{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZKLGGKANYYSTGPKM365MVJXEAH","short_pith_number":"pith:ZKLGGKAN","canonical_record":{"source":{"id":"2608.09324","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T09:06:03Z","cross_cats_sorted":[],"title_canon_sha256":"8dfabbdf38970bcb6c749fbac6380ecc50b79f60ae708c51ac958f337d8c1234","abstract_canon_sha256":"be9ecc91c6f362df6f847480c8b2514c77a1a44b7f939bd4c979916b6a98a1ba"},"schema_version":"1.0"},"canonical_sha256":"ca9663280dc625333d4cdfbacaa6e401df599abecbc7bd37d45c77d4e3563189","source":{"kind":"arxiv","id":"2608.09324","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09324","created_at":"2026-08-11T02:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09324v1","created_at":"2026-08-11T02:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09324","created_at":"2026-08-11T02:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"ZKLGGKANYYST","created_at":"2026-08-11T02:22:20Z"},{"alias_kind":"pith_short_16","alias_value":"ZKLGGKANYYSTGPKM","created_at":"2026-08-11T02:22:20Z"},{"alias_kind":"pith_short_8","alias_value":"ZKLGGKAN","created_at":"2026-08-11T02:22:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZKLGGKANYYSTGPKM365MVJXEAH","target":"record","payload":{"canonical_record":{"source":{"id":"2608.09324","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T09:06:03Z","cross_cats_sorted":[],"title_canon_sha256":"8dfabbdf38970bcb6c749fbac6380ecc50b79f60ae708c51ac958f337d8c1234","abstract_canon_sha256":"be9ecc91c6f362df6f847480c8b2514c77a1a44b7f939bd4c979916b6a98a1ba"},"schema_version":"1.0"},"canonical_sha256":"ca9663280dc625333d4cdfbacaa6e401df599abecbc7bd37d45c77d4e3563189","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:22:20.973432Z","signature_b64":"AI34EQv1JPkEOHkR3fHk0fqxqTmTXsCmSmHoWmM0G0yJnNpsVAXUNXlccJTZfVtyY3TdwfTulp922JpFo49JAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca9663280dc625333d4cdfbacaa6e401df599abecbc7bd37d45c77d4e3563189","last_reissued_at":"2026-08-11T02:22:20.971856Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:22:20.971856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.09324","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":"2026-08-11T02:22:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kmxG+7lkgBhJfpUagjc3CNGJfD8rO6BkKJc+A5RVkhV4GNwjxGbZg5Nt5+M3vrIRfxhqmKyU3liwuNwACxY5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:14:43.641967Z"},"content_sha256":"c6780cf8d5b91e779aa97b02e3f46e5644c73ccd601345403a8f966f242fcd99","schema_version":"1.0","event_id":"sha256:c6780cf8d5b91e779aa97b02e3f46e5644c73ccd601345403a8f966f242fcd99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZKLGGKANYYSTGPKM365MVJXEAH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoRE: Consensus Rewards via Equilibrium for Test-Time Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ambuj Mehrish, Sebastiano Vascon","submitted_at":"2026-08-10T09:06:03Z","abstract_excerpt":"On unlabeled test data, reinforcement learning lacks a ground-truth reward; test-time RL methods derive one from the model's own roll-outs, rewarding those that match the majority vote over $N$ sampled answers. That vote discards a correct answer whenever it is a minority and scores every majority-matching roll-out identically. We replace it with \\emph{CoRE} (Consensus Rewards via Equilibrium): the $N$ roll-outs form a graph whose edges combine answer agreement, reasoning similarity, and generation confidence, and replicator dynamics extract its dominant set, yielding a refined pseudo-label, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09324","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/2608.09324/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":"2026-08-11T02:22:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ckNg2oH/XOJQ56FYFePYS+i4sYwLcjxbuAsJe8KWu6xEmqiOOScAXD06MOU4/b/lKCC5vdI5kF8Q3MO5K+7FAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:14:43.642457Z"},"content_sha256":"efeb9458b22c85a6f568a8555221a4cc62361d436d81ac78d52ed70932107783","schema_version":"1.0","event_id":"sha256:efeb9458b22c85a6f568a8555221a4cc62361d436d81ac78d52ed70932107783"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZKLGGKANYYSTGPKM365MVJXEAH/bundle.json","state_url":"https://pith.science