{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SENXW4QKD54FFWLWNK54WLVP4Y","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":"20c48d4006b53df902a5664e553348d5a8f339d47629cf2a8e999f1708d5043b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-07T09:51:01Z","title_canon_sha256":"c5d935aedfd899466e8437c3ce0bbbfac217affa428ee367c0221acc70127290"},"schema_version":"1.0","source":{"id":"2606.08543","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08543","created_at":"2026-06-09T01:05:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08543v1","created_at":"2026-06-09T01:05:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08543","created_at":"2026-06-09T01:05:39Z"},{"alias_kind":"pith_short_12","alias_value":"SENXW4QKD54F","created_at":"2026-06-09T01:05:39Z"},{"alias_kind":"pith_short_16","alias_value":"SENXW4QKD54FFWLW","created_at":"2026-06-09T01:05:39Z"},{"alias_kind":"pith_short_8","alias_value":"SENXW4QK","created_at":"2026-06-09T01:05:39Z"}],"graph_snapshots":[{"event_id":"sha256:8dc9cb45981bd2f9a417c790e619017d56108a6c8e1c1ae0f0962349a8ca4373","target":"graph","created_at":"2026-06-09T01:05:39Z","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/2606.08543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) improves large language model reasoning but often suffers from rapid policy-entropy collapse, where the policy prematurely concentrates on narrow high-probability reasoning paths. While global entropy regularization can encourage exploration, uniformly increasing entropy across all token positions is inefficient for long reasoning trajectories, where many tokens are not decision-relevant. We propose Position-Aware Entropy Calibration (PAEC), a token-level entropy-management framework that constructs a soft mask from local top-p entropy and ","authors_text":"Jiayi Zheng, Linjing Li, Shumeng Yang, Yisu Liu, Zhaohui Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-07T09:51:01Z","title":"PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08543","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:b32da082a4aaeb173a647fa0445643d7ce8c177feb87eea0e9ed2d058a533cb4","target":"record","created_at":"2026-06-09T01:05:39Z","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":"20c48d4006b53df902a5664e553348d5a8f339d47629cf2a8e999f1708d5043b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-07T09:51:01Z","title_canon_sha256":"c5d935aedfd899466e8437c3ce0bbbfac217affa428ee367c0221acc70127290"},"schema_version":"1.0","source":{"id":"2606.08543","kind":"arxiv","version":1}},"canonical_sha256":"911b7b720a1f7852d9766abbcb2eafe606f257f1152ee8541f8cc774ecdaf2d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"911b7b720a1f7852d9766abbcb2eafe606f257f1152ee8541f8cc774ecdaf2d6","first_computed_at":"2026-06-09T01:05:39.658230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:39.658230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vqCHC+JBqJkkB9ADdflOOK9DDRDgUzIxsvxuw9XZgEBQUT8o8Emo1UE2NZRl+aC8AyUQQarR+ufIJ8jfMDnpAw==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:39.658647Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08543","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b32da082a4aaeb173a647fa0445643d7ce8c177feb87eea0e9ed2d058a533cb4","sha256:8dc9cb45981bd2f9a417c790e619017d56108a6c8e1c1ae0f0962349a8ca4373"],"state_sha256":"8781a97c49369dd438892f95964eed484ca8379561c0d5a90b4f1d1a5ce19580"}