{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WTU2NKKIJUX6ZOI6FCYHYDUMTC","short_pith_number":"pith:WTU2NKKI","canonical_record":{"source":{"id":"2501.09653","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-16T16:48:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d27eefaa4ff1f4e9afa5984af00dfe1114ecfd3f5973dce6e090611868a40671","abstract_canon_sha256":"59dab39dc31cd4f07d7dac7e8d9e9a4bf12d6e785f9d43d9ee0eb2ee4c53ea58"},"schema_version":"1.0"},"canonical_sha256":"b4e9a6a9484d2fecb91e28b07c0e8c98a8110831337ebee512fe559bb75104c8","source":{"kind":"arxiv","id":"2501.09653","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09653","created_at":"2026-07-17T01:20:34Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09653v2","created_at":"2026-07-17T01:20:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09653","created_at":"2026-07-17T01:20:34Z"},{"alias_kind":"pith_short_12","alias_value":"WTU2NKKIJUX6","created_at":"2026-07-17T01:20:34Z"},{"alias_kind":"pith_short_16","alias_value":"WTU2NKKIJUX6ZOI6","created_at":"2026-07-17T01:20:34Z"},{"alias_kind":"pith_short_8","alias_value":"WTU2NKKI","created_at":"2026-07-17T01:20:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WTU2NKKIJUX6ZOI6FCYHYDUMTC","target":"record","payload":{"canonical_record":{"source":{"id":"2501.09653","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-16T16:48:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d27eefaa4ff1f4e9afa5984af00dfe1114ecfd3f5973dce6e090611868a40671","abstract_canon_sha256":"59dab39dc31cd4f07d7dac7e8d9e9a4bf12d6e785f9d43d9ee0eb2ee4c53ea58"},"schema_version":"1.0"},"canonical_sha256":"b4e9a6a9484d2fecb91e28b07c0e8c98a8110831337ebee512fe559bb75104c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:20:34.270009Z","signature_b64":"0kYTB1yGyvAVBJ/iJ6vpHnsW53cKqpeodpSAVvgUL5YrcoeCHDjAk08twi3mOh/Cd6zuAX7S+wfvXLnuGfEsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4e9a6a9484d2fecb91e28b07c0e8c98a8110831337ebee512fe559bb75104c8","last_reissued_at":"2026-07-17T01:20:34.268992Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:20:34.268992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.09653","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":"2026-07-17T01:20:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ye9RIvdJkFJLn4yjH0hcThXPUnsYzpoidaTTbMW9VKBu+IYCb/65vGGYesNgZdVAGGG+kfwQp5k0gM2B/9OnBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:02:17.968130Z"},"content_sha256":"1a03745bee21d4f378fd17298447d9d54d99dc9e32c69c1dda31aa9647a901cf","schema_version":"1.0","event_id":"sha256:1a03745bee21d4f378fd17298447d9d54d99dc9e32c69c1dda31aa9647a901cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WTU2NKKIJUX6ZOI6FCYHYDUMTC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Heap: A Contamination-Free Multilingual Code Dataset for Evaluating Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arie van Deursen, Jonathan Katzy, Maliheh Izadi, Razvan Mihai Popescu","submitted_at":"2025-01-16T16:48:41Z","abstract_excerpt":"The recent rise in the popularity of large language models has spurred the development of extensive code datasets needed to train them. This has left limited code available for collection and use in the downstream investigation of specific behaviors, or evaluation of large language models without suffering from data contamination. To address this problem, we release The Heap, a large multilingual dataset covering 57 programming languages that has been deduplicated with respect to other open datasets of code, enabling researchers to conduct fair evaluations of large language models without sign"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09653","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/2501.09653/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":"2026-07-17T01:20:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+FiMJz1owjuU+MzdO6/W9P6L27021F8pUryQB0RoIZ2Yb1Kx1US/CdzuYH/A/KQO9SYRn8xQZz30X5NU+sgMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:02:17.968678Z"},"content_sha256":"d19422f0ade84a069a70077b01c7107ee0d0042fd00f4394d554ea496b63d201","schema_version":"1.0","event_id":"sha256:d19422f0ade84a069a70077b01c7107ee0d0042fd00f4394d554ea496b63d201"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WTU2NKKIJUX6ZOI6FCYHYDUMTC/bundle.json","state_url":"https://pith.science