{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NETQRCQWEJD6OAXLKV3JKFZHUP","short_pith_number":"pith:NETQRCQW","canonical_record":{"source":{"id":"2501.01054","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T04:33:31Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"7bb3263b72703751df1c58f4f57ea22d3553aeae7f5683ba989c779f545f101f","abstract_canon_sha256":"232b6fe5be8e89aeb7302a482ba6225e3d5281492be1d7e1bcf367232e20f02c"},"schema_version":"1.0"},"canonical_sha256":"6927088a162247e702eb5576951727a3f5041cc06446fdc0c45a0a836a9a2674","source":{"kind":"arxiv","id":"2501.01054","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01054","created_at":"2026-07-05T09:56:13Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01054v1","created_at":"2026-07-05T09:56:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01054","created_at":"2026-07-05T09:56:13Z"},{"alias_kind":"pith_short_12","alias_value":"NETQRCQWEJD6","created_at":"2026-07-05T09:56:13Z"},{"alias_kind":"pith_short_16","alias_value":"NETQRCQWEJD6OAXL","created_at":"2026-07-05T09:56:13Z"},{"alias_kind":"pith_short_8","alias_value":"NETQRCQW","created_at":"2026-07-05T09:56:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NETQRCQWEJD6OAXLKV3JKFZHUP","target":"record","payload":{"canonical_record":{"source":{"id":"2501.01054","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T04:33:31Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"7bb3263b72703751df1c58f4f57ea22d3553aeae7f5683ba989c779f545f101f","abstract_canon_sha256":"232b6fe5be8e89aeb7302a482ba6225e3d5281492be1d7e1bcf367232e20f02c"},"schema_version":"1.0"},"canonical_sha256":"6927088a162247e702eb5576951727a3f5041cc06446fdc0c45a0a836a9a2674","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:13.630131Z","signature_b64":"CNKO1ZMsV0VEshVRkbnKbNN+dTXa0L67K9sHYqrDVcNipSnsoS8OpTlI8nqM+aGNQqMJjLI8YesrERY0GoH6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6927088a162247e702eb5576951727a3f5041cc06446fdc0c45a0a836a9a2674","last_reissued_at":"2026-07-05T09:56:13.629717Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:13.629717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.01054","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":"2026-07-05T09:56:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TtisvPpVaXAwpsXkDONj2bV1p3w3qnHPzBiG8GKtL1xnomrkRFr3VGof0+5RsUkyZdUujYe5z7TZsNucrFayBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:48:24.169341Z"},"content_sha256":"0ce22628665ed679a6c5fc5a336122308acfa4398e87c78dc3c2fc2afcbb3e25","schema_version":"1.0","event_id":"sha256:0ce22628665ed679a6c5fc5a336122308acfa4398e87c78dc3c2fc2afcbb3e25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NETQRCQWEJD6OAXLKV3JKFZHUP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Scaling of Unit Tests for Code Reward Modeling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Jie Tang, Jifan Yu, Jing Zhang, Sijia Luo, Xiaokang Zhang, Zeyao Ma","submitted_at":"2025-01-02T04:33:31Z","abstract_excerpt":"Current large language models (LLMs) often struggle to produce accurate responses on the first attempt for complex reasoning tasks like code generation. Prior research tackles this challenge by generating multiple candidate solutions and validating them with LLM-generated unit tests. The execution results of unit tests serve as reward signals to identify correct solutions. As LLMs always confidently make mistakes, these unit tests are not reliable, thereby diminishing the quality of reward signals. Motivated by the observation that scaling the number of solutions improves LLM performance, we e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01054","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/2501.01054/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":"2026-07-05T09:56:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AUEl6Br/RDxCm8g/VD/UXPBWS5Gwe5c8Z3Wd9KkDDOjCzx6Neygvdx0LRcuJ/3qKz2entuKEEWckIMngqGumCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:48:24.169718Z"},"content_sha256":"26eb12d97580d2fba1116177bb66c9ec16e9c4207065e7b8ec3d853b9e398609","schema_version":"1.0","event_id":"sha256:26eb12d97580d2fba1116177bb66c9ec16e9c4207065e7b8ec3d853b9e398609"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NETQRCQWEJD6OAXLKV3JKFZHUP/bundle.json","state_url":"https://pith.science