{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZQKYOAKRGRWN2O3AE5VZBIRH6P","short_pith_number":"pith:ZQKYOAKR","canonical_record":{"source":{"id":"2201.10866","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-26T10:54:30Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"7335223cf2cf9447ba4bfc4a649bd608a2d7241771210c163a8e82e927b75ad8","abstract_canon_sha256":"206b06976f00af83aad9e263d38662aef7ea0852737a69ef384f5f7b4f1a842f"},"schema_version":"1.0"},"canonical_sha256":"cc15870151346cdd3b60276b90a227f3ef95ddf91c083689feee0948ec4dfe8e","source":{"kind":"arxiv","id":"2201.10866","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.10866","created_at":"2026-07-05T05:10:36Z"},{"alias_kind":"arxiv_version","alias_value":"2201.10866v3","created_at":"2026-07-05T05:10:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10866","created_at":"2026-07-05T05:10:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZQKYOAKRGRWN","created_at":"2026-07-05T05:10:36Z"},{"alias_kind":"pith_short_16","alias_value":"ZQKYOAKRGRWN2O3A","created_at":"2026-07-05T05:10:36Z"},{"alias_kind":"pith_short_8","alias_value":"ZQKYOAKR","created_at":"2026-07-05T05:10:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZQKYOAKRGRWN2O3AE5VZBIRH6P","target":"record","payload":{"canonical_record":{"source":{"id":"2201.10866","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-26T10:54:30Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"7335223cf2cf9447ba4bfc4a649bd608a2d7241771210c163a8e82e927b75ad8","abstract_canon_sha256":"206b06976f00af83aad9e263d38662aef7ea0852737a69ef384f5f7b4f1a842f"},"schema_version":"1.0"},"canonical_sha256":"cc15870151346cdd3b60276b90a227f3ef95ddf91c083689feee0948ec4dfe8e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:36.380615Z","signature_b64":"XHnFY5g5oUVmtoUR0Ny26Umh8JOT96P/6tEIHHrRgbBkaEchhUj8MAuXBGqr2hYV2QtVR+lMWVBQ9ugf6pUdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc15870151346cdd3b60276b90a227f3ef95ddf91c083689feee0948ec4dfe8e","last_reissued_at":"2026-07-05T05:10:36.380123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:36.380123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.10866","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:10:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nhTokqDioCNLLHRTqyOtejrHKcNZG1dYSs2w0wHWbNnumF4FIAx4unbfe1BdPslW1tSHS2otzDRNY/IsBi1iCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:12:33.962076Z"},"content_sha256":"ee2b24edf1d89781610bb6627b08848c165f508e9b564986eebfc778546a53c8","schema_version":"1.0","event_id":"sha256:ee2b24edf1d89781610bb6627b08848c165f508e9b564986eebfc778546a53c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZQKYOAKRGRWN2O3AE5VZBIRH6P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CodeRetriever: Unimodal and Bimodal Contrastive Learning for Code Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Bolun Yao, Daxin Jiang, Hang Zhang, Nan Duan, Weizhen Qi, Weizhu Chen, Xiaonan Li, Xipeng Qiu, Yelong Shen, Yeyun Gong","submitted_at":"2022-01-26T10:54:30Z","abstract_excerpt":"In this paper, we propose the CodeRetriever model, which learns the function-level code semantic representations through large-scale code-text contrastive pre-training. We adopt two contrastive learning schemes in CodeRetriever: unimodal contrastive learning and bimodal contrastive learning. For unimodal contrastive learning, we design an unsupervised learning approach to build semantic-related code pairs based on the documentation and function name. For bimodal contrastive learning, we leverage the documentation and in-line comments of code to build code-text pairs. Both contrastive objective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10866","kind":"arxiv","version":3},"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/2201.10866/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":"2026-07-05T05:10:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4awmY4WtGUiakodIu2kGidu0PIPmlUmhxGMJm9mvR5mhJ+Lj2T8RuF1kVhJbbFTqnO9FUt91tv8qIUbHLyxqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:12:33.962464Z"},"content_sha256":"c08da1c36b862fba930ce4e3ccedf8f1c96210319b99e1ebad016d3dd1083abe","schema_version":"1.0","event_id":"sha256:c08da1c36b862fba930ce4e3ccedf8f1c96210319b99e1ebad016d3dd1083abe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQKYOAKRGRWN2O3AE5VZBIRH6P/bundle.json","state_url":"https://pith.science