id":"sha256:8b0ae44a79c8aca72f559a948127e2615f3d20b2d56bb86be640403f116af5aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XWL5W5Q5M32NN5GEQQ6LMIT66U/bundle.json","state_url":"https://pith.science/pith/XWL5W5Q5M32NN5GEQQ6LMIT66U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XWL5W5Q5M32NN5GEQQ6LMIT66U/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":"2026-05-30T11:29:19Z","links":{"resolver":"https://pith.science/pith/XWL5W5Q5M32NN5GEQQ6LMIT66U","bundle":"https://pith.science/pith/XWL5W5Q5M32NN5GEQQ6LMIT66U/bundle.json","state":"https://pith.science/pith/XWL5W5Q5M32NN5GEQQ6LMIT66U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XWL5W5Q5M32NN5GEQQ6LMIT66U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XWL5W5Q5M32NN5GEQQ6LMIT66U","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":"688341a0cc9ea03b9ff4dddd6a36a27e8e43b96c70f5cdf3524056419f0b5706","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-05T02:56:58Z","title_canon_sha256":"8fc51b292e4451d57979e7f266c436b0d7bf814602865f078b18e606a5177e08"},"schema_version":"1.0","source":{"id":"2508.03018","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.03018","created_at":"2026-05-20T00:02:52Z"},{"alias_kind":"arxiv_version","alias_value":"2508.03018v2","created_at":"2026-05-20T00:02:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03018","created_at":"2026-05-20T00:02:52Z"},{"alias_kind":"pith_short_12","alias_value":"XWL5W5Q5M32N","created_at":"2026-05-20T00:02:52Z"},{"alias_kind":"pith_short_16","alias_value":"XWL5W5Q5M32NN5GE","created_at":"2026-05-20T00:02:52Z"},{"alias_kind":"pith_short_8","alias_value":"XWL5W5Q5","created_at":"2026-05-20T00:02:52Z"}],"graph_snapshots":[{"event_id":"sha256:8b0ae44a79c8aca72f559a948127e2615f3d20b2d56bb86be640403f116af5aa","target":"graph","created_at":"2026-05-20T00:02:52Z","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/2508.03018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Reasoning Models have demonstrated remarkable success on static tasks, yet their application to multi-round agentic planning in interactive environments faces two fundamental challenges. First, the intractable credit assignment problem renders conventional reinforcement learning ineffective in sparse-reward settings. Second, the computational overhead of verbose, step-by-step reasoning histories is prohibitive. To address these challenges, we propose BPO, a three-stage framework (bootstrapping, extrapolation, and refinement) that establishes a self-improving data flywheel to dev","authors_text":"Baolong Bi, Guillaume Sartoretti, Kaixin Li, Pengliang Ji, Tao Feng, Yutong Wang","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-05T02:56:58Z","title":"Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03018","kind":"arxiv","version":2},"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":"sha256:952fe1fd5bba8bf2fe38c6377576683575c95e61e163de26c937c103fc439a36","target":"record","created_at":"2026-05-20T00:02:52Z","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":"688341a0cc9ea03b9ff4dddd6a36a27e8e43b96c70f5cdf3524056419f0b5706","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-05T02:56:58Z","title_canon_sha256":"8fc51b292e4451d57979e7f266c436b0d7bf814602865f078b18e606a5177e08"},"schema_version":"1.0","source":{"id":"2508.03018","kind":"arxiv","version":2}},"canonical_sha256":"bd97db761d66f4d6f4c4843cb6227ef50cf13be6518942107a71c344f88ec947","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd97db761d66f4d6f4c4843cb6227ef50cf13be6518942107a71c344f88ec947","first_computed_at":"2026-05-20T00:02:52.494958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:52.494958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lxxucz69RDCa2l2dqn8tgQ5VL+9q8G+WszBO8jBdMG3mvAD7ilm0/thycfyEk0sFWJMsrIgBo92g9MZbFvdFAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:52.496039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.03018","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:952fe1fd5bba8bf2fe38c6377576683575c95e61e163de26c937c103fc439a36","sha256:8b0ae44a79c8aca72f559a948127e2615f3d20b2d56bb86be640403f116af5aa"],"state_sha256":"34591bef178e795ca79d220f9a8447e49ee31bc1b4508fc46d1f585b78776293"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G4wLNDmBVgWR9SCTV0tkC7zmkP54ii7JL1l2Mw/Xp7JdC+7r+2OBjWYi5NSW7T5pdCCWRvOmJJmJqSBscRPtDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T11:29:19.798605Z","bundle_sha256":"6be54ef6d1bc1de6aefab924f459b0218a08c173468f2b0aa09017c6c454d83b"}}