{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MALOSAX6RCTT6S3WPUZSX4IDQM","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":"93abc1549528391d582922cabb66e64462ec97d7b2c6e4c35f36721ec2c53515","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-08T12:29:23Z","title_canon_sha256":"653153150e1c99b7456aae9b55216e860e19d0866111af553e71d6c5f7f16c4b"},"schema_version":"1.0","source":{"id":"2607.16206","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16206","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16206v1","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16206","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"pith_short_12","alias_value":"MALOSAX6RCTT","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"pith_short_16","alias_value":"MALOSAX6RCTT6S3W","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"pith_short_8","alias_value":"MALOSAX6","created_at":"2026-07-21T00:20:05Z"}],"graph_snapshots":[{"event_id":"sha256:b4c624f1ea6d8e66fcc7150130d6a137dbeac4f8a77c2a91c4ccefdfe4e0821a","target":"graph","created_at":"2026-07-21T00:20:05Z","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/2607.16206/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces PPO-HSC (Proximal Policy Optimization with High-order Sampling Coverage), an exploratory reinforcement learning framework designed to address the \"Invisible Shackles\" of mode collapse in Large Language Model (LLM) fine-tuning. While standard Reinforcement Learning from Verifiable Rewards (RLVR) effectively reinforces high-reward trajectories, it often leads models to over-optimize known solutions, sacrificing curiosity and the ability to explore broader solution manifolds. To overcome this, PPO-HSC incorporates a High-order Sampling Coverage (HSC) reward that incentivizes","authors_text":"Haowen Chen, Yujie Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-08T12:29:23Z","title":"PPO-HSC: An Exploratory Reinforcement Learning Framework Based on Wide-Area Policy Coverage Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16206","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":"sha256:556bf6212751585555aeb78bc1c63a434646e9a74efd86af43d8146175743237","target":"record","created_at":"2026-07-21T00:20:05Z","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":"93abc1549528391d582922cabb66e64462ec97d7b2c6e4c35f36721ec2c53515","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-08T12:29:23Z","title_canon_sha256":"653153150e1c99b7456aae9b55216e860e19d0866111af553e71d6c5f7f16c4b"},"schema_version":"1.0","source":{"id":"2607.16206","kind":"arxiv","version":1}},"canonical_sha256":"6016e902fe88a73f4b767d332bf103833b0df4092b050eedf967bf3f181b54ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6016e902fe88a73f4b767d332bf103833b0df4092b050eedf967bf3f181b54ad","first_computed_at":"2026-07-21T00:20:05.701174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T00:20:05.701174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M+VL3l+gTN8d8F5TCVft2vLmqE5Dk/M1XuXpLKLCo0kc4Gy2zRoVRtjhbHGVrRuqgwG/TQ8S2W1SBHBj25AXCA==","signature_status":"signed_v1","signed_at":"2026-07-21T00:20:05.702173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16206","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:556bf6212751585555aeb78bc1c63a434646e9a74efd86af43d8146175743237","sha256:b4c624f1ea6d8e66fcc7150130d6a137dbeac4f8a77c2a91c4ccefdfe4e0821a"],"state_sha256":"c6bebb90e7e46ca219c61f4525234017cf26cc3fa116672d59ac8ab873c7469b"}