/pith/ZQKYOAKRGRWN2O3AE5VZBIRH6P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQKYOAKRGRWN2O3AE5VZBIRH6P/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":"2026-07-08T19:12:33Z","links":{"resolver":"https://pith.science/pith/ZQKYOAKRGRWN2O3AE5VZBIRH6P","bundle":"https://pith.science/pith/ZQKYOAKRGRWN2O3AE5VZBIRH6P/bundle.json","state":"https://pith.science/pith/ZQKYOAKRGRWN2O3AE5VZBIRH6P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQKYOAKRGRWN2O3AE5VZBIRH6P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZQKYOAKRGRWN2O3AE5VZBIRH6P","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":"206b06976f00af83aad9e263d38662aef7ea0852737a69ef384f5f7b4f1a842f","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-26T10:54:30Z","title_canon_sha256":"7335223cf2cf9447ba4bfc4a649bd608a2d7241771210c163a8e82e927b75ad8"},"schema_version":"1.0","source":{"id":"2201.10866","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.10866","created_at":"2026-07-05T05:10:36Z"},{"alias_kind":"arxiv_version","alias_value":"2201.10866v3","created_at":"2026-07-05T05:10:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10866","created_at":"2026-07-05T05:10:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZQKYOAKRGRWN","created_at":"2026-07-05T05:10:36Z"},{"alias_kind":"pith_short_16","alias_value":"ZQKYOAKRGRWN2O3A","created_at":"2026-07-05T05:10:36Z"},{"alias_kind":"pith_short_8","alias_value":"ZQKYOAKR","created_at":"2026-07-05T05:10:36Z"}],"graph_snapshots":[{"event_id":"sha256:c08da1c36b862fba930ce4e3ccedf8f1c96210319b99e1ebad016d3dd1083abe","target":"graph","created_at":"2026-07-05T05:10:36Z","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/2201.10866/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose the CodeRetriever model, which learns the function-level code semantic representations through large-scale code-text contrastive pre-training. We adopt two contrastive learning schemes in CodeRetriever: unimodal contrastive learning and bimodal contrastive learning. For unimodal contrastive learning, we design an unsupervised learning approach to build semantic-related code pairs based on the documentation and function name. For bimodal contrastive learning, we leverage the documentation and in-line comments of code to build code-text pairs. Both contrastive objective","authors_text":"Bolun Yao, Daxin Jiang, Hang Zhang, Nan Duan, Weizhen Qi, Weizhu Chen, Xiaonan Li, Xipeng Qiu, Yelong Shen, Yeyun Gong","cross_cats":["cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-26T10:54:30Z","title":"CodeRetriever: Unimodal and Bimodal Contrastive Learning for Code Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10866","kind":"arxiv","version":3},"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:ee2b24edf1d89781610bb6627b08848c165f508e9b564986eebfc778546a53c8","target":"record","created_at":"2026-07-05T05:10:36Z","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":"206b06976f00af83aad9e263d38662aef7ea0852737a69ef384f5f7b4f1a842f","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-26T10:54:30Z","title_canon_sha256":"7335223cf2cf9447ba4bfc4a649bd608a2d7241771210c163a8e82e927b75ad8"},"schema_version":"1.0","source":{"id":"2201.10866","kind":"arxiv","version":3}},"canonical_sha256":"cc15870151346cdd3b60276b90a227f3ef95ddf91c083689feee0948ec4dfe8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc15870151346cdd3b60276b90a227f3ef95ddf91c083689feee0948ec4dfe8e","first_computed_at":"2026-07-05T05:10:36.380123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:36.380123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XHnFY5g5oUVmtoUR0Ny26Umh8JOT96P/6tEIHHrRgbBkaEchhUj8MAuXBGqr2hYV2QtVR+lMWVBQ9ugf6pUdBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:36.380615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.10866","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee2b24edf1d89781610bb6627b08848c165f508e9b564986eebfc778546a53c8","sha256:c08da1c36b862fba930ce4e3ccedf8f1c96210319b99e1ebad016d3dd1083abe"],"state_sha256":"f8a76a8a5ad5739fa719e2f580b7103a09efdc0e78e46d83f883e43700e74df0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OxL6YBwQFNpsPsID3Zah8Mq3ygOmv5upO3df0M4rh6dvoA4PaxJvra7Z+8DbWeJTYFJbsm95VtCiUgtxihVuDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T19:12:33.964619Z","bundle_sha256":"bb21517112073a7f609619370fa2c5aa79b56f3d20f6f1fad40895b642dc0917"}}