{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TWMJNYEY7PYGMX6F6UFDVYFUK7","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":"de7b00e37acb25f4cd0b0936dfa2658a2f76849de5a3211d521ac93d747afc13","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T17:49:14Z","title_canon_sha256":"470f5e3e2f09c757eda182dcb8c02115b772c503dec88cf50dbe8df37b13b20d"},"schema_version":"1.0","source":{"id":"2607.07690","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07690","created_at":"2026-07-09T01:20:39Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07690v1","created_at":"2026-07-09T01:20:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07690","created_at":"2026-07-09T01:20:39Z"},{"alias_kind":"pith_short_12","alias_value":"TWMJNYEY7PYG","created_at":"2026-07-09T01:20:39Z"},{"alias_kind":"pith_short_16","alias_value":"TWMJNYEY7PYGMX6F","created_at":"2026-07-09T01:20:39Z"},{"alias_kind":"pith_short_8","alias_value":"TWMJNYEY","created_at":"2026-07-09T01:20:39Z"}],"graph_snapshots":[{"event_id":"sha256:7c8e8981bc01f9c995b34175258581a22099f30de150aed6d87820e3e3e20e29","target":"graph","created_at":"2026-07-09T01:20:39Z","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/2607.07690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning from verifiable rewards (e.g. GRPO) is the engine behind today's reasoning models, yet it grades only the final answer. On hard problems this trains models to write more rather than to think better, since the trace itself is never graded and no label for good thinking exists. We introduce Agon, which makes two competing models each other's graders. Both attempt the same problem; in alternating roles, one drafts a solution and the other reads it while solving, and each is rewarded for out-solving the other. To win, a model must out-reason a rival that has seen its work, s","authors_text":"Vladislav Beliaev","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T17:49:14Z","title":"Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07690","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":"sha256:8507ee0884af4f1ede391d51b4dbbc082de62de008cb2c4bbcd0000d2082d5f0","target":"record","created_at":"2026-07-09T01:20:39Z","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":"de7b00e37acb25f4cd0b0936dfa2658a2f76849de5a3211d521ac93d747afc13","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T17:49:14Z","title_canon_sha256":"470f5e3e2f09c757eda182dcb8c02115b772c503dec88cf50dbe8df37b13b20d"},"schema_version":"1.0","source":{"id":"2607.07690","kind":"arxiv","version":1}},"canonical_sha256":"9d9896e098fbf0665fc5f50a3ae0b457f30f5d457f3e5b93c9dc56e3d113be77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d9896e098fbf0665fc5f50a3ae0b457f30f5d457f3e5b93c9dc56e3d113be77","first_computed_at":"2026-07-09T01:20:39.241129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:20:39.241129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EojSfXwWaM0DS2hh9NbAXjZMJcSPRR9rbasuujcmAmXl9YrrObZbK3X6cBryUyJqlM2OZeAmm/POKG4J5e0yBw==","signature_status":"signed_v1","signed_at":"2026-07-09T01:20:39.241540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.07690","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8507ee0884af4f1ede391d51b4dbbc082de62de008cb2c4bbcd0000d2082d5f0","sha256:7c8e8981bc01f9c995b34175258581a22099f30de150aed6d87820e3e3e20e29"],"state_sha256":"5667a832c205373dbf37349962a6bc3466fca1fe0ec1bf651b468169a9984eb2"}