/pith/ZKLGGKANYYSTGPKM365MVJXEAH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZKLGGKANYYSTGPKM365MVJXEAH/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":"2026-08-15T21:14:43Z","links":{"resolver":"https://pith.science/pith/ZKLGGKANYYSTGPKM365MVJXEAH","bundle":"https://pith.science/pith/ZKLGGKANYYSTGPKM365MVJXEAH/bundle.json","state":"https://pith.science/pith/ZKLGGKANYYSTGPKM365MVJXEAH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZKLGGKANYYSTGPKM365MVJXEAH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZKLGGKANYYSTGPKM365MVJXEAH","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":"be9ecc91c6f362df6f847480c8b2514c77a1a44b7f939bd4c979916b6a98a1ba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T09:06:03Z","title_canon_sha256":"8dfabbdf38970bcb6c749fbac6380ecc50b79f60ae708c51ac958f337d8c1234"},"schema_version":"1.0","source":{"id":"2608.09324","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09324","created_at":"2026-08-11T02:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09324v1","created_at":"2026-08-11T02:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09324","created_at":"2026-08-11T02:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"ZKLGGKANYYST","created_at":"2026-08-11T02:22:20Z"},{"alias_kind":"pith_short_16","alias_value":"ZKLGGKANYYSTGPKM","created_at":"2026-08-11T02:22:20Z"},{"alias_kind":"pith_short_8","alias_value":"ZKLGGKAN","created_at":"2026-08-11T02:22:20Z"}],"graph_snapshots":[{"event_id":"sha256:efeb9458b22c85a6f568a8555221a4cc62361d436d81ac78d52ed70932107783","target":"graph","created_at":"2026-08-11T02:22:20Z","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/2608.09324/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On unlabeled test data, reinforcement learning lacks a ground-truth reward; test-time RL methods derive one from the model's own roll-outs, rewarding those that match the majority vote over $N$ sampled answers. That vote discards a correct answer whenever it is a minority and scores every majority-matching roll-out identically. We replace it with \\emph{CoRE} (Consensus Rewards via Equilibrium): the $N$ roll-outs form a graph whose edges combine answer agreement, reasoning similarity, and generation confidence, and replicator dynamics extract its dominant set, yielding a refined pseudo-label, a","authors_text":"Ambuj Mehrish, Sebastiano Vascon","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T09:06:03Z","title":"CoRE: Consensus Rewards via Equilibrium for Test-Time Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09324","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:c6780cf8d5b91e779aa97b02e3f46e5644c73ccd601345403a8f966f242fcd99","target":"record","created_at":"2026-08-11T02:22:20Z","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":"be9ecc91c6f362df6f847480c8b2514c77a1a44b7f939bd4c979916b6a98a1ba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T09:06:03Z","title_canon_sha256":"8dfabbdf38970bcb6c749fbac6380ecc50b79f60ae708c51ac958f337d8c1234"},"schema_version":"1.0","source":{"id":"2608.09324","kind":"arxiv","version":1}},"canonical_sha256":"ca9663280dc625333d4cdfbacaa6e401df599abecbc7bd37d45c77d4e3563189","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca9663280dc625333d4cdfbacaa6e401df599abecbc7bd37d45c77d4e3563189","first_computed_at":"2026-08-11T02:22:20.971856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:22:20.971856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AI34EQv1JPkEOHkR3fHk0fqxqTmTXsCmSmHoWmM0G0yJnNpsVAXUNXlccJTZfVtyY3TdwfTulp922JpFo49JAQ==","signature_status":"signed_v1","signed_at":"2026-08-11T02:22:20.973432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09324","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6780cf8d5b91e779aa97b02e3f46e5644c73ccd601345403a8f966f242fcd99","sha256:efeb9458b22c85a6f568a8555221a4cc62361d436d81ac78d52ed70932107783"],"state_sha256":"5df9dd77ddd4a7883dd6d0fc87eb798311159273aa86853969e4f21b65571e82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XQknXMGaqeYtt0jK1yupwFuK9/OOeONKh9e/Zg2TJE3Ys1ZJNXZQi5FtK5fBCGkL/ccyY+YSK7GnNx79c/AfCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T21:14:43.646303Z","bundle_sha256":"a329086addcecce146c64c80c0fb6bb9e8fcbd92f374f967d28985c42f4c363c"}}