{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NGLFOP6NQU4CULTREQ4KXYIJYN","short_pith_number":"pith:NGLFOP6N","canonical_record":{"source":{"id":"2605.21801","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T22:59:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"06ea4005ef8e27828a8e33159f9539eb0a99a19ea1a781cc2202015cf4f9e029","abstract_canon_sha256":"5dc550f8b682bbe3c305364f9929985dd2f06f7bfb3fa9c793901bc1b2a364e2"},"schema_version":"1.0"},"canonical_sha256":"6996573fcd85382a2e712438abe109c342b571354977b8e2657317aaeb036136","source":{"kind":"arxiv","id":"2605.21801","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21801","created_at":"2026-05-22T01:03:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21801v1","created_at":"2026-05-22T01:03:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21801","created_at":"2026-05-22T01:03:33Z"},{"alias_kind":"pith_short_12","alias_value":"NGLFOP6NQU4C","created_at":"2026-05-22T01:03:33Z"},{"alias_kind":"pith_short_16","alias_value":"NGLFOP6NQU4CULTR","created_at":"2026-05-22T01:03:33Z"},{"alias_kind":"pith_short_8","alias_value":"NGLFOP6N","created_at":"2026-05-22T01:03:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NGLFOP6NQU4CULTREQ4KXYIJYN","target":"record","payload":{"canonical_record":{"source":{"id":"2605.21801","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T22:59:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"06ea4005ef8e27828a8e33159f9539eb0a99a19ea1a781cc2202015cf4f9e029","abstract_canon_sha256":"5dc550f8b682bbe3c305364f9929985dd2f06f7bfb3fa9c793901bc1b2a364e2"},"schema_version":"1.0"},"canonical_sha256":"6996573fcd85382a2e712438abe109c342b571354977b8e2657317aaeb036136","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:33.109352Z","signature_b64":"tLG96ZCDKc2jGk3ipdPLYPItYMbP7C8HvC8R9xLkA/CtjmC9HJgmPFIjkFUHGE0Z6dCgBX9rzfpgs+Uey8V6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6996573fcd85382a2e712438abe109c342b571354977b8e2657317aaeb036136","last_reissued_at":"2026-05-22T01:03:33.108838Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:33.108838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.21801","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":"2026-05-22T01:03:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h401n5WKwKxYGdEFCJyqPd5mIqaxfBgyp1cudD+fZyJ9GlH/1bWs6KEYnHCL10BtA1ZVzpAWLfc6dZQBG1odCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T17:28:25.940290Z"},"content_sha256":"0470e9626d8308a1381b55ac2d14d5b308c16c483ca49e3d682592201f58bb61","schema_version":"1.0","event_id":"sha256:0470e9626d8308a1381b55ac2d14d5b308c16c483ca49e3d682592201f58bb61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NGLFOP6NQU4CULTREQ4KXYIJYN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Han Bao, Kaiwen Shi, Tianyi Ma, Yanfang Ye, Zehong Wang, Zheyuan Zhang","submitted_at":"2026-05-20T22:59:02Z","abstract_excerpt":"Post-training has become central to improving reasoning and alignment in large language models, where critic-free models enable scalable learning from model-generated outputs but lack principled mechanisms to distinguish informative from noisy signals. Recent approaches leverage response-level measures as uncertainty signals to regulate group-based optimization methods such as GRPO. Yet their empirical success remains unstable and unclear in how they influence optimization dynamics. In this paper, we provide, to our knowledge, the first principled formulation that interprets uncertainty signal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21801","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/2605.21801/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":"2026-05-22T01:03:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/CxmDQV7oM2pKa8MxN4wQTj9zLWZzpC7WstqZyQU+ipWOs2tCsMT1zQDHZx6Ef3TUOFWOhuVoY9jXsZTsDUrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T17:28:25.941029Z"},"content_sha256":"e5df0cf76271bfa601ce7184dc9237b56fab958a09297a700ba9092b657afd49","schema_version":"1.0","event_id":"sha256:e5df0cf76271bfa601ce7184dc9237b56fab958a09297a700ba9092b657afd49"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NGLFOP6NQU4CULTREQ4KXYIJYN/bundle.json","state_url":"https://pith.science/pith/NGLFOP6NQU4CULTREQ4KXYIJYN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NGLFOP6NQU4CULTREQ4KXYIJYN/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":"2026-05-23T17:28:25Z","links":{"resolver":"https://pith.science/pith/NGLFOP6NQU4CULTREQ4KXYIJYN","bundle":"https://pith.science/pith/NGLFOP6NQU4CULTREQ4KXYIJYN/bundle.json","state":"https://pith.science/pith/NGLFOP6NQU4CULTREQ4KXYIJYN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NGLFOP6NQU4CULTREQ4KXYIJYN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NGLFOP6NQU4CULTREQ4KXYIJYN","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":"5dc550f8b682bbe3c305364f9929985dd2f06f7bfb3fa9c793901bc1b2a364e2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T22:59:02Z","title_canon_sha256":"06ea4005ef8e27828a8e33159f9539eb0a99a19ea1a781cc2202015cf4f9e029"},"schema_version":"1.0","source":{"id":"2605.21801","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21801","created_at":"2026-05-22T01:03:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21801v1","created_at":"2026-05-22T01:03:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21801","created_at":"2026-05-22T01:03:33Z"},{"alias_kind":"pith_short_12","alias_value":"NGLFOP6NQU4C","created_at":"2026-05-22T01:03:33Z"},{"alias_kind":"pith_short_16","alias_value":"NGLFOP6NQU4CULTR","created_at":"2026-05-22T01:03:33Z"},{"alias_kind":"pith_short_8","alias_value":"NGLFOP6N","created_at":"2026-05-22T01:03:33Z"}],"graph_snapshots":[{"event_id":"sha256:e5df0cf76271bfa601ce7184dc9237b56fab958a09297a700ba9092b657afd49","target":"graph","created_at":"2026-05-22T01:03:33Z","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/2605.21801/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training has become central to improving reasoning and alignment in large language models, where critic-free models enable scalable learning from model-generated outputs but lack principled mechanisms to distinguish informative from noisy signals. Recent approaches leverage response-level measures as uncertainty signals to regulate group-based optimization methods such as GRPO. Yet their empirical success remains unstable and unclear in how they influence optimization dynamics. In this paper, we provide, to our knowledge, the first principled formulation that interprets uncertainty signal","authors_text":"Han Bao, Kaiwen Shi, Tianyi Ma, Yanfang Ye, Zehong Wang, Zheyuan Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T22:59:02Z","title":"Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21801","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":"sha256:0470e9626d8308a1381b55ac2d14d5b308c16c483ca49e3d682592201f58bb61","target":"record","created_at":"2026-05-22T01:03:33Z","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":"5dc550f8b682bbe3c305364f9929985dd2f06f7bfb3fa9c793901bc1b2a364e2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T22:59:02Z","title_canon_sha256":"06ea4005ef8e27828a8e33159f9539eb0a99a19ea1a781cc2202015cf4f9e029"},"schema_version":"1.0","source":{"id":"2605.21801","kind":"arxiv","version":1}},"canonical_sha256":"6996573fcd85382a2e712438abe109c342b571354977b8e2657317aaeb036136","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6996573fcd85382a2e712438abe109c342b571354977b8e2657317aaeb036136","first_computed_at":"2026-05-22T01:03:33.108838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:33.108838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tLG96ZCDKc2jGk3ipdPLYPItYMbP7C8HvC8R9xLkA/CtjmC9HJgmPFIjkFUHGE0Z6dCgBX9rzfpgs+Uey8V6DA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:33.109352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21801","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0470e9626d8308a1381b55ac2d14d5b308c16c483ca49e3d682592201f58bb61","sha256:e5df0cf76271bfa601ce7184dc9237b56fab958a09297a700ba9092b657afd49"],"state_sha256":"4e9f4f8b8f36830420d1c2aa73aa3aed67f0145b37a6bab3bb8658cfe242d8a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K5kHI5KIpVJrwfxpLQKadGdLc9TFqZVk4M2wpR4R9nS5OoMT6CkgB1+7By1YP2PYw/ZTzLm4/4M1nN08oSlfBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T17:28:25.945078Z","bundle_sha256":"3edab95e91fbb7ee109e0832fd02ce2d7092c4e3dc1d0645643d6818b1ca25cc"}}