{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:V76DHFFENLMW3H5NPLQFPZTYKI","short_pith_number":"pith:V76DHFFE","canonical_record":{"source":{"id":"2601.12186","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-01-17T22:30:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ede0c4455424171b681a3c7b9fbef67aa7487cbae91a191e745398791b7f3140","abstract_canon_sha256":"ac50e1c6ac0293d570cddafd2a1aaffddbf1130f05c1c901be8e951ee4a4e4ba"},"schema_version":"1.0"},"canonical_sha256":"affc3394a46ad96d9fad7ae057e678523399dd9d2e4dbcf433943d4e5929ed9e","source":{"kind":"arxiv","id":"2601.12186","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.12186","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2601.12186v3","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.12186","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"V76DHFFENLMW","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"V76DHFFENLMW3H5N","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"V76DHFFE","created_at":"2026-06-03T01:05:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:V76DHFFENLMW3H5NPLQFPZTYKI","target":"record","payload":{"canonical_record":{"source":{"id":"2601.12186","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-01-17T22:30:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ede0c4455424171b681a3c7b9fbef67aa7487cbae91a191e745398791b7f3140","abstract_canon_sha256":"ac50e1c6ac0293d570cddafd2a1aaffddbf1130f05c1c901be8e951ee4a4e4ba"},"schema_version":"1.0"},"canonical_sha256":"affc3394a46ad96d9fad7ae057e678523399dd9d2e4dbcf433943d4e5929ed9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:09.135654Z","signature_b64":"cLz+F7vMP6V2T1X42yXX4JWAcFEFdMSV/C4Ex3PTI/8SXNMP8eZ674NNVa+Ssg4dbtTRKJxydi4BOm6FJSFHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"affc3394a46ad96d9fad7ae057e678523399dd9d2e4dbcf433943d4e5929ed9e","last_reissued_at":"2026-06-03T01:05:09.135187Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:09.135187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.12186","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CFrRc/uHimz8feenkxeL8fQsSZaZOYDlhu6HK7Hd+6TEMAGbOV+3Lscxu6u1OI/nWg4MzSi5kHzIS5furFHYAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T12:39:14.075211Z"},"content_sha256":"8a2318db0354ddd0aa6b65f261fd5393bb70befafcb2148a1777b07f48a9e6f1","schema_version":"1.0","event_id":"sha256:8a2318db0354ddd0aa6b65f261fd5393bb70befafcb2148a1777b07f48a9e6f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:V76DHFFENLMW3H5NPLQFPZTYKI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Indraneil Paul, Iryna Gurevych, Vatsal Venkatkrishna","submitted_at":"2026-01-17T22:30:45Z","abstract_excerpt":"Multi-domain thinking verifiers trained via Reinforcement Learning with Verifiable Rewards (RLVR) are a cornerstone of modern post-training. However, their adoption in code generation has lagged behind that of execution feedback due to the prohibitive costs of the full RLVR pipeline. In this work, we ablate three primary choices along the performance-cost trade-off in RLVR: intermediate thinking traces, learning from negative samples, and on-policy training. We introduce Aletheia, a controlled, execution-grounded testbed to facilitate a contamination-free analysis of code verifier training rec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.12186","kind":"arxiv","version":3},"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/2601.12186/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":"2026-06-03T01:05:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dCF3AvdR+bAI/i5FTOI9HG+UduY9tKZsjR4C3Z78vZm6qb0O1a6E3YmBszZX6F0B5AsG6ugQCmLRIqjTiydWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T12:39:14.075610Z"},"content_sha256":"0da4b88fa28b93944eb08c35ce9f462651429abd4da9a7d7d3d1e692f88f9e11","schema_version":"1.0","event_id":"sha256:0da4b88fa28b93944eb08c35ce9f462651429abd4da9a7d7d3d1e692f88f9e11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V76DHFFENLMW3H5NPLQFPZTYKI/bundle.json","state_url":"https://pith.science/pith/V76DHFFENLMW3H5NPLQFPZTYKI