{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:B6NWYACYMFSVGDE5VSXWSIZETI","short_pith_number":"pith:B6NWYACY","canonical_record":{"source":{"id":"2605.27954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T04:47:52Z","cross_cats_sorted":[],"title_canon_sha256":"ad3a2b0781d750985286f9d426eb5a29927dafadcbe6210beb86f485a81c940c","abstract_canon_sha256":"8b732aeab05d64ef90f498524d54dfaabff5e5f1cad589fc535bb4a8ae29d2d7"},"schema_version":"1.0"},"canonical_sha256":"0f9b6c00586165530c9dacaf6923249a37425b265fd8222cca836b37ebc484f4","source":{"kind":"arxiv","id":"2605.27954","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27954","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27954v1","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27954","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"B6NWYACYMFSV","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"B6NWYACYMFSVGDE5","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"B6NWYACY","created_at":"2026-05-28T01:04:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:B6NWYACYMFSVGDE5VSXWSIZETI","target":"record","payload":{"canonical_record":{"source":{"id":"2605.27954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T04:47:52Z","cross_cats_sorted":[],"title_canon_sha256":"ad3a2b0781d750985286f9d426eb5a29927dafadcbe6210beb86f485a81c940c","abstract_canon_sha256":"8b732aeab05d64ef90f498524d54dfaabff5e5f1cad589fc535bb4a8ae29d2d7"},"schema_version":"1.0"},"canonical_sha256":"0f9b6c00586165530c9dacaf6923249a37425b265fd8222cca836b37ebc484f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:54.019747Z","signature_b64":"SHo+EIGPd1Q849lJyEKx0iUvoMvpT5vSHMJLuoF63uIj78lOjyLX58RClP5Mci2/Ozfx55I9Vy/kLBLK1OHRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f9b6c00586165530c9dacaf6923249a37425b265fd8222cca836b37ebc484f4","last_reissued_at":"2026-05-28T01:04:54.019247Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:54.019247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.27954","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fH7apW0suMYR9oskPQVdyfhZFztxX1gZpXwBbZomiDU3DW12D7fWqLVdeOzMyWHb71wdQ0ffToqTtaJneB+eAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T21:06:25.071005Z"},"content_sha256":"a456f82755f45c4b556a589975440e909b55397d4c8ef3c0bbf702e8d09d079c","schema_version":"1.0","event_id":"sha256:a456f82755f45c4b556a589975440e909b55397d4c8ef3c0bbf702e8d09d079c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:B6NWYACYMFSVGDE5VSXWSIZETI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cyclical Entropy Eruption: Entropy Dynamics in Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Sharon Li, Shawn Im, Wendi Li","submitted_at":"2026-05-27T04:47:52Z","abstract_excerpt":"Agentic large language models are increasingly used to solve real-world tasks by reasoning over goals, invoking tools, and interacting with external environments. Reinforcement learning provides a natural framework for improving these behaviors, and recent agent RL methods have achieved strong results across domains. However, the training dynamics of agent RL remain poorly understood, limiting our ability to diagnose instabilities and design more effective training algorithms. In this work, we identify a previously underexplored phenomenon in agent RL, which we term cyclical entropy eruption. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27954","kind":"arxiv","version":1},"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/2605.27954/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":"2026-05-28T01:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ASHd7WwyR1bGe3hO+YjSjZN7ZVtzKAlKUeonu30i3NaNpzafVbKXOvyWK0HZZj9VTFDG1Dyfj0YRBkuHAVmYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T21:06:25.071969Z"},"content_sha256":"1694cc697039ddbac536c4ab2fd81c082edbe17773cc354629a42aa7bd2c5d9b","schema_version":"1.0","event_id":"sha256:1694cc697039ddbac536c4ab2fd81c082edbe17773cc354629a42aa7bd2c5d9b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B6NWYACYMFSVGDE5VSXWSIZETI/bundle.json","state_url":"https://pith.science/pith/B6NWYACYMFSVGDE5VSXWSIZETI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B6NWYACYMFSVGDE5VSXWSIZETI/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":"2026-05-31T21:06:25Z","links":{"resolver":"https://pith.science/pith/B6NWYACYMFSVGDE5VSXWSIZETI","bundle":"https://pith.science/pith/B6NWYACYMFSVGDE5VSXWSIZETI/bundle.json","state":"https://pith.science/pith/B6NWYACYMFSVGDE5VSXWSIZETI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B6NWYACYMFSVGDE5VSXWSIZETI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:B6NWYACYMFSVGDE5VSXWSIZETI","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":"8b732aeab05d64ef90f498524d54dfaabff5e5f1cad589fc535bb4a8ae29d2d7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T04:47:52Z","title_canon_sha256":"ad3a2b0781d750985286f9d426eb5a29927dafadcbe6210beb86f485a81c940c"},"schema_version":"1.0","source":{"id":"2605.27954","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27954","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27954v1","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27954","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"B6NWYACYMFSV","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"B6NWYACYMFSVGDE5","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"B6NWYACY","created_at":"2026-05-28T01:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:1694cc697039ddbac536c4ab2fd81c082edbe17773cc354629a42aa7bd2c5d9b","target":"graph","created_at":"2026-05-28T01:04:54Z","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/2605.27954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agentic large language models are increasingly used to solve real-world tasks by reasoning over goals, invoking tools, and interacting with external environments. Reinforcement learning provides a natural framework for improving these behaviors, and recent agent RL methods have achieved strong results across domains. However, the training dynamics of agent RL remain poorly understood, limiting our ability to diagnose instabilities and design more effective training algorithms. In this work, we identify a previously underexplored phenomenon in agent RL, which we term cyclical entropy eruption. ","authors_text":"Sharon Li, Shawn Im, Wendi Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T04:47:52Z","title":"Cyclical Entropy Eruption: Entropy Dynamics in Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27954","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:a456f82755f45c4b556a589975440e909b55397d4c8ef3c0bbf702e8d09d079c","target":"record","created_at":"2026-05-28T01:04:54Z","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":"8b732aeab05d64ef90f498524d54dfaabff5e5f1cad589fc535bb4a8ae29d2d7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T04:47:52Z","title_canon_sha256":"ad3a2b0781d750985286f9d426eb5a29927dafadcbe6210beb86f485a81c940c"},"schema_version":"1.0","source":{"id":"2605.27954","kind":"arxiv","version":1}},"canonical_sha256":"0f9b6c00586165530c9dacaf6923249a37425b265fd8222cca836b37ebc484f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f9b6c00586165530c9dacaf6923249a37425b265fd8222cca836b37ebc484f4","first_computed_at":"2026-05-28T01:04:54.019247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:54.019247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SHo+EIGPd1Q849lJyEKx0iUvoMvpT5vSHMJLuoF63uIj78lOjyLX58RClP5Mci2/Ozfx55I9Vy/kLBLK1OHRBA==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:54.019747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27954","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a456f82755f45c4b556a589975440e909b55397d4c8ef3c0bbf702e8d09d079c","sha256:1694cc697039ddbac536c4ab2fd81c082edbe17773cc354629a42aa7bd2c5d9b"],"state_sha256":"0b16157fc6ac4973c02ec702040e94280e3cabec7701e900b3fb1f217ae2c7ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+QNLXlGBhI5z/ymiZ/2DlhK/rWw1DHE01xF0hbTlRZTCSV/luDpOcK+/xQ96xQuFMi4rZY3MjjQAskJSru+RAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T21:06:25.077006Z","bundle_sha256":"205da50f5a4b377b3ce06f2f82cf5530f6d878c9db28734ea6f403df825c5566"}}