{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RBXLU3BS7YK5RVNJ5PQCGGZMXK","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":"f94cde6da73112c8229888ae48618255b373c4dcdbb5a34d500031599bbeeb60","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T04:01:56Z","title_canon_sha256":"6c4ac6c41f9dac59b0d06fac59b553e42eccfc4fa5ec597f9b25b468131bc33d"},"schema_version":"1.0","source":{"id":"2607.22724","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22724","created_at":"2026-07-28T00:21:51Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22724v1","created_at":"2026-07-28T00:21:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22724","created_at":"2026-07-28T00:21:51Z"},{"alias_kind":"pith_short_12","alias_value":"RBXLU3BS7YK5","created_at":"2026-07-28T00:21:51Z"},{"alias_kind":"pith_short_16","alias_value":"RBXLU3BS7YK5RVNJ","created_at":"2026-07-28T00:21:51Z"},{"alias_kind":"pith_short_8","alias_value":"RBXLU3BS","created_at":"2026-07-28T00:21:51Z"}],"graph_snapshots":[{"event_id":"sha256:b78494590a67e6f659586188305afe3707110dba06a6ed112b20ae872020f649","target":"graph","created_at":"2026-07-28T00:21:51Z","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/2607.22724/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards by comparing trajectories or steps within a group. However, on difficult long-horizon tasks, this comparison can suffer from a sampling imbalance: repeated or low-effect actions dominate the high-probability region of the policy while useful state-changing actions remain under-sampled. This imbalance produces many all-failed rollout groups, where outcome rewards provide no direction for correcting the policy. Together, these effects can form a self-reinforcing credi","authors_text":"Guangfeng Cai, Jun Xu, Kaibing Yang, Lei Feng, Mengyi Liu, Pengwei Chen, Shengtian Yang, Shuo He, Yu Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T04:01:56Z","title":"Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22724","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":"sha256:743a11a52c35f8cdc250d52e58ca5ff8dbaf24af79c7f28a9700f52b70db982c","target":"record","created_at":"2026-07-28T00:21:51Z","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":"f94cde6da73112c8229888ae48618255b373c4dcdbb5a34d500031599bbeeb60","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T04:01:56Z","title_canon_sha256":"6c4ac6c41f9dac59b0d06fac59b553e42eccfc4fa5ec597f9b25b468131bc33d"},"schema_version":"1.0","source":{"id":"2607.22724","kind":"arxiv","version":1}},"canonical_sha256":"886eba6c32fe15d8d5a9ebe0231b2cbaa675df02e6a97ea091ce2e3bae98bd4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"886eba6c32fe15d8d5a9ebe0231b2cbaa675df02e6a97ea091ce2e3bae98bd4c","first_computed_at":"2026-07-28T00:21:51.248925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:21:51.248925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/P5BNF1Ozekprjlx5JAcOiuCLVej/cwWNLoIj4jkJXXtEEnT5Y7qXVFgQ1PBS+GY2V8tPW2y4SbZr8qoE+8KDQ==","signature_status":"signed_v1","signed_at":"2026-07-28T00:21:51.249757Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22724","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:743a11a52c35f8cdc250d52e58ca5ff8dbaf24af79c7f28a9700f52b70db982c","sha256:b78494590a67e6f659586188305afe3707110dba06a6ed112b20ae872020f649"],"state_sha256":"633e7bbfb907b2c358c082fa4599c34eccf11863270988d7457a28fb56063bc4"}