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V76DHFFENLMW3H5NPLQFPZTYKI/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":"2026-06-03T12:39:14Z","links":{"resolver":"https://pith.science/pith/V76DHFFENLMW3H5NPLQFPZTYKI","bundle":"https://pith.science/pith/V76DHFFENLMW3H5NPLQFPZTYKI/bundle.json","state":"https://pith.science/pith/V76DHFFENLMW3H5NPLQFPZTYKI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V76DHFFENLMW3H5NPLQFPZTYKI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V76DHFFENLMW3H5NPLQFPZTYKI","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":"ac50e1c6ac0293d570cddafd2a1aaffddbf1130f05c1c901be8e951ee4a4e4ba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-01-17T22:30:45Z","title_canon_sha256":"ede0c4455424171b681a3c7b9fbef67aa7487cbae91a191e745398791b7f3140"},"schema_version":"1.0","source":{"id":"2601.12186","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.12186","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2601.12186v3","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.12186","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"V76DHFFENLMW","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"V76DHFFENLMW3H5N","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"V76DHFFE","created_at":"2026-06-03T01:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:0da4b88fa28b93944eb08c35ce9f462651429abd4da9a7d7d3d1e692f88f9e11","target":"graph","created_at":"2026-06-03T01:05:09Z","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/2601.12186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-domain thinking verifiers trained via Reinforcement Learning with Verifiable Rewards (RLVR) are a cornerstone of modern post-training. However, their adoption in code generation has lagged behind that of execution feedback due to the prohibitive costs of the full RLVR pipeline. In this work, we ablate three primary choices along the performance-cost trade-off in RLVR: intermediate thinking traces, learning from negative samples, and on-policy training. We introduce Aletheia, a controlled, execution-grounded testbed to facilitate a contamination-free analysis of code verifier training rec","authors_text":"Indraneil Paul, Iryna Gurevych, Vatsal Venkatkrishna","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-01-17T22:30:45Z","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.12186","kind":"arxiv","version":3},"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":"sha256:8a2318db0354ddd0aa6b65f261fd5393bb70befafcb2148a1777b07f48a9e6f1","target":"record","created_at":"2026-06-03T01:05:09Z","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":"ac50e1c6ac0293d570cddafd2a1aaffddbf1130f05c1c901be8e951ee4a4e4ba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-01-17T22:30:45Z","title_canon_sha256":"ede0c4455424171b681a3c7b9fbef67aa7487cbae91a191e745398791b7f3140"},"schema_version":"1.0","source":{"id":"2601.12186","kind":"arxiv","version":3}},"canonical_sha256":"affc3394a46ad96d9fad7ae057e678523399dd9d2e4dbcf433943d4e5929ed9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"affc3394a46ad96d9fad7ae057e678523399dd9d2e4dbcf433943d4e5929ed9e","first_computed_at":"2026-06-03T01:05:09.135187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:09.135187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cLz+F7vMP6V2T1X42yXX4JWAcFEFdMSV/C4Ex3PTI/8SXNMP8eZ674NNVa+Ssg4dbtTRKJxydi4BOm6FJSFHAw==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:09.135654Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.12186","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a2318db0354ddd0aa6b65f261fd5393bb70befafcb2148a1777b07f48a9e6f1","sha256:0da4b88fa28b93944eb08c35ce9f462651429abd4da9a7d7d3d1e692f88f9e11"],"state_sha256":"cc0d6f29af916fcb6192e01cdc5bff6b24ca9522693510081f8b64087f4bb8f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2196ex+AyVcxG2YKGpaUV91vx4NqP7Z2TvMr61filLgZ5cJV//nI48cO1buRLzV50NCgdlSiFzyxZP+IcdaFBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T12:39:14.077948Z","bundle_sha256":"cbc668fd2bdee835d5e81ee9f2706be5ff91fdd613e0a3d691c1dfb676563d17"}}