{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6PUCUZAT7SMFMPTE6ZOKXWJPOD","short_pith_number":"pith:6PUCUZAT","schema_version":"1.0","canonical_sha256":"f3e82a6413fc98563e64f65cabd92f70e414a4cc9a35a667c115d6551208d6bc","source":{"kind":"arxiv","id":"2108.04556","version":3},"attestation_state":"computed","paper":{"title":"SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.CL","authors_text":"Fei Mi, Hao Wu, Jin Liu, Li Li, Pingyi Zhou, Xiao Liu, Xin Jiang, Xin Wang, Yao Wan, Yasheng Wang","submitted_at":"2021-08-10T10:08:21Z","abstract_excerpt":"Code representation learning, which aims to encode the semantics of source code into distributed vectors, plays an important role in recent deep-learning-based models for code intelligence. Recently, many pre-trained language models for source code (e.g., CuBERT and CodeBERT) have been proposed to model the context of code and serve as a basis for downstream code intelligence tasks such as code search, code clone detection, and program translation. Current approaches typically consider the source code as a plain sequence of tokens, or inject the structure information (e.g., AST and data-flow) "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2108.04556","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-10T10:08:21Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"2ef309753e34c8cfafe22a78f3177605f4990431a6d96376dd134b2d7bcd3432","abstract_canon_sha256":"c43ddd2e8594d0f311de52e3d372f62fc4e395e321fcb004b3b1c2122c6cd947"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:50.026881Z","signature_b64":"aXIX3Gat+TzVyJNlqPrYQNda/+czwYDo0nsYH7v/+PTfB2VgkL/ssKyIvZs/w0wv1ukHczsvuguzf7+tBbMMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3e82a6413fc98563e64f65cabd92f70e414a4cc9a35a667c115d6551208d6bc","last_reissued_at":"2026-07-05T03:12:50.026440Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:50.026440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.CL","authors_text":"Fei Mi, Hao Wu, Jin Liu, Li Li, Pingyi Zhou, Xiao Liu, Xin Jiang, Xin Wang, Yao Wan, Yasheng Wang","submitted_at":"2021-08-10T10:08:21Z","abstract_excerpt":"Code representation learning, which aims to encode the semantics of source code into distributed vectors, plays an important role in recent deep-learning-based models for code intelligence. Recently, many pre-trained language models for source code (e.g., CuBERT and CodeBERT) have been proposed to model the context of code and serve as a basis for downstream code intelligence tasks such as code search, code clone detection, and program translation. Current approaches typically consider the source code as a plain sequence of tokens, or inject the structure information (e.g., AST and data-flow) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04556","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/2108.04556/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2108.04556","created_at":"2026-07-05T03:12:50.026494+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.04556v3","created_at":"2026-07-05T03:12:50.026494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04556","created_at":"2026-07-05T03:12:50.026494+00:00"},{"alias_kind":"pith_short_12","alias_value":"6PUCUZAT7SMF","created_at":"2026-07-05T03:12:50.026494+00:00"},{"alias_kind":"pith_short_16","alias_value":"6PUCUZAT7SMFMPTE","created_at":"2026-07-05T03:12:50.026494+00:00"},{"alias_kind":"pith_short_8","alias_value":"6PUCUZAT","created_at":"2026-07-05T03:12:50.026494+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16046","citing_title":"XSearch: Explainable Code Search via Concept-to-Code Alignment","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27747","citing_title":"UNICS: Multilingual Code Search via Unified Pseudocode and Contrastive Transfer Learning","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2305.12138","citing_title":"Exploring Code Analysis: Zero-Shot Insights on Syntax and Semantics with LLMs","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16046","citing_title":"XSearch: Explainable Code Search via Concept-to-Code Alignment","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17184","citing_title":"SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6PUCUZAT7SMFMPTE6ZOKXWJPOD","json":"https://pith.science/pith/6PUCUZAT7SMFMPTE6ZOKXWJPOD.json","graph_json":"https://pith.science/api/pith-number/6PUCUZAT7SMFMPTE6ZOKXWJPOD/graph.json","events_json":"https://pith.science/api/pith-number/6PUCUZAT7SMFMPTE6ZOKXWJPOD/events.json","paper":"https://pith.science/paper/6PUCUZAT"},"agent_actions":{"view_html":"https://pith.science/pith/6PUCUZAT7SMFMPTE6ZOKXWJPOD","download_json":"https://pith.science/pith/6PUCUZAT7SMFMPTE6ZOKXWJPOD.json","view_paper":"https://pith.science/paper/6PUCUZAT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.04556&json=true","fetch_graph":"https://pith.science/api/pith-number/6PUCUZAT7SMFMPTE6ZOKXWJPOD/graph.json","fetch_events":"https://pith.science/api/pith-number/6PUCUZAT7SMFMPTE6ZOKXWJPOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6PUCUZAT7SMFMPTE6ZOKXWJPOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6PUCUZAT7SMFMPTE6ZOKXWJPOD/action/storage_attestation","attest_author":"https://pith.science/pith/6PUCUZAT7SMFMPTE6ZOKXWJPOD/action/author_attestation","sign_citation":"https://pith.science/pith/6PUCUZAT7SMFMPTE6ZOKXWJPOD/action/citation_signature","submit_replication":"https://pith.science/pith/6PUCUZAT7SMFMPTE6ZOKXWJPOD/action/replication_record"}},"created_at":"2026-07-05T03:12:50.026494+00:00","updated_at":"2026-07-05T03:12:50.026494+00:00"}