{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:7CRKLLFA46S6UJF4OUPX3YFNXM","short_pith_number":"pith:7CRKLLFA","canonical_record":{"source":{"id":"2210.14473","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T04:47:18Z","cross_cats_sorted":[],"title_canon_sha256":"74a3fb0978b34a542d509591060a953ed2a3814b9151385141694728885b5a7a","abstract_canon_sha256":"1e76747594e9318a4bd50e0c3ec504a5580b3480d9f03a971e9f45c2036e5946"},"schema_version":"1.0"},"canonical_sha256":"f8a2a5aca0e7a5ea24bc751f7de0adbb00c7ae5ffb62fb797fbbd65655bf9012","source":{"kind":"arxiv","id":"2210.14473","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.14473","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"arxiv_version","alias_value":"2210.14473v1","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14473","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"pith_short_12","alias_value":"7CRKLLFA46S6","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"pith_short_16","alias_value":"7CRKLLFA46S6UJF4","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"pith_short_8","alias_value":"7CRKLLFA","created_at":"2026-07-05T05:10:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:7CRKLLFA46S6UJF4OUPX3YFNXM","target":"record","payload":{"canonical_record":{"source":{"id":"2210.14473","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T04:47:18Z","cross_cats_sorted":[],"title_canon_sha256":"74a3fb0978b34a542d509591060a953ed2a3814b9151385141694728885b5a7a","abstract_canon_sha256":"1e76747594e9318a4bd50e0c3ec504a5580b3480d9f03a971e9f45c2036e5946"},"schema_version":"1.0"},"canonical_sha256":"f8a2a5aca0e7a5ea24bc751f7de0adbb00c7ae5ffb62fb797fbbd65655bf9012","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:45.556737Z","signature_b64":"hBsdchj05eNlWAEaARG816t4kjbp3puDym2uN501mc3jDjyn55EUyveZkbVhDOMMPxuCbS0ppXfB4e0O+oqqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8a2a5aca0e7a5ea24bc751f7de0adbb00c7ae5ffb62fb797fbbd65655bf9012","last_reissued_at":"2026-07-05T05:10:45.556372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:45.556372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.14473","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":"2026-07-05T05:10:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n1EiVn6s/Gf/9aSpL7l6gY4v1USBMiYCh3RhAGH1HyIM5pCWkqodVzAwbbLeaIFgShvyXUe0npVCLeJvY5SWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:37:21.347281Z"},"content_sha256":"542a616d74497dde1dc53ec97a9074e980c84a9d4fa35753a5b3533b53aaa3fb","schema_version":"1.0","event_id":"sha256:542a616d74497dde1dc53ec97a9074e980c84a9d4fa35753a5b3533b53aaa3fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:7CRKLLFA46S6UJF4OUPX3YFNXM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Language Models for Code Syntax Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenguang Wang, Da Shen, Dawn Song, Koushik Sen, Xinyun Chen","submitted_at":"2022-10-26T04:47:18Z","abstract_excerpt":"Pre-trained language models have demonstrated impressive performance in both natural language processing and program understanding, which represent the input as a token sequence without explicitly modeling its structure. Some prior works show that pre-trained language models can capture the syntactic rules of natural languages without finetuning on syntax understanding tasks. However, there is limited understanding of how well pre-trained models understand the code structure so far. In this work, we perform the first thorough benchmarking of the state-of-the-art pre-trained models for identify"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14473","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/2210.14473/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":"2026-07-05T05:10:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SjzL3xMlYUbSK2yVdB08KOqptHIsIHvFwrVta3nNLBjlkQb8dIfTWrGAenG1p6QzCnUMHBoTNNwPpwAky/LQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:37:21.347766Z"},"content_sha256":"699450650a1f1b8e1e1b14e9cfec66dda5f2578dd3539b0365176d09d4b9ab63","schema_version":"1.0","event_id":"sha256:699450650a1f1b8e1e1b14e9cfec66dda5f2578dd3539b0365176d09d4b9ab63"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7CRKLLFA46S6UJF4OUPX3YFNXM/bundle.json","state_url":"https://pith.science/pith/7CRKLLFA46S6UJF4OUPX3YFNXM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7CRKLLFA46S6UJF4OUPX3YFNXM/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":"2026-08-03T19:37:21Z","links":{"resolver":"https://pith.science/pith/7CRKLLFA46S6UJF4OUPX3YFNXM","bundle":"https://pith.science/pith/7CRKLLFA46S6UJF4OUPX3YFNXM/bundle.json","state":"https://pith.science/pith/7CRKLLFA46S6UJF4OUPX3YFNXM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7CRKLLFA46S6UJF4OUPX3YFNXM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7CRKLLFA46S6UJF4OUPX3YFNXM","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":"1e76747594e9318a4bd50e0c3ec504a5580b3480d9f03a971e9f45c2036e5946","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T04:47:18Z","title_canon_sha256":"74a3fb