{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TWMJNYEY7PYGMX6F6UFDVYFUK7","short_pith_number":"pith:TWMJNYEY","canonical_record":{"source":{"id":"2607.07690","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T17:49:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"470f5e3e2f09c757eda182dcb8c02115b772c503dec88cf50dbe8df37b13b20d","abstract_canon_sha256":"de7b00e37acb25f4cd0b0936dfa2658a2f76849de5a3211d521ac93d747afc13"},"schema_version":"1.0"},"canonical_sha256":"9d9896e098fbf0665fc5f50a3ae0b457f30f5d457f3e5b93c9dc56e3d113be77","source":{"kind":"arxiv","id":"2607.07690","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TWMJNYEY7PYGMX6F6UFDVYFUK7","target":"record","payload":{"canonical_record":{"source":{"id":"2607.07690","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T17:49:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"470f5e3e2f09c757eda182dcb8c02115b772c503dec88cf50dbe8df37b13b20d","abstract_canon_sha256":"de7b00e37acb25f4cd0b0936dfa2658a2f76849de5a3211d521ac93d747afc13"},"schema_version":"1.0"},"canonical_sha256":"9d9896e098fbf0665fc5f50a3ae0b457f30f5d457f3e5b93c9dc56e3d113be77","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:39.241540Z","signature_b64":"EojSfXwWaM0DS2hh9NbAXjZMJcSPRR9rbasuujcmAmXl9YrrObZbK3X6cBryUyJqlM2OZeAmm/POKG4J5e0yBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d9896e098fbf0665fc5f50a3ae0b457f30f5d457f3e5b93c9dc56e3d113be77","last_reissued_at":"2026-07-09T01:20:39.241129Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:39.241129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.07690","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":"2026-07-09T01:20:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCT3rxL8rrhx67MCujJfDSzyKwZu4kHLwStJD/oxcnFP3WU9tbtryg/pG60O4Ka167UIKxZUZgLnFM4hNjkPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:27:36.277419Z"},"content_sha256":"8507ee0884af4f1ede391d51b4dbbc082de62de008cb2c4bbcd0000d2082d5f0","schema_version":"1.0","event_id":"sha256:8507ee0884af4f1ede391d51b4dbbc082de62de008cb2c4bbcd0000d2082d5f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TWMJNYEY7PYGMX6F6UFDVYFUK7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Vladislav Beliaev","submitted_at":"2026-07-08T17:49:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07690","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/2607.07690/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":"2026-07-09T01:20:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oGv+fKpkRnfArfEHEeQUzROAvW1osDOg4UdFKCTRck+DDsqwMD6j3foMr1BTuhNgSEiprErj3Nv64TbAFXwEBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:27:36.278114Z"},"content_sha256":"7c8e8981bc01f9c995b34175258581a22099f30de150aed6d87820e3e3e20e29","schema_version":"1.0","event_id":"sha256:7c8e8981bc01f9c995b34175258581a22099f30de150aed6d87820e3e3e20e29"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TWMJNYEY7PYGMX6F6UFDVYFUK7/bundle.json","state_url":"https://pith.science/pith/TWMJNYEY7PYGMX6F6UFDVYFUK7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TWMJNYEY7PYGMX6F6UFDVYFUK7/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":"2026-08-12T12:27:36Z","links":{"resolver":"https://pith.science/pith/TWMJNYEY7PYGMX6F6UFDVYFUK7","bundle":"https://pith.science/pith/TWMJNYEY7PYGMX6F6UFDVYFUK7/bundle.json","state":"https://pith.science/pith/TWMJNYEY7PYGMX6F6UFDVYFUK7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TWMJNYEY7PYGMX6F6UFDVYFUK7/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b5szouKM8VIly6C01VbdQHJzvJMOcaVCC/tvxKr2B7AaODgk9ZLmbk7Y77QX91BLsiFgwESPEeoeKEB57hluBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T12:27:36.283684Z","bundle_sha256":"20d792d6c2ea3920ad48017350c85ee1718e99f399e18771a697d6a79d129956"}}