{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TFHZ3UUGUNSAA4CODCKKHPWKDM","short_pith_number":"pith:TFHZ3UUG","canonical_record":{"source":{"id":"2004.09015","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-20T01:45:27Z","cross_cats_sorted":[],"title_canon_sha256":"0b03ae062cb71b25291dea0ed6f10aa46d68a3d189b7c6aa887f6bc38b3cce64","abstract_canon_sha256":"b98d9b3f13a86fc862e0b81c95963a8bfcd75ed4cd1293a24d5d5517354d309d"},"schema_version":"1.0"},"canonical_sha256":"994f9dd286a36400704e1894a3beca1b303dbf9877d50d48d5fdddb7f8f1164d","source":{"kind":"arxiv","id":"2004.09015","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.09015","created_at":"2026-07-05T00:56:12Z"},{"alias_kind":"arxiv_version","alias_value":"2004.09015v1","created_at":"2026-07-05T00:56:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.09015","created_at":"2026-07-05T00:56:12Z"},{"alias_kind":"pith_short_12","alias_value":"TFHZ3UUGUNSA","created_at":"2026-07-05T00:56:12Z"},{"alias_kind":"pith_short_16","alias_value":"TFHZ3UUGUNSAA4CO","created_at":"2026-07-05T00:56:12Z"},{"alias_kind":"pith_short_8","alias_value":"TFHZ3UUG","created_at":"2026-07-05T00:56:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TFHZ3UUGUNSAA4CODCKKHPWKDM","target":"record","payload":{"canonical_record":{"source":{"id":"2004.09015","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-20T01:45:27Z","cross_cats_sorted":[],"title_canon_sha256":"0b03ae062cb71b25291dea0ed6f10aa46d68a3d189b7c6aa887f6bc38b3cce64","abstract_canon_sha256":"b98d9b3f13a86fc862e0b81c95963a8bfcd75ed4cd1293a24d5d5517354d309d"},"schema_version":"1.0"},"canonical_sha256":"994f9dd286a36400704e1894a3beca1b303dbf9877d50d48d5fdddb7f8f1164d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:56:12.296956Z","signature_b64":"Z/cg7sBHw+8yEkOEAls6UjnkOIL6biMQl6i18elGK7xcsVpiz7z3gVpxtENRbSd3bOWcNEihqOF89mldwRiEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"994f9dd286a36400704e1894a3beca1b303dbf9877d50d48d5fdddb7f8f1164d","last_reissued_at":"2026-07-05T00:56:12.296473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:56:12.296473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.09015","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":"2026-07-05T00:56:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YsefS/UCsLm1Hap1WVmFo/1V7kUu3VeQlaSW3C8GT8BoGxpnadW43LTfdKQ/Fq4FAtHDjKHHgwkDC8U/5Z4jAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:58:29.267543Z"},"content_sha256":"8c784f0c8a077151fe7502a582d6d22f9ab3a094c8a0fe06ff31cc13626fee35","schema_version":"1.0","event_id":"sha256:8c784f0c8a077151fe7502a582d6d22f9ab3a094c8a0fe06ff31cc13626fee35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TFHZ3UUGUNSAA4CODCKKHPWKDM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Incorporating External Knowledge through Pre-training for Natural Language to Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bogdan Vasilescu, Frank F. Xu, Graham Neubig, Pengcheng Yin, Zhengbao Jiang","submitted_at":"2020-04-20T01:45:27Z","abstract_excerpt":"Open-domain code generation aims to generate code in a general-purpose programming language (such as Python) from natural language (NL) intents. Motivated by the intuition that developers usually retrieve resources on the web when writing code, we explore the effectiveness of incorporating two varieties of external knowledge into NL-to-code generation: automatically mined NL-code pairs from the online programming QA forum StackOverflow and programming language API documentation. Our evaluations show that combining the two sources with data augmentation and retrieval-based data re-sampling impr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.09015","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/2004.09015/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":"2026-07-05T00:56:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RwoDJ0J2dvafVfAhCvAtL0DwhwqKTT7/QQ8uTdj0FpzwcKGQ7g2g/stCSzlFcHZ295aO5MfR9K/O48NP73/VAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:58:29.272099Z"},"content_sha256":"5cfbe369d216870bab91853550db2a1bd7c093fd8b9af9c7327a56bbffe00554","schema_version":"1.0","event_id":"sha256:5cfbe369d216870bab91853550db2a1bd7c093fd8b9af9c7327a56bbffe00554"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TFHZ3UUGUNSAA4CODCKKHPWKDM/bundle.json","state_url":"https://