{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OQPXG764FILLM4WZEJNG52EPLI","short_pith_number":"pith:OQPXG764","canonical_record":{"source":{"id":"2605.17958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T07:12:44Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"a81e6b5f78533d0b79a8b80688eee425d41ae179f7898530cf8d7100c7fcfeab","abstract_canon_sha256":"df3d33dd823b59e1290846cd55b1bc868040c340e7af2f7336bf2ff2ea7ef86a"},"schema_version":"1.0"},"canonical_sha256":"741f737fdc2a16b672d9225a6ee88f5a1359c3dde4569d1fadacd5383629934d","source":{"kind":"arxiv","id":"2605.17958","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17958","created_at":"2026-05-20T00:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17958v1","created_at":"2026-05-20T00:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17958","created_at":"2026-05-20T00:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"OQPXG764FILL","created_at":"2026-05-20T00:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"OQPXG764FILLM4WZ","created_at":"2026-05-20T00:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"OQPXG764","created_at":"2026-05-20T00:05:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OQPXG764FILLM4WZEJNG52EPLI","target":"record","payload":{"canonical_record":{"source":{"id":"2605.17958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T07:12:44Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"a81e6b5f78533d0b79a8b80688eee425d41ae179f7898530cf8d7100c7fcfeab","abstract_canon_sha256":"df3d33dd823b59e1290846cd55b1bc868040c340e7af2f7336bf2ff2ea7ef86a"},"schema_version":"1.0"},"canonical_sha256":"741f737fdc2a16b672d9225a6ee88f5a1359c3dde4569d1fadacd5383629934d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:08.164668Z","signature_b64":"8IynFdAWH77GZkjoqccWHlYGPOErrb4HRQ7Do9CvJaJLiG14SHz6iFQYvdQkps2yLZNKy6GrupG3wADaHpgZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"741f737fdc2a16b672d9225a6ee88f5a1359c3dde4569d1fadacd5383629934d","last_reissued_at":"2026-05-20T00:05:08.163762Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:08.163762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.17958","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":"2026-05-20T00:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xNVZFO5iUkI+rSeQThKKyAjI2t3f+0F9uqMCRATAYwCd1RhBKMZ+ke9A9nkOq2Q3UHP7XJyUL9dhL9sge/XzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T03:15:40.540437Z"},"content_sha256":"458a81b2fc4dea0840b0e43ee5231790064e7b7beca7ceef169e49dffe8baddf","schema_version":"1.0","event_id":"sha256:458a81b2fc4dea0840b0e43ee5231790064e7b7beca7ceef169e49dffe8baddf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OQPXG764FILLM4WZEJNG52EPLI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.LG","authors_text":"Cuiyun Gao, Dianbo Sui, Jia Feng, Qing Liao, Yibo Lyu, Yun Peng, Zhanyue Qin","submitted_at":"2026-05-18T07:12:44Z","abstract_excerpt":"Code reasoning refers to the task of predicting the output of a program given its source code and specific inputs. It can measure the reasoning capability of large language models (LLMs) and also benefit downstream tasks such as code generation and mathematical reasoning. Existing work has verified the effectiveness of reinforcement learning on the task. However, these methods design rewards solely based on final outputs or coarse-grained signals, and neglect the inherent consistency of the stepwise reasoning process in the task. Therefore, these methods often result in sparse reward or reward"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17958","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/2605.17958/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.589683Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d7ae6b5052728f77a1092f7df68e60cfc260d8e5396a71438cbf2c97846eca1c"},"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":"2026-05-20T00:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eSDUCjRSaPK92e2bPF6JjCCciMGT5ZO2S9QGZ4QtIRA1ZBmeuNJhbk/h4J/GqoVPhS9Jcpo9JwZKJ6nA5u46Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T03:15:40.541129Z"},"content_sha256":"432f930a9a5130783c60d9a137f48f17a22373fae7f6dacb9c549963895e74cd","schema_version":"1.0","event_id":"sha256:432f930a9a5130783c60d9a137f48f17a22373fae7f6dacb9c549963895e74cd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OQPXG764FILLM4WZEJNG52EPLI/bundle.json","state_url":"https://pith.science/