{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7XLYZ6UQHGOAUWLRFYPEWEVNKD","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":"43f3fb13978a8e150f923b3a597bc8075e50dac3cd6f9ea3091f517605cc38c7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T14:26:05Z","title_canon_sha256":"7538a0988cae31c880280d92e335152f7aa202ac6cdf010322c0384a6c33bbaa"},"schema_version":"1.0","source":{"id":"2606.09961","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09961","created_at":"2026-06-10T00:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09961v1","created_at":"2026-06-10T00:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09961","created_at":"2026-06-10T00:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"7XLYZ6UQHGOA","created_at":"2026-06-10T00:08:35Z"},{"alias_kind":"pith_short_16","alias_value":"7XLYZ6UQHGOAUWLR","created_at":"2026-06-10T00:08:35Z"},{"alias_kind":"pith_short_8","alias_value":"7XLYZ6UQ","created_at":"2026-06-10T00:08:35Z"}],"graph_snapshots":[{"event_id":"sha256:6a5358f4494889f328ac1afbf6921d48d07a90bebb2e39ebbc0ebbcca044f716","target":"graph","created_at":"2026-06-10T00:08:35Z","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/2606.09961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large language models (LLMs) as autonomous agents via reinforcement learning (RL) has enabled frontier models to achieve superhuman performance in long-horizon tasks. However, existing RL algorithms operate at the trajectory level, performing policy optimization only after collecting complete episode rollouts. This coarse-grained approach faces fundamental challenges in multi-turn agent settings where rewards are sparse, delayed, and credit assignment across individual steps is critical. In this work, we propose \\textbf{State-Score-Supervised Policy Optimization (3SPO)}, a novel RL al","authors_text":"Kailing Li, Linhai Zhuo, Tianwen Qian, Yang Jiao, Yu Han, Yulin Dai, Yuqian Fu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T14:26:05Z","title":"3SPO: State-Score-Supervised Policy Optimization for LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09961","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:f3d5c4a55fe4cdcd50aa6633fc50e7b3fbc4811df2d0ea23f113c4e110789439","target":"record","created_at":"2026-06-10T00:08:35Z","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":"43f3fb13978a8e150f923b3a597bc8075e50dac3cd6f9ea3091f517605cc38c7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T14:26:05Z","title_canon_sha256":"7538a0988cae31c880280d92e335152f7aa202ac6cdf010322c0384a6c33bbaa"},"schema_version":"1.0","source":{"id":"2606.09961","kind":"arxiv","version":1}},"canonical_sha256":"fdd78cfa90399c0a59712e1e4b12ad50d8d3675a8a6b1bdc0fb63b8cff0f582e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdd78cfa90399c0a59712e1e4b12ad50d8d3675a8a6b1bdc0fb63b8cff0f582e","first_computed_at":"2026-06-10T00:08:35.130902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T00:08:35.130902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"goEE+Xf27baGYQc4ZSQtaaJZTCrdbZJNenThOTRfUw8dkuq/w0S9mbCNF9BNQx36ECyyy71BPDfDpUAyzLvAAQ==","signature_status":"signed_v1","signed_at":"2026-06-10T00:08:35.131823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09961","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3d5c4a55fe4cdcd50aa6633fc50e7b3fbc4811df2d0ea23f113c4e110789439","sha256:6a5358f4494889f328ac1afbf6921d48d07a90bebb2e39ebbc0ebbcca044f716"],"state_sha256":"5a8816d45a03efdd175cb1f6f5d8c245f9f78a861544c394335b497313f772cc"}