/pith/NETQRCQWEJD6OAXLKV3JKFZHUP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NETQRCQWEJD6OAXLKV3JKFZHUP/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":"2026-07-09T04:48:24Z","links":{"resolver":"https://pith.science/pith/NETQRCQWEJD6OAXLKV3JKFZHUP","bundle":"https://pith.science/pith/NETQRCQWEJD6OAXLKV3JKFZHUP/bundle.json","state":"https://pith.science/pith/NETQRCQWEJD6OAXLKV3JKFZHUP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NETQRCQWEJD6OAXLKV3JKFZHUP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NETQRCQWEJD6OAXLKV3JKFZHUP","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":"232b6fe5be8e89aeb7302a482ba6225e3d5281492be1d7e1bcf367232e20f02c","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T04:33:31Z","title_canon_sha256":"7bb3263b72703751df1c58f4f57ea22d3553aeae7f5683ba989c779f545f101f"},"schema_version":"1.0","source":{"id":"2501.01054","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01054","created_at":"2026-07-05T09:56:13Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01054v1","created_at":"2026-07-05T09:56:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01054","created_at":"2026-07-05T09:56:13Z"},{"alias_kind":"pith_short_12","alias_value":"NETQRCQWEJD6","created_at":"2026-07-05T09:56:13Z"},{"alias_kind":"pith_short_16","alias_value":"NETQRCQWEJD6OAXL","created_at":"2026-07-05T09:56:13Z"},{"alias_kind":"pith_short_8","alias_value":"NETQRCQW","created_at":"2026-07-05T09:56:13Z"}],"graph_snapshots":[{"event_id":"sha256:26eb12d97580d2fba1116177bb66c9ec16e9c4207065e7b8ec3d853b9e398609","target":"graph","created_at":"2026-07-05T09:56:13Z","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/2501.01054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current large language models (LLMs) often struggle to produce accurate responses on the first attempt for complex reasoning tasks like code generation. Prior research tackles this challenge by generating multiple candidate solutions and validating them with LLM-generated unit tests. The execution results of unit tests serve as reward signals to identify correct solutions. As LLMs always confidently make mistakes, these unit tests are not reliable, thereby diminishing the quality of reward signals. Motivated by the observation that scaling the number of solutions improves LLM performance, we e","authors_text":"Jie Tang, Jifan Yu, Jing Zhang, Sijia Luo, Xiaokang Zhang, Zeyao Ma","cross_cats":["cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T04:33:31Z","title":"Dynamic Scaling of Unit Tests for Code Reward Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01054","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":"sha256:0ce22628665ed679a6c5fc5a336122308acfa4398e87c78dc3c2fc2afcbb3e25","target":"record","created_at":"2026-07-05T09:56:13Z","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":"232b6fe5be8e89aeb7302a482ba6225e3d5281492be1d7e1bcf367232e20f02c","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T04:33:31Z","title_canon_sha256":"7bb3263b72703751df1c58f4f57ea22d3553aeae7f5683ba989c779f545f101f"},"schema_version":"1.0","source":{"id":"2501.01054","kind":"arxiv","version":1}},"canonical_sha256":"6927088a162247e702eb5576951727a3f5041cc06446fdc0c45a0a836a9a2674","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6927088a162247e702eb5576951727a3f5041cc06446fdc0c45a0a836a9a2674","first_computed_at":"2026-07-05T09:56:13.629717Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:13.629717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CNKO1ZMsV0VEshVRkbnKbNN+dTXa0L67K9sHYqrDVcNipSnsoS8OpTlI8nqM+aGNQqMJjLI8YesrERY0GoH6CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:13.630131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01054","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ce22628665ed679a6c5fc5a336122308acfa4398e87c78dc3c2fc2afcbb3e25","sha256:26eb12d97580d2fba1116177bb66c9ec16e9c4207065e7b8ec3d853b9e398609"],"state_sha256":"28dcdcc57ff1a0f9ac78b4ce99dc9790357db84f9577d4e829c4578186d27c30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qW7m1OUsJBriiNxvGQV7K4K/ZyT3KsMMCABKvxDLrsDZWuGqriD2/rahhuqanMi1Wpxqube6gaPCtyzuaokVCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:48:24.171722Z","bundle_sha256":"2b16264d88b93223eb70d39185c72f29acb167ec20e24104608e17fcd65bb04f"}}