pith.science/pith/TFHZ3UUGUNSAA4CODCKKHPWKDM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TFHZ3UUGUNSAA4CODCKKHPWKDM/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":"2026-07-06T20:58:29Z","links":{"resolver":"https://pith.science/pith/TFHZ3UUGUNSAA4CODCKKHPWKDM","bundle":"https://pith.science/pith/TFHZ3UUGUNSAA4CODCKKHPWKDM/bundle.json","state":"https://pith.science/pith/TFHZ3UUGUNSAA4CODCKKHPWKDM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TFHZ3UUGUNSAA4CODCKKHPWKDM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TFHZ3UUGUNSAA4CODCKKHPWKDM","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":"b98d9b3f13a86fc862e0b81c95963a8bfcd75ed4cd1293a24d5d5517354d309d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-20T01:45:27Z","title_canon_sha256":"0b03ae062cb71b25291dea0ed6f10aa46d68a3d189b7c6aa887f6bc38b3cce64"},"schema_version":"1.0","source":{"id":"2004.09015","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.09015","created_at":"2026-07-05T00:56:12Z"},{"alias_kind":"arxiv_version","alias_value":"2004.09015v1","created_at":"2026-07-05T00:56:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.09015","created_at":"2026-07-05T00:56:12Z"},{"alias_kind":"pith_short_12","alias_value":"TFHZ3UUGUNSA","created_at":"2026-07-05T00:56:12Z"},{"alias_kind":"pith_short_16","alias_value":"TFHZ3UUGUNSAA4CO","created_at":"2026-07-05T00:56:12Z"},{"alias_kind":"pith_short_8","alias_value":"TFHZ3UUG","created_at":"2026-07-05T00:56:12Z"}],"graph_snapshots":[{"event_id":"sha256:5cfbe369d216870bab91853550db2a1bd7c093fd8b9af9c7327a56bbffe00554","target":"graph","created_at":"2026-07-05T00:56:12Z","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/2004.09015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-domain code generation aims to generate code in a general-purpose programming language (such as Python) from natural language (NL) intents. Motivated by the intuition that developers usually retrieve resources on the web when writing code, we explore the effectiveness of incorporating two varieties of external knowledge into NL-to-code generation: automatically mined NL-code pairs from the online programming QA forum StackOverflow and programming language API documentation. Our evaluations show that combining the two sources with data augmentation and retrieval-based data re-sampling impr","authors_text":"Bogdan Vasilescu, Frank F. Xu, Graham Neubig, Pengcheng Yin, Zhengbao Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-20T01:45:27Z","title":"Incorporating External Knowledge through Pre-training for Natural Language to Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.09015","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":"sha256:8c784f0c8a077151fe7502a582d6d22f9ab3a094c8a0fe06ff31cc13626fee35","target":"record","created_at":"2026-07-05T00:56:12Z","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":"b98d9b3f13a86fc862e0b81c95963a8bfcd75ed4cd1293a24d5d5517354d309d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-20T01:45:27Z","title_canon_sha256":"0b03ae062cb71b25291dea0ed6f10aa46d68a3d189b7c6aa887f6bc38b3cce64"},"schema_version":"1.0","source":{"id":"2004.09015","kind":"arxiv","version":1}},"canonical_sha256":"994f9dd286a36400704e1894a3beca1b303dbf9877d50d48d5fdddb7f8f1164d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"994f9dd286a36400704e1894a3beca1b303dbf9877d50d48d5fdddb7f8f1164d","first_computed_at":"2026-07-05T00:56:12.296473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:56:12.296473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z/cg7sBHw+8yEkOEAls6UjnkOIL6biMQl6i18elGK7xcsVpiz7z3gVpxtENRbSd3bOWcNEihqOF89mldwRiEBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:56:12.296956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.09015","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c784f0c8a077151fe7502a582d6d22f9ab3a094c8a0fe06ff31cc13626fee35","sha256:5cfbe369d216870bab91853550db2a1bd7c093fd8b9af9c7327a56bbffe00554"],"state_sha256":"193a854f95781388b163e4a50c51a71e66752f0672bcea829ca287e923dc29c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9cNf2mKfdmpMDN7bsXV35qqq10GS/DyudY4ykF3IyuxYUcyfugRFCLnlxTUi3y2mzdhdESG0Hl4ms4sxQKHXCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:58:29.574152Z","bundle_sha256":"3f64e9714c30932fc7436cd4c4f2aca21e6b3b82a04bd3aab26424b1abcb8fac"}}