{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FNKBILTQR3KMYOYTFHJKP6UNXA","short_pith_number":"pith:FNKBILTQ","canonical_record":{"source":{"id":"2608.00301","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T21:31:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0db57c36df70a20447f6d8038419df64d9f35ec6768c3bbe1fc06a09d3148309","abstract_canon_sha256":"2e2057b4249a1c94afa7a1f2c633fa9791c7a932e1774dbf97aa10faab0acbc0"},"schema_version":"1.0"},"canonical_sha256":"2b54142e708ed4cc3b1329d2a7fa8db80bfbddfd174df1f39e9ff090192ad5f1","source":{"kind":"arxiv","id":"2608.00301","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00301","created_at":"2026-08-04T00:35:00Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00301v1","created_at":"2026-08-04T00:35:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00301","created_at":"2026-08-04T00:35:00Z"},{"alias_kind":"pith_short_12","alias_value":"FNKBILTQR3KM","created_at":"2026-08-04T00:35:00Z"},{"alias_kind":"pith_short_16","alias_value":"FNKBILTQR3KMYOYT","created_at":"2026-08-04T00:35:00Z"},{"alias_kind":"pith_short_8","alias_value":"FNKBILTQ","created_at":"2026-08-04T00:35:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FNKBILTQR3KMYOYTFHJKP6UNXA","target":"record","payload":{"canonical_record":{"source":{"id":"2608.00301","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T21:31:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0db57c36df70a20447f6d8038419df64d9f35ec6768c3bbe1fc06a09d3148309","abstract_canon_sha256":"2e2057b4249a1c94afa7a1f2c633fa9791c7a932e1774dbf97aa10faab0acbc0"},"schema_version":"1.0"},"canonical_sha256":"2b54142e708ed4cc3b1329d2a7fa8db80bfbddfd174df1f39e9ff090192ad5f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:35:00.344603Z","signature_b64":"D2q1pcHJ38lI9kfIS5DbCXK8s0exXhnmPOsU4PXxX+Kts2tL2edKmifSVpDsqcoQZuuYuZt94RjRY0BLprl1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b54142e708ed4cc3b1329d2a7fa8db80bfbddfd174df1f39e9ff090192ad5f1","last_reissued_at":"2026-08-04T00:35:00.343178Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:35:00.343178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.00301","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":"2026-08-04T00:35:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8A85HkIFAMadLvty/LGfNQcjNffoZvfatNjJDrlfmNDEsekLYLgi0jCZNBFNvQuelbIpqxjkhEPMrlGiVJv3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:08:11.381198Z"},"content_sha256":"d9cdca1f04f08b3b0fa9cb60e3f90926bb3110471b274c1fdbf250812be45255","schema_version":"1.0","event_id":"sha256:d9cdca1f04f08b3b0fa9cb60e3f90926bb3110471b274c1fdbf250812be45255"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FNKBILTQR3KMYOYTFHJKP6UNXA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Chenyang Yu, Weida Zhao, Xujun Che, Yuchen Yuan","submitted_at":"2026-07-31T21:31:07Z","abstract_excerpt":"Error-penalized scoring rules ($+1$ for a correct answer, $-\\lambda$ for a wrong one, $0$ for abstaining) are increasingly prescribed against hallucination: a rational agent facing such a rule answers exactly when its correctness probability exceeds Chow's threshold $t^\\ast=\\lambda/(1+\\lambda)$. We prove that a KL-anchored gradient learner can do the opposite. When abstention is a discrete action, the reward gradient and the anchor's restoring force are throttled by the same gate-saturation factor and die together: under explicit conditions (among them, blanket answering loses score in expecta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00301","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/2608.00301/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":"2026-08-04T00:35:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U+oBAD4iSLiLQZJQLclrFwcN71HxCndvYeYdV8AS29++YJcEA2sIew2CrtvxRvDyzMbB8SPD9yVjNJukEA07CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:08:11.381768Z"},"content_sha256":"a930364f0446d77fd532cfe7be9f619b7fc961353180139a652aa6d543e57822","schema_version":"1.0","event_id":"sha256:a930364f0446d77fd532cfe7be9f619b7fc961353180139a652aa6d543e57822"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FNKBILTQR3KMYOYTFHJKP6UNXA/bundle.json","state_url":"https://pith.science/pith/FNKBILTQR3KMYOYTFHJKP6UNXA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FNKBILTQR3KMYOYTFHJKP6UNXA/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":"2026-08-05T07:08:11Z","links":{"resolver":"https://pith.science/pith/FNKBILTQR3KMYOYTFHJKP6UNXA","bundle":"https://pith.science/pith/FNKBILTQR3KMYOYTFHJKP6UNXA/bundle.json","state":"https://pith.science/pith/FNKBILTQR3KMYOYTFHJKP6UNXA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FNKBILTQR3KMYOYTFHJKP6UNXA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FNKBILTQR3KMYOYTFHJKP6UNXA","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":"2e2057b4249a1c94afa7a1f2c633fa9791c7a932e1774dbf97aa10faab0acbc0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T21:31:07Z","title_canon_sha256":"0db57c36df70a20447f6d8038419df64d9f35ec6768c3bbe1fc06a09d3148309"},"schema_version":"1.0","source":{"id":"2608.00301","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00301","created_at":"2026-08-04T00:35:00Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00301v1","created_at":"2026-08-04T00:35:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00301","created_at":"2026-08-04T00:35:00Z"},{"alias_kind":"pith_short_12","alias_value":"FNKBILTQR3KM","created_at":"2026-08-04T00:35:00Z"},{"alias_kind":"pith_short_16","alias_value":"FNKBILTQR3KMYOYT","created_at":"2026-08-04T00:35:00Z"},{"alias_kind":"pith_short_8","alias_value":"FNKBILTQ","created_at":"2026-08-04T00:35:00Z"}],"graph_snapshots":[{"event_id":"sha256:a930364f0446d77fd532cfe7be9f619b7fc961353180139a652aa6d543e57822","target":"graph","created_at":"2026-08-04T00:35:00Z","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/2608.00301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Error-penalized scoring rules ($+1$ for a correct answer, $-\\lambda$ for a wrong one, $0$ for abstaining) are increasingly prescribed against hallucination: a rational agent facing such a rule answers exactly when its correctness probability exceeds Chow's threshold $t^\\ast=\\lambda/(1+\\lambda)$. We prove that a KL-anchored gradient learner can do the opposite. When abstention is a discrete action, the reward gradient and the anchor's restoring force are throttled by the same gate-saturation factor and die together: under explicit conditions (among them, blanket answering loses score in expecta","authors_text":"Chenyang Yu, Weida Zhao, Xujun Che, Yuchen Yuan","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T21:31:07Z","title":"Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00301","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:d9cdca1f04f08b3b0fa9cb60e3f90926bb3110471b274c1fdbf250812be45255","target":"record","created_at":"2026-08-04T00:35:00Z","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":"2e2057b4249a1c94afa7a1f2c633fa9791c7a932e1774dbf97aa10faab0acbc0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T21:31:07Z","title_canon_sha256":"0db57c36df70a20447f6d8038419df64d9f35ec6768c3bbe1fc06a09d3148309"},"schema_version":"1.0","source":{"id":"2608.00301","kind":"arxiv","version":1}},"canonical_sha256":"2b54142e708ed4cc3b1329d2a7fa8db80bfbddfd174df1f39e9ff090192ad5f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b54142e708ed4cc3b1329d2a7fa8db80bfbddfd174df1f39e9ff090192ad5f1","first_computed_at":"2026-08-04T00:35:00.343178Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T00:35:00.343178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D2q1pcHJ38lI9kfIS5DbCXK8s0exXhnmPOsU4PXxX+Kts2tL2edKmifSVpDsqcoQZuuYuZt94RjRY0BLprl1Bg==","signature_status":"signed_v1","signed_at":"2026-08-04T00:35:00.344603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00301","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9cdca1f04f08b3b0fa9cb60e3f90926bb3110471b274c1fdbf250812be45255","sha256:a930364f0446d77fd532cfe7be9f619b7fc961353180139a652aa6d543e57822"],"state_sha256":"5c065533386aa0640cce4d9e893728903c50522259bebe884ed83bdbdf362b2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P0tLLfZ1sRUHZpPDRclfdv6EvX82KcT3o9Jiz15g4TO1tqu7ke0esSOmspf+vIV+XqLHnc4OD4VA2Sg7D8CeCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:08:11.385153Z","bundle_sha256":"80a405116ee813c5d2277ff4072bab3eb8fa8d007176016b2934ea4b615f7cf3"}}