{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MCNMQU42FGKFA25HKUTV75R25B","short_pith_number":"pith:MCNMQU42","canonical_record":{"source":{"id":"2607.20543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-12T17:17:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eedf2787f8bcab71ef1c7f7ad0ba4adbce132b11463b4fb403a0281c4f553ff4","abstract_canon_sha256":"b0fd5ce26919dd2ee32a9511af1cdc02ba9f8b879d31c29a9b2d6899ddbb1673"},"schema_version":"1.0"},"canonical_sha256":"609ac8539a2994506ba755275ff63ae84bb1eb0aed7dc83aed4d43f7428171fc","source":{"kind":"arxiv","id":"2607.20543","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20543","created_at":"2026-07-24T00:23:21Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20543v1","created_at":"2026-07-24T00:23:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20543","created_at":"2026-07-24T00:23:21Z"},{"alias_kind":"pith_short_12","alias_value":"MCNMQU42FGKF","created_at":"2026-07-24T00:23:21Z"},{"alias_kind":"pith_short_16","alias_value":"MCNMQU42FGKFA25H","created_at":"2026-07-24T00:23:21Z"},{"alias_kind":"pith_short_8","alias_value":"MCNMQU42","created_at":"2026-07-24T00:23:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MCNMQU42FGKFA25HKUTV75R25B","target":"record","payload":{"canonical_record":{"source":{"id":"2607.20543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-12T17:17:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eedf2787f8bcab71ef1c7f7ad0ba4adbce132b11463b4fb403a0281c4f553ff4","abstract_canon_sha256":"b0fd5ce26919dd2ee32a9511af1cdc02ba9f8b879d31c29a9b2d6899ddbb1673"},"schema_version":"1.0"},"canonical_sha256":"609ac8539a2994506ba755275ff63ae84bb1eb0aed7dc83aed4d43f7428171fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T00:23:21.676270Z","signature_b64":"60Yo13HXWzBS7o002V5i5k3VItNC73M949P5ugBaFCpo218UYkLmfL/vnBdKhIlRwKQ8UVGLyVKLWqRXNbZLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"609ac8539a2994506ba755275ff63ae84bb1eb0aed7dc83aed4d43f7428171fc","last_reissued_at":"2026-07-24T00:23:21.675396Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T00:23:21.675396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.20543","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":"2026-07-24T00:23:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wbDLRom0edJye6KmPoILQBY0ALJaPLU53/K+psj0a8PmujaTlIR/z6rbukC949hvkXSoAk/lLnXr6/7z6MOCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:39:37.648050Z"},"content_sha256":"553bdc90d9a01a7ccbb181714f2f1d4b26d40ee602eaed06c95fda0b030ec4ba","schema_version":"1.0","event_id":"sha256:553bdc90d9a01a7ccbb181714f2f1d4b26d40ee602eaed06c95fda0b030ec4ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MCNMQU42FGKFA25HKUTV75R25B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Todd Zhou","submitted_at":"2026-07-12T17:17:18Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) can improve one-sample accuracy while making a model worse under repeated sampling. We study this pass@k inversion: after training, the policy may solve fewer distinct problems than its base model at large $k$. The failure concentrates on boundary prompts, where the base model contains rare correct trajectories that are recoverable by sampling but too sparse to reliably appear in finite RLVR rollout groups. We argue that a two-mode account explains this as an absence-of-evidence failure: rare correct trajectories may disappear before RLVR s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20543","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/2607.20543/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":"2026-07-24T00:23:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P7mZeVWmamSSakVnalDuEP/+M57lK5KvACNby2nNK7wGvF6V3adj27X9kFN5ytarwLtLHh/D2KjXeGLVaW81AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:39:37.648615Z"},"content_sha256":"4f0fe16a3956f4031f02a225a0524581613ce63ef6aa0ecb0713f95123319b79","schema_version":"1.0","event_id":"sha256:4f0fe16a3956f4031f02a225a0524581613ce63ef6aa0ecb0713f95123319b79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MCNMQU42FGKFA25HKUTV75R25B/bundle.json","state_url":"https://pith.science/pith/MCNMQU42FGKFA25HKUTV75R25B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MCNMQU42FGKFA25HKUTV75R25B/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":"2026-08-18T10:39:37Z","links":{"resolver":"https://pith.science/pith/MCNMQU42FGKFA25HKUTV75R25B","bundle":"https://pith.science/pith/MCNMQU42FGKFA25HKUTV75R25B/bundle.json","state":"https://pith.science/pith/MCNMQU42FGKFA25HKUTV75R25B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MCNMQU42FGKFA25HKUTV75R25B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MCNMQU42FGKFA25HKUTV75R25B","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":"b0fd5ce26919dd2ee32a9511af1cdc02ba9f8b879d31c29a9b2d6899ddbb1673","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-12T17:17:18Z","title_canon_sha256":"eedf2787f8bcab71ef1c7f7ad0ba4adbce132b11463b4fb403a0281c4f553ff4"},"schema_version":"1.0","source":{"id":"2607.20543","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20543","created_at":"2026-07-24T00:23:21Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20543v1","created_at":"2026-07-24T00:23:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20543","created_at":"2026-07-24T00:23:21Z"},{"alias_kind":"pith_short_12","alias_value":"MCNMQU42FGKF","created_at":"2026-07-24T00:23:21Z"},{"alias_kind":"pith_short_16","alias_value":"MCNMQU42FGKFA25H","created_at":"2026-07-24T00:23:21Z"},{"alias_kind":"pith_short_8","alias_value":"MCNMQU42","created_at":"2026-07-24T00:23:21Z"}],"graph_snapshots":[{"event_id":"sha256:4f0fe16a3956f4031f02a225a0524581613ce63ef6aa0ecb0713f95123319b79","target":"graph","created_at":"2026-07-24T00:23:21Z","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/2607.20543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) can improve one-sample accuracy while making a model worse under repeated sampling. We study this pass@k inversion: after training, the policy may solve fewer distinct problems than its base model at large $k$. The failure concentrates on boundary prompts, where the base model contains rare correct trajectories that are recoverable by sampling but too sparse to reliably appear in finite RLVR rollout groups. We argue that a two-mode account explains this as an absence-of-evidence failure: rare correct trajectories may disappear before RLVR s","authors_text":"Todd Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-12T17:17:18Z","title":"When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20543","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":"sha256:553bdc90d9a01a7ccbb181714f2f1d4b26d40ee602eaed06c95fda0b030ec4ba","target":"record","created_at":"2026-07-24T00:23:21Z","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":"b0fd5ce26919dd2ee32a9511af1cdc02ba9f8b879d31c29a9b2d6899ddbb1673","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-12T17:17:18Z","title_canon_sha256":"eedf2787f8bcab71ef1c7f7ad0ba4adbce132b11463b4fb403a0281c4f553ff4"},"schema_version":"1.0","source":{"id":"2607.20543","kind":"arxiv","version":1}},"canonical_sha256":"609ac8539a2994506ba755275ff63ae84bb1eb0aed7dc83aed4d43f7428171fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"609ac8539a2994506ba755275ff63ae84bb1eb0aed7dc83aed4d43f7428171fc","first_computed_at":"2026-07-24T00:23:21.675396Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T00:23:21.675396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"60Yo13HXWzBS7o002V5i5k3VItNC73M949P5ugBaFCpo218UYkLmfL/vnBdKhIlRwKQ8UVGLyVKLWqRXNbZLDw==","signature_status":"signed_v1","signed_at":"2026-07-24T00:23:21.676270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.20543","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:553bdc90d9a01a7ccbb181714f2f1d4b26d40ee602eaed06c95fda0b030ec4ba","sha256:4f0fe16a3956f4031f02a225a0524581613ce63ef6aa0ecb0713f95123319b79"],"state_sha256":"dd6c099249b47efe81984c082b4e954e87021b76ce286d9c92a7f812e79d2174"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uNSVaeJlbUgDS6z3Iy8nYe94BKXndu42QNebNB+u51BGOEal4+wSzz1TMeiZl/41dP6s3rt4Q86/6+ZdB/ctDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T10:39:37.652416Z","bundle_sha256":"02fcfcdbb6bc53132673a79712e358e91560ceb3f13cb45fcfb6a05c24b9f052"}}