{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XL5ODWNSEOQXGRDEUAY4K2LQE4","short_pith_number":"pith:XL5ODWNS","canonical_record":{"source":{"id":"2503.04149","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-06T06:56:59Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c5495b47c66563d366ddd00741061131fbc70fa7a97b5fd411d29dcaa2da09a6","abstract_canon_sha256":"2d381ed3dc9bab30d278ca61c5b5e9933a533ccb21f05ff3b767cc6b230c1aa5"},"schema_version":"1.0"},"canonical_sha256":"bafae1d9b223a1734464a031c56970272a7f43a76f1bb2525583feb93542368e","source":{"kind":"arxiv","id":"2503.04149","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04149","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04149v2","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04149","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"pith_short_12","alias_value":"XL5ODWNSEOQX","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"pith_short_16","alias_value":"XL5ODWNSEOQXGRDE","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"pith_short_8","alias_value":"XL5ODWNS","created_at":"2026-07-05T11:15:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XL5ODWNSEOQXGRDEUAY4K2LQE4","target":"record","payload":{"canonical_record":{"source":{"id":"2503.04149","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-06T06:56:59Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c5495b47c66563d366ddd00741061131fbc70fa7a97b5fd411d29dcaa2da09a6","abstract_canon_sha256":"2d381ed3dc9bab30d278ca61c5b5e9933a533ccb21f05ff3b767cc6b230c1aa5"},"schema_version":"1.0"},"canonical_sha256":"bafae1d9b223a1734464a031c56970272a7f43a76f1bb2525583feb93542368e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:19.947802Z","signature_b64":"GF6ODksSn5+4leLuu8zr8oTI80oSqhKUkAzW6s9rz6lh+i2uE0uZNwLxDxppDoZvLGFuDqZMvo6/4TpkoLkuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bafae1d9b223a1734464a031c56970272a7f43a76f1bb2525583feb93542368e","last_reissued_at":"2026-07-05T11:15:19.947259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:19.947259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.04149","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZSlZ1tzqqGzXrwPLnmT6qKVOGMW0XiNsDf3Fqp+Jx5frqY7HOT19q6wnq4xxs1jmkhBePca0HTB3nHoixTlyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T08:53:16.890386Z"},"content_sha256":"afdf06c3f387c817acbbed271920a5f45aa23a197f25612a8c95c0bb8f2cf401","schema_version":"1.0","event_id":"sha256:afdf06c3f387c817acbbed271920a5f45aa23a197f25612a8c95c0bb8f2cf401"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XL5ODWNSEOQXGRDEUAY4K2LQE4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Baishakhi Ray, Pranav Pusarla, Simin Chen","submitted_at":"2025-03-06T06:56:59Z","abstract_excerpt":"The rapid evolution of code largelanguage models underscores the need for effective and transparent benchmarking of their reasoning capabilities. However, the current benchmarking approach heavily depends on publicly available, human-created datasets. The widespread use of these fixed benchmark datasets makes the benchmarking process to be static and thus particularly susceptible to data contamination, an unavoidable consequence of the extensive data collection processes used to train Code LLMs. Existing approaches that address data contamination often suffer from human effort limitations and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04149","kind":"arxiv","version":2},"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/2503.04149/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":"2026-07-05T11:15:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qIV8RWGpEj+Ueju793D+RFPQaeO2kBGywJcNZ9hAlOTTQlcQ3qohKXdtEMsPIkmkn/caghCmMuNcE6snvu23Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T08:53:16.891280Z"},"content_sha256":"5d88d8c57507a01bbe877e1d54d5f2bb2871f8b226d40ee0f0bcc2a1f4a98a66","schema_version":"1.0","event_id":"sha256:5d88d8c57507a01bbe877e1d54d5f2bb2871f8b226d40ee0f0bcc2a1f4a98a66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XL5ODWNSEOQXGRDEUAY4K2LQE4/bundle.json","state_url":"https://pith.science/pith/XL5ODWNSEOQXGRDEUAY4K2LQE4