{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HLVQRJQ2CUKDKHYUDROQ5ILYLP","short_pith_number":"pith:HLVQRJQ2","canonical_record":{"source":{"id":"2311.09707","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T09:35:00Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"4f9a431acb35a6fbde95569b55a68b3ab12e490240784535783511dc24a30b01","abstract_canon_sha256":"e4cb538888fcb7b0fc1c01967bd790f9954bc458253184d66416ceaa75ccc7ce"},"schema_version":"1.0"},"canonical_sha256":"3aeb08a61a1514351f141c5d0ea1785bc6ac78279e0692173304d14dad1d849a","source":{"kind":"arxiv","id":"2311.09707","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09707","created_at":"2026-07-05T07:13:31Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09707v1","created_at":"2026-07-05T07:13:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09707","created_at":"2026-07-05T07:13:31Z"},{"alias_kind":"pith_short_12","alias_value":"HLVQRJQ2CUKD","created_at":"2026-07-05T07:13:31Z"},{"alias_kind":"pith_short_16","alias_value":"HLVQRJQ2CUKDKHYU","created_at":"2026-07-05T07:13:31Z"},{"alias_kind":"pith_short_8","alias_value":"HLVQRJQ2","created_at":"2026-07-05T07:13:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HLVQRJQ2CUKDKHYUDROQ5ILYLP","target":"record","payload":{"canonical_record":{"source":{"id":"2311.09707","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T09:35:00Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"4f9a431acb35a6fbde95569b55a68b3ab12e490240784535783511dc24a30b01","abstract_canon_sha256":"e4cb538888fcb7b0fc1c01967bd790f9954bc458253184d66416ceaa75ccc7ce"},"schema_version":"1.0"},"canonical_sha256":"3aeb08a61a1514351f141c5d0ea1785bc6ac78279e0692173304d14dad1d849a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:31.690619Z","signature_b64":"CWsnbZS8cHyOXTJ2B0RyX6IpKP2O4u+j4zMVbunGerTDU6+JryFcrs69yVYkyNlbmH5diDVcaT5aNg8TBEsMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3aeb08a61a1514351f141c5d0ea1785bc6ac78279e0692173304d14dad1d849a","last_reissued_at":"2026-07-05T07:13:31.690123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:31.690123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.09707","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":"2026-07-05T07:13:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RoJ2TgTL3ALma75Tit16ilGYoWHijhe7Zn5FRvyts6g9b7J1XJX686JFpeeHsLwvSuGQUe3ZDTtO0jXmBOJQBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:32:19.495169Z"},"content_sha256":"ba4ee5c6bf97cffbcec8bb101d57e17074cc6ff0e5deeeb4c172b3b90535e96f","schema_version":"1.0","event_id":"sha256:ba4ee5c6bf97cffbcec8bb101d57e17074cc6ff0e5deeeb4c172b3b90535e96f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HLVQRJQ2CUKDKHYUDROQ5ILYLP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.CL","authors_text":"Abdelhalim Dahou, Andor Diera, Ansgar Scherp, Fabian Karl, Florian Sihler, Lukas Galke","submitted_at":"2023-11-16T09:35:00Z","abstract_excerpt":"Language models can serve as a valuable tool for software developers to increase productivity. Large generative models can be used for code generation and code completion, while smaller encoder-only models are capable of performing code search tasks using natural language queries.These capabilities are heavily influenced by the quality and diversity of the available training data. Source code datasets used for training usually focus on the most popular languages and testing is mostly conducted on the same distributions, often overlooking low-resource programming languages. Motivated by the NLP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09707","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/2311.09707/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":"2026-07-05T07:13:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GodCd/S9V5UsGxC/Gw24FRYjSjhn7Fk8ZI8CuczGQyj7wobwbY7HHxHK9GyU/FSM3RNyQadBh3u3CR7QWTLqDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:32:19.495699Z"},"content_sha256":"af20bb011d2f0af661ae8a3ee3077a99412efa0e52c5cdefb0d2f17d3e042f89","schema_version":"1.0","event_id":"sha256:af20bb011d2f0af661ae8a3ee3077a99412efa0e52c5cdefb0d2f17d3e042f89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HLVQRJQ2CUKDKHYUDROQ5ILYLP/bundle.json","state_url":"https://pith.science/pith/HLVQRJQ2CUKDKHYUDROQ5ILYLP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HLVQRJQ2CUKDKHYUDROQ5ILYLP/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":"2026-08-10T11:32:19Z","links":{"resolver":"https://pith.science/pith/HLVQRJQ2CUKDKHYUDROQ5ILYLP","bundle":"https://pith.science/pith/HLVQRJQ2CUKDKHYUDROQ5ILYLP/bundle.json","state":"https://pith.science/pith/HLVQRJQ2CUKDKHYUDROQ5ILYLP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HLVQRJQ2CUKDKHYUDROQ5ILYLP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HLVQRJQ2CUKDKHYUDROQ5ILYLP","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":"e4cb538888fcb7b0fc1c01967bd790f9954bc458253184d66416ceaa75ccc7ce","cross_cats_sorted":["cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T09:35:00Z","title_canon_sha256":"4f9a431acb35a6fbde95569b55a68b3ab12e490240784535783511dc24a30b01"},"schema_version":"1.0","source":{"id":"2311.09707","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09707","created_at":"2026-07-05T07:13:31Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09707v1","created_at":"2026-07-05T07:13:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09707","created_at":"2026-07-05T07:13:31Z"},{"alias_kind":"pith_short_12","alias_value":"HLVQRJQ2CUKD","created_at":"2026-07-05T07:13:31Z"},{"alias_kind":"pith_short_16","alias_value":"HLVQRJQ2CUKDKHYU","created_at":"2026-07-05T07:13:31Z"},{"alias_kind":"pith_short_8","alias_value":"HLVQRJQ2","created_at":"2026-07-05T07:13:31Z"}],"graph_snapshots":[{"event_id":"sha256:af20bb011d2f0af661ae8a3ee3077a99412efa0e52c5cdefb0d2f17d3e042f89","target":"graph","created_at":"2026-07-05T07:13:31Z","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/2311.09707/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models can serve as a valuable tool for software developers to increase productivity. Large generative models can be used for code generation and code completion, while smaller encoder-only models are capable of performing code search tasks using natural language queries.These capabilities are heavily influenced by the quality and diversity of the available training data. Source code datasets used for training usually focus on the most popular languages and testing is mostly conducted on the same distributions, often overlooking low-resource programming languages. Motivated by the NLP","authors_text":"Abdelhalim Dahou, Andor Diera, Ansgar Scherp, Fabian Karl, Florian Sihler, Lukas Galke","cross_cats":["cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T09:35:00Z","title":"GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09707","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:ba4ee5c6bf97cffbcec8bb101d57e17074cc6ff0e5deeeb4c172b3b90535e96f","target":"record","created_at":"2026-07-05T07:13:31Z","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":"e4cb538888fcb7b0fc1c01967bd790f9954bc458253184d66416ceaa75ccc7ce","cross_cats_sorted":["cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T09:35:00Z","title_canon_sha256":"4f9a431acb35a6fbde95569b55a68b3ab12e490240784535783511dc24a30b01"},"schema_version":"1.0","source":{"id":"2311.09707","kind":"arxiv","version":1}},"canonical_sha256":"3aeb08a61a1514351f141c5d0ea1785bc6ac78279e0692173304d14dad1d849a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3aeb08a61a1514351f141c5d0ea1785bc6ac78279e0692173304d14dad1d849a","first_computed_at":"2026-07-05T07:13:31.690123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:13:31.690123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CWsnbZS8cHyOXTJ2B0RyX6IpKP2O4u+j4zMVbunGerTDU6+JryFcrs69yVYkyNlbmH5diDVcaT5aNg8TBEsMDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:13:31.690619Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09707","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba4ee5c6bf97cffbcec8bb101d57e17074cc6ff0e5deeeb4c172b3b90535e96f","sha256:af20bb011d2f0af661ae8a3ee3077a99412efa0e52c5cdefb0d2f17d3e042f89"],"state_sha256":"2c7adc2f737fd855c4148c55e396c33bdc2751f0413bb6b831c57517fba4baf1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S8YD2DQncYzgGFkVuhuBjHl6CVUheCyyk9MRYPw5fwFiEvFX0eWpwQQBYMX8fMidhwYRSFoQAjzYLO/hj89wCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:32:19.499979Z","bundle_sha256":"a0ddf8f025627a124ec98752d6747f5616061d09687fc02b342f1f5c46b2e118"}}