{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HWNOVPQOQ5BFB7F5NLT4NC3UA3","short_pith_number":"pith:HWNOVPQO","canonical_record":{"source":{"id":"2510.08141","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-09T12:24:08Z","cross_cats_sorted":[],"title_canon_sha256":"fc4761e5b741857de4c8675103220740781e91ffec02818bf92576b4bc66d784","abstract_canon_sha256":"a42179c6f3b856d70f49530dec0b8e1340c4c309cec78030b92420213f96a917"},"schema_version":"1.0"},"canonical_sha256":"3d9aeabe0e874250fcbd6ae7c68b7406f865b5a72cd9cc465d7a096ea3706081","source":{"kind":"arxiv","id":"2510.08141","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.08141","created_at":"2026-05-20T00:05:34Z"},{"alias_kind":"arxiv_version","alias_value":"2510.08141v7","created_at":"2026-05-20T00:05:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.08141","created_at":"2026-05-20T00:05:34Z"},{"alias_kind":"pith_short_12","alias_value":"HWNOVPQOQ5BF","created_at":"2026-05-20T00:05:34Z"},{"alias_kind":"pith_short_16","alias_value":"HWNOVPQOQ5BFB7F5","created_at":"2026-05-20T00:05:34Z"},{"alias_kind":"pith_short_8","alias_value":"HWNOVPQO","created_at":"2026-05-20T00:05:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HWNOVPQOQ5BFB7F5NLT4NC3UA3","target":"record","payload":{"canonical_record":{"source":{"id":"2510.08141","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-09T12:24:08Z","cross_cats_sorted":[],"title_canon_sha256":"fc4761e5b741857de4c8675103220740781e91ffec02818bf92576b4bc66d784","abstract_canon_sha256":"a42179c6f3b856d70f49530dec0b8e1340c4c309cec78030b92420213f96a917"},"schema_version":"1.0"},"canonical_sha256":"3d9aeabe0e874250fcbd6ae7c68b7406f865b5a72cd9cc465d7a096ea3706081","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:34.544447Z","signature_b64":"MxNZz3XwE1H311/tKTKeYXABqddfY3PYFPToEzwH6YMFnZZ3p2uW2XwKLqKU39FIVbUzNOimNKc/R5gWRi1DBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d9aeabe0e874250fcbd6ae7c68b7406f865b5a72cd9cc465d7a096ea3706081","last_reissued_at":"2026-05-20T00:05:34.543640Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:34.543640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.08141","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OguMqUBGZNHd2iE/I7AmgFChBV6vnIF58IWuMuskV7cqEa2BWb5Kqfv2KC0IY6D8xdikiYUVs+a1/104gsNzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T02:34:12.265948Z"},"content_sha256":"79f90fe9752fcf2c279d71e8c27abda66b1ce524e52c24c54f9b05b49feccd3b","schema_version":"1.0","event_id":"sha256:79f90fe9752fcf2c279d71e8c27abda66b1ce524e52c24c54f9b05b49feccd3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HWNOVPQOQ5BFB7F5NLT4NC3UA3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen Wang, Ge Lan, Hexuan Deng, Jionghao Bai, Yue Wang, Zhaochun Li","submitted_at":"2025-10-09T12:24:08Z","abstract_excerpt":"Reinforcement learning (RL) is a key paradigm for post-training large language models (LLMs), but the widely used Group Relative Policy Optimization (GRPO) often suffers from entropy collapse: exploration quickly disappears, policies converge prematurely, and sample diversity declines, ultimately harming training effectiveness. Existing remedies, including entropy bonuses and clip-based methods, rarely keep entropy within a stable exploration regime and often introduce oscillatory entropy or reward degradation. In this work, we identify a previously overlooked asymmetry in entropy dynamics: un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.08141","kind":"arxiv","version":7},"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/2510.08141/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":"2026-05-20T00:05:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0MAJ5c5j8TDi5RUxi1plRpqthZYwQolScicZ85VNnDkqOPISDzcAdmoQ1F/v/O9607QpFoRai2wvDp8ruS/VCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T02:34:12.266561Z"},"content_sha256":"204982c09b2e25dae38eb721add93023f726e2364272bb8338dd587ccb1f9da9","schema_version":"1.0","event_id":"sha256:204982c09b2e25dae38eb721add93023f726e2364272bb8338dd587ccb1f9da9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HWNOVPQOQ5BFB7F5NLT4NC3UA3/bundle.json","state_url":"https://pith.science/pith/HWNOVPQOQ5BFB7F5NLT4NC3UA3