{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PQH3AW5BGZID7H6OVIFSX2BAJC","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":"a6daeba3bc1fd3b0bb7f688795dd158e0f42fce5308390a57b9f2cc18cb186a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T12:20:17Z","title_canon_sha256":"adaf9b8b5e92fa6fe461a97b03fee23d78dc83c3ee36cb866ba226ce4b68fb2b"},"schema_version":"1.0","source":{"id":"2608.03545","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03545","created_at":"2026-08-05T01:36:05Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03545v1","created_at":"2026-08-05T01:36:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03545","created_at":"2026-08-05T01:36:05Z"},{"alias_kind":"pith_short_12","alias_value":"PQH3AW5BGZID","created_at":"2026-08-05T01:36:05Z"},{"alias_kind":"pith_short_16","alias_value":"PQH3AW5BGZID7H6O","created_at":"2026-08-05T01:36:05Z"},{"alias_kind":"pith_short_8","alias_value":"PQH3AW5B","created_at":"2026-08-05T01:36:05Z"}],"graph_snapshots":[{"event_id":"sha256:ed4629e40d8db3ff6d9f20a740dc521f1e75268ad829a45f27142fe2978adbf2","target":"graph","created_at":"2026-08-05T01:36:05Z","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/2608.03545/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Test-time reinforcement learning (TTRL) improves the reasoning capabilities of large language models without labeled data by updating the policy with pseudo-labels constructed through majority voting. While effective, the reward signal assigned from majority voting is highly sensitive to consensus strength, defined as the frequency of the most common answer within a rollout group. In TTRL, consensus strength plays a dual role: it reflects both the reliability of the pseudo-label and the distribution of advantages. Low consensus can amplify updates from unreliable pseudo-labels through dispropo","authors_text":"Kehai Chen, Kunbin Xu, Xingzuo Li, Xuefeng Bai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T12:20:17Z","title":"Hi-TTRL: Regulating Consensus with Hints for Test-Time Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03545","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:a1d3c9e8a2e6933c1e78f481430b691b42370b5a985e352eda55c6b9ef0894b7","target":"record","created_at":"2026-08-05T01:36:05Z","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":"a6daeba3bc1fd3b0bb7f688795dd158e0f42fce5308390a57b9f2cc18cb186a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T12:20:17Z","title_canon_sha256":"adaf9b8b5e92fa6fe461a97b03fee23d78dc83c3ee36cb866ba226ce4b68fb2b"},"schema_version":"1.0","source":{"id":"2608.03545","kind":"arxiv","version":1}},"canonical_sha256":"7c0fb05ba136503f9fceaa0b2be820488d038f3222b7955ac6ce7480f25d7fb3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c0fb05ba136503f9fceaa0b2be820488d038f3222b7955ac6ce7480f25d7fb3","first_computed_at":"2026-08-05T01:36:05.011374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:36:05.011374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cjrrkbsz4iO+D/9kJVmzn4KuszxfEPFee4CehMSiO/MNKOooNRMnQyKr9hhnMZfRpEWbnfKqXkirNesSg08XAw==","signature_status":"signed_v1","signed_at":"2026-08-05T01:36:05.013243Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03545","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1d3c9e8a2e6933c1e78f481430b691b42370b5a985e352eda55c6b9ef0894b7","sha256:ed4629e40d8db3ff6d9f20a740dc521f1e75268ad829a45f27142fe2978adbf2"],"state_sha256":"f7a6e73fa7401b2f7076108b9ee76d08336e372adf136b7bd82a76c9d85152ef"}