/pith/WTU2NKKIJUX6ZOI6FCYHYDUMTC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WTU2NKKIJUX6ZOI6FCYHYDUMTC/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":"2026-08-18T03:02:17Z","links":{"resolver":"https://pith.science/pith/WTU2NKKIJUX6ZOI6FCYHYDUMTC","bundle":"https://pith.science/pith/WTU2NKKIJUX6ZOI6FCYHYDUMTC/bundle.json","state":"https://pith.science/pith/WTU2NKKIJUX6ZOI6FCYHYDUMTC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WTU2NKKIJUX6ZOI6FCYHYDUMTC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WTU2NKKIJUX6ZOI6FCYHYDUMTC","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":"59dab39dc31cd4f07d7dac7e8d9e9a4bf12d6e785f9d43d9ee0eb2ee4c53ea58","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-16T16:48:41Z","title_canon_sha256":"d27eefaa4ff1f4e9afa5984af00dfe1114ecfd3f5973dce6e090611868a40671"},"schema_version":"1.0","source":{"id":"2501.09653","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09653","created_at":"2026-07-17T01:20:34Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09653v2","created_at":"2026-07-17T01:20:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09653","created_at":"2026-07-17T01:20:34Z"},{"alias_kind":"pith_short_12","alias_value":"WTU2NKKIJUX6","created_at":"2026-07-17T01:20:34Z"},{"alias_kind":"pith_short_16","alias_value":"WTU2NKKIJUX6ZOI6","created_at":"2026-07-17T01:20:34Z"},{"alias_kind":"pith_short_8","alias_value":"WTU2NKKI","created_at":"2026-07-17T01:20:34Z"}],"graph_snapshots":[{"event_id":"sha256:d19422f0ade84a069a70077b01c7107ee0d0042fd00f4394d554ea496b63d201","target":"graph","created_at":"2026-07-17T01:20:34Z","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/2501.09653/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent rise in the popularity of large language models has spurred the development of extensive code datasets needed to train them. This has left limited code available for collection and use in the downstream investigation of specific behaviors, or evaluation of large language models without suffering from data contamination. To address this problem, we release The Heap, a large multilingual dataset covering 57 programming languages that has been deduplicated with respect to other open datasets of code, enabling researchers to conduct fair evaluations of large language models without sign","authors_text":"Arie van Deursen, Jonathan Katzy, Maliheh Izadi, Razvan Mihai Popescu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-16T16:48:41Z","title":"The Heap: A Contamination-Free Multilingual Code Dataset for Evaluating Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09653","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":"sha256:1a03745bee21d4f378fd17298447d9d54d99dc9e32c69c1dda31aa9647a901cf","target":"record","created_at":"2026-07-17T01:20:34Z","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":"59dab39dc31cd4f07d7dac7e8d9e9a4bf12d6e785f9d43d9ee0eb2ee4c53ea58","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-16T16:48:41Z","title_canon_sha256":"d27eefaa4ff1f4e9afa5984af00dfe1114ecfd3f5973dce6e090611868a40671"},"schema_version":"1.0","source":{"id":"2501.09653","kind":"arxiv","version":2}},"canonical_sha256":"b4e9a6a9484d2fecb91e28b07c0e8c98a8110831337ebee512fe559bb75104c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4e9a6a9484d2fecb91e28b07c0e8c98a8110831337ebee512fe559bb75104c8","first_computed_at":"2026-07-17T01:20:34.268992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:20:34.268992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0kYTB1yGyvAVBJ/iJ6vpHnsW53cKqpeodpSAVvgUL5YrcoeCHDjAk08twi3mOh/Cd6zuAX7S+wfvXLnuGfEsDw==","signature_status":"signed_v1","signed_at":"2026-07-17T01:20:34.270009Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09653","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a03745bee21d4f378fd17298447d9d54d99dc9e32c69c1dda31aa9647a901cf","sha256:d19422f0ade84a069a70077b01c7107ee0d0042fd00f4394d554ea496b63d201"],"state_sha256":"e2f0a528433c0c5e119bb981b7fbf155973ddfd0d49fd74a5fa438c3e424fe00"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Aul3DIXlG597LckNlenNLKbMqocTAWOYLOcyd6FwVD4uTWLr/b1wb2sCydII6UxXUGHU5tUx3pVycn4PH7kEDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T03:02:17.974128Z","bundle_sha256":"c200bd602233b24df76b48a5a5f395ea2afeff6dfc8c3f34285ba07263c3e99d"}}