{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DESGC7R4MXB4HLPK4ZTGDRHMW2","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":"67bfa9d441363aa2040db222f078720e315c7d021524aee0f67a10fd897f8cf2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T04:07:26Z","title_canon_sha256":"bb6cc1f9e60145d460cafe97899dd2324a0ce4ef84f1167ec4b5cbf924e10efa"},"schema_version":"1.0","source":{"id":"2605.27934","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27934","created_at":"2026-05-28T01:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27934v1","created_at":"2026-05-28T01:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27934","created_at":"2026-05-28T01:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"DESGC7R4MXB4","created_at":"2026-05-28T01:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"DESGC7R4MXB4HLPK","created_at":"2026-05-28T01:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"DESGC7R4","created_at":"2026-05-28T01:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:b708dbb8ccacbc21eefc7770593426ede3f90a51225a8b4640c7d933f7115979","target":"graph","created_at":"2026-05-28T01:04:52Z","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/2605.27934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards improves language model reasoning, but its reliance on domain-specific verifiers, sparse outcome rewards, and coarse-grained credit assignment limits its applicability. We introduce GeneralThinker, an on-policy framework that reformulates reasoning supervision as dense answer-conditioned optimization, enabling response-level evaluation and token-level credit assignment without domain-specific verifiers. GeneralThinker evaluates generated reasoning trajectories using the likelihood of the ground-truth answer and derives token-wise compatibility sig","authors_text":"Sanghyun Park, Shengmin Piao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T04:07:26Z","title":"GeneralThinker: Domain-General Reasoning through Likelihood-Guided Answer-Conditioned Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27934","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:aded9a725fdfd413ad2a1ceef979330114d6dc868b182a001de6ad42201de086","target":"record","created_at":"2026-05-28T01:04:52Z","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":"67bfa9d441363aa2040db222f078720e315c7d021524aee0f67a10fd897f8cf2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T04:07:26Z","title_canon_sha256":"bb6cc1f9e60145d460cafe97899dd2324a0ce4ef84f1167ec4b5cbf924e10efa"},"schema_version":"1.0","source":{"id":"2605.27934","kind":"arxiv","version":1}},"canonical_sha256":"1924617e3c65c3c3adeae66661c4ecb69952d5e4abe2b7ef97d5523fb7c7b57a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1924617e3c65c3c3adeae66661c4ecb69952d5e4abe2b7ef97d5523fb7c7b57a","first_computed_at":"2026-05-28T01:04:52.980191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:52.980191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wzznJ70dZaSn3gBNyM8XiE6FJiwO+fzaZDphfslSMj7WfT4Tm27ypD1v9fw5dGKqkt5SMUTkXyTQfrMjtNB3Dg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:52.980646Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27934","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aded9a725fdfd413ad2a1ceef979330114d6dc868b182a001de6ad42201de086","sha256:b708dbb8ccacbc21eefc7770593426ede3f90a51225a8b4640c7d933f7115979"],"state_sha256":"5ee09c58ab6844d6d518e775c5f2b7f6f728b2639083f62f89ef40fd286023d9"}