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HWNOVPQOQ5BFB7F5NLT4NC3UA3/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":"2026-06-05T02:34:12Z","links":{"resolver":"https://pith.science/pith/HWNOVPQOQ5BFB7F5NLT4NC3UA3","bundle":"https://pith.science/pith/HWNOVPQOQ5BFB7F5NLT4NC3UA3/bundle.json","state":"https://pith.science/pith/HWNOVPQOQ5BFB7F5NLT4NC3UA3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HWNOVPQOQ5BFB7F5NLT4NC3UA3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HWNOVPQOQ5BFB7F5NLT4NC3UA3","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":"a42179c6f3b856d70f49530dec0b8e1340c4c309cec78030b92420213f96a917","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-09T12:24:08Z","title_canon_sha256":"fc4761e5b741857de4c8675103220740781e91ffec02818bf92576b4bc66d784"},"schema_version":"1.0","source":{"id":"2510.08141","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.08141","created_at":"2026-05-20T00:05:34Z"},{"alias_kind":"arxiv_version","alias_value":"2510.08141v7","created_at":"2026-05-20T00:05:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.08141","created_at":"2026-05-20T00:05:34Z"},{"alias_kind":"pith_short_12","alias_value":"HWNOVPQOQ5BF","created_at":"2026-05-20T00:05:34Z"},{"alias_kind":"pith_short_16","alias_value":"HWNOVPQOQ5BFB7F5","created_at":"2026-05-20T00:05:34Z"},{"alias_kind":"pith_short_8","alias_value":"HWNOVPQO","created_at":"2026-05-20T00:05:34Z"}],"graph_snapshots":[{"event_id":"sha256:204982c09b2e25dae38eb721add93023f726e2364272bb8338dd587ccb1f9da9","target":"graph","created_at":"2026-05-20T00:05:34Z","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/2510.08141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is a key paradigm for post-training large language models (LLMs), but the widely used Group Relative Policy Optimization (GRPO) often suffers from entropy collapse: exploration quickly disappears, policies converge prematurely, and sample diversity declines, ultimately harming training effectiveness. Existing remedies, including entropy bonuses and clip-based methods, rarely keep entropy within a stable exploration regime and often introduce oscillatory entropy or reward degradation. In this work, we identify a previously overlooked asymmetry in entropy dynamics: un","authors_text":"Chen Wang, Ge Lan, Hexuan Deng, Jionghao Bai, Yue Wang, Zhaochun Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-09T12:24:08Z","title":"SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.08141","kind":"arxiv","version":7},"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":"sha256:79f90fe9752fcf2c279d71e8c27abda66b1ce524e52c24c54f9b05b49feccd3b","target":"record","created_at":"2026-05-20T00:05:34Z","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":"a42179c6f3b856d70f49530dec0b8e1340c4c309cec78030b92420213f96a917","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-09T12:24:08Z","title_canon_sha256":"fc4761e5b741857de4c8675103220740781e91ffec02818bf92576b4bc66d784"},"schema_version":"1.0","source":{"id":"2510.08141","kind":"arxiv","version":7}},"canonical_sha256":"3d9aeabe0e874250fcbd6ae7c68b7406f865b5a72cd9cc465d7a096ea3706081","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d9aeabe0e874250fcbd6ae7c68b7406f865b5a72cd9cc465d7a096ea3706081","first_computed_at":"2026-05-20T00:05:34.543640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:34.543640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MxNZz3XwE1H311/tKTKeYXABqddfY3PYFPToEzwH6YMFnZZ3p2uW2XwKLqKU39FIVbUzNOimNKc/R5gWRi1DBg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:34.544447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.08141","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79f90fe9752fcf2c279d71e8c27abda66b1ce524e52c24c54f9b05b49feccd3b","sha256:204982c09b2e25dae38eb721add93023f726e2364272bb8338dd587ccb1f9da9"],"state_sha256":"e210b4b4b6212b05e0fb38bf8fb0dfb37fce6307ebcd0d8f3bee53e1d1c9dc13"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ngnmpK4kbjuJtECce4pc4Of0YSJbTYxrrv2C75LYv6kSQxpleKT1kSSe2AYWC/KvhbDyjpkoOmv3MjpSTMNjBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T02:34:12.269248Z","bundle_sha256":"0db43a0915eab6d04473b75906a69c994b63a8a74375ad88ca5d9346ec3653ba"}}