pith/OQPXG764FILLM4WZEJNG52EPLI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OQPXG764FILLM4WZEJNG52EPLI/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":"2026-05-22T03:15:40Z","links":{"resolver":"https://pith.science/pith/OQPXG764FILLM4WZEJNG52EPLI","bundle":"https://pith.science/pith/OQPXG764FILLM4WZEJNG52EPLI/bundle.json","state":"https://pith.science/pith/OQPXG764FILLM4WZEJNG52EPLI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OQPXG764FILLM4WZEJNG52EPLI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OQPXG764FILLM4WZEJNG52EPLI","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":"df3d33dd823b59e1290846cd55b1bc868040c340e7af2f7336bf2ff2ea7ef86a","cross_cats_sorted":["cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T07:12:44Z","title_canon_sha256":"a81e6b5f78533d0b79a8b80688eee425d41ae179f7898530cf8d7100c7fcfeab"},"schema_version":"1.0","source":{"id":"2605.17958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17958","created_at":"2026-05-20T00:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17958v1","created_at":"2026-05-20T00:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17958","created_at":"2026-05-20T00:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"OQPXG764FILL","created_at":"2026-05-20T00:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"OQPXG764FILLM4WZ","created_at":"2026-05-20T00:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"OQPXG764","created_at":"2026-05-20T00:05:08Z"}],"graph_snapshots":[{"event_id":"sha256:432f930a9a5130783c60d9a137f48f17a22373fae7f6dacb9c549963895e74cd","target":"graph","created_at":"2026-05-20T00:05:08Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.589683Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.17958/integrity.json","findings":[],"snapshot_sha256":"d7ae6b5052728f77a1092f7df68e60cfc260d8e5396a71438cbf2c97846eca1c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code reasoning refers to the task of predicting the output of a program given its source code and specific inputs. It can measure the reasoning capability of large language models (LLMs) and also benefit downstream tasks such as code generation and mathematical reasoning. Existing work has verified the effectiveness of reinforcement learning on the task. However, these methods design rewards solely based on final outputs or coarse-grained signals, and neglect the inherent consistency of the stepwise reasoning process in the task. Therefore, these methods often result in sparse reward or reward","authors_text":"Cuiyun Gao, Dianbo Sui, Jia Feng, Qing Liao, Yibo Lyu, Yun Peng, Zhanyue Qin","cross_cats":["cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T07:12:44Z","title":"Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17958","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":"sha256:458a81b2fc4dea0840b0e43ee5231790064e7b7beca7ceef169e49dffe8baddf","target":"record","created_at":"2026-05-20T00:05:08Z","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":"df3d33dd823b59e1290846cd55b1bc868040c340e7af2f7336bf2ff2ea7ef86a","cross_cats_sorted":["cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T07:12:44Z","title_canon_sha256":"a81e6b5f78533d0b79a8b80688eee425d41ae179f7898530cf8d7100c7fcfeab"},"schema_version":"1.0","source":{"id":"2605.17958","kind":"arxiv","version":1}},"canonical_sha256":"741f737fdc2a16b672d9225a6ee88f5a1359c3dde4569d1fadacd5383629934d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"741f737fdc2a16b672d9225a6ee88f5a1359c3dde4569d1fadacd5383629934d","first_computed_at":"2026-05-20T00:05:08.163762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:08.163762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8IynFdAWH77GZkjoqccWHlYGPOErrb4HRQ7Do9CvJaJLiG14SHz6iFQYvdQkps2yLZNKy6GrupG3wADaHpgZBQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:08.164668Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:458a81b2fc4dea0840b0e43ee5231790064e7b7beca7ceef169e49dffe8baddf","sha256:432f930a9a5130783c60d9a137f48f17a22373fae7f6dacb9c549963895e74cd"],"state_sha256":"a2dc660fdbc4fdd5eb333407be62ac252b30faa642ab8e15c3c662aaf1380d6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AM94i3fCDDlLd43F+eUM2ORx0H21qqVlQUl6lNumr13as2nq0WCjxBqo5+pw5TrWUgzNGKx88Kz03eIwYrziAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T03:15:40.544549Z","bundle_sha256":"4c5573a91346fe3cb1970a1f00a7f0206823ba2cc794fb0cbf1cf270fbbbe7a3"}}