{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6PUCUZAT7SMFMPTE6ZOKXWJPOD","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":"c43ddd2e8594d0f311de52e3d372f62fc4e395e321fcb004b3b1c2122c6cd947","cross_cats_sorted":["cs.AI","cs.PL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-10T10:08:21Z","title_canon_sha256":"2ef309753e34c8cfafe22a78f3177605f4990431a6d96376dd134b2d7bcd3432"},"schema_version":"1.0","source":{"id":"2108.04556","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.04556","created_at":"2026-07-05T03:12:50Z"},{"alias_kind":"arxiv_version","alias_value":"2108.04556v3","created_at":"2026-07-05T03:12:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04556","created_at":"2026-07-05T03:12:50Z"},{"alias_kind":"pith_short_12","alias_value":"6PUCUZAT7SMF","created_at":"2026-07-05T03:12:50Z"},{"alias_kind":"pith_short_16","alias_value":"6PUCUZAT7SMFMPTE","created_at":"2026-07-05T03:12:50Z"},{"alias_kind":"pith_short_8","alias_value":"6PUCUZAT","created_at":"2026-07-05T03:12:50Z"}],"graph_snapshots":[{"event_id":"sha256:0b676036da848f7798aea7aaa7b75040ee38541b33f79ec18b82e0a68ba75be9","target":"graph","created_at":"2026-07-05T03:12:50Z","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/2108.04556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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) ","authors_text":"Fei Mi, Hao Wu, Jin Liu, Li Li, Pingyi Zhou, Xiao Liu, Xin Jiang, Xin Wang, Yao Wan, Yasheng Wang","cross_cats":["cs.AI","cs.PL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-10T10:08:21Z","title":"SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04556","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:d6cd5be4ece2d4350d984f10fbfb814d0903e66936517cde2ef24160d67f5e17","target":"record","created_at":"2026-07-05T03:12:50Z","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":"c43ddd2e8594d0f311de52e3d372f62fc4e395e321fcb004b3b1c2122c6cd947","cross_cats_sorted":["cs.AI","cs.PL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-10T10:08:21Z","title_canon_sha256":"2ef309753e34c8cfafe22a78f3177605f4990431a6d96376dd134b2d7bcd3432"},"schema_version":"1.0","source":{"id":"2108.04556","kind":"arxiv","version":3}},"canonical_sha256":"f3e82a6413fc98563e64f65cabd92f70e414a4cc9a35a667c115d6551208d6bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3e82a6413fc98563e64f65cabd92f70e414a4cc9a35a667c115d6551208d6bc","first_computed_at":"2026-07-05T03:12:50.026440Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:12:50.026440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aXIX3Gat+TzVyJNlqPrYQNda/+czwYDo0nsYH7v/+PTfB2VgkL/ssKyIvZs/w0wv1ukHczsvuguzf7+tBbMMCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:12:50.026881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.04556","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6cd5be4ece2d4350d984f10fbfb814d0903e66936517cde2ef24160d67f5e17","sha256:0b676036da848f7798aea7aaa7b75040ee38541b33f79ec18b82e0a68ba75be9"],"state_sha256":"2d1171688d89225d24483000ab44037194880995faeb674f0cb4a9e51eac2726"}