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XL5ODWNSEOQXGRDEUAY4K2LQE4/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":"2026-08-20T08:53:16Z","links":{"resolver":"https://pith.science/pith/XL5ODWNSEOQXGRDEUAY4K2LQE4","bundle":"https://pith.science/pith/XL5ODWNSEOQXGRDEUAY4K2LQE4/bundle.json","state":"https://pith.science/pith/XL5ODWNSEOQXGRDEUAY4K2LQE4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XL5ODWNSEOQXGRDEUAY4K2LQE4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XL5ODWNSEOQXGRDEUAY4K2LQE4","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":"2d381ed3dc9bab30d278ca61c5b5e9933a533ccb21f05ff3b767cc6b230c1aa5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-06T06:56:59Z","title_canon_sha256":"c5495b47c66563d366ddd00741061131fbc70fa7a97b5fd411d29dcaa2da09a6"},"schema_version":"1.0","source":{"id":"2503.04149","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04149","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04149v2","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04149","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"pith_short_12","alias_value":"XL5ODWNSEOQX","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"pith_short_16","alias_value":"XL5ODWNSEOQXGRDE","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"pith_short_8","alias_value":"XL5ODWNS","created_at":"2026-07-05T11:15:19Z"}],"graph_snapshots":[{"event_id":"sha256:5d88d8c57507a01bbe877e1d54d5f2bb2871f8b226d40ee0f0bcc2a1f4a98a66","target":"graph","created_at":"2026-07-05T11:15:19Z","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/2503.04149/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid evolution of code largelanguage models underscores the need for effective and transparent benchmarking of their reasoning capabilities. However, the current benchmarking approach heavily depends on publicly available, human-created datasets. The widespread use of these fixed benchmark datasets makes the benchmarking process to be static and thus particularly susceptible to data contamination, an unavoidable consequence of the extensive data collection processes used to train Code LLMs. Existing approaches that address data contamination often suffer from human effort limitations and ","authors_text":"Baishakhi Ray, Pranav Pusarla, Simin Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-06T06:56:59Z","title":"Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04149","kind":"arxiv","version":2},"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:afdf06c3f387c817acbbed271920a5f45aa23a197f25612a8c95c0bb8f2cf401","target":"record","created_at":"2026-07-05T11:15:19Z","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":"2d381ed3dc9bab30d278ca61c5b5e9933a533ccb21f05ff3b767cc6b230c1aa5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-06T06:56:59Z","title_canon_sha256":"c5495b47c66563d366ddd00741061131fbc70fa7a97b5fd411d29dcaa2da09a6"},"schema_version":"1.0","source":{"id":"2503.04149","kind":"arxiv","version":2}},"canonical_sha256":"bafae1d9b223a1734464a031c56970272a7f43a76f1bb2525583feb93542368e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bafae1d9b223a1734464a031c56970272a7f43a76f1bb2525583feb93542368e","first_computed_at":"2026-07-05T11:15:19.947259Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:19.947259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GF6ODksSn5+4leLuu8zr8oTI80oSqhKUkAzW6s9rz6lh+i2uE0uZNwLxDxppDoZvLGFuDqZMvo6/4TpkoLkuDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:19.947802Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04149","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afdf06c3f387c817acbbed271920a5f45aa23a197f25612a8c95c0bb8f2cf401","sha256:5d88d8c57507a01bbe877e1d54d5f2bb2871f8b226d40ee0f0bcc2a1f4a98a66"],"state_sha256":"b842a86588b5a56f93bc3877655184c8c811daaced32757ae7cf1dc584b4b8e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ayv10Eb3f4NFy/vlNXz+tjM46LLaNXRYioASK0Cflw3QKHcSdgaJuoeeR7hct+n4jNe4VvtNQyAjXEFk+cynBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T08:53:16.898772Z","bundle_sha256":"32e32795910c01941c3853bc6a3e3f0f2925965822be61a0f1e9e9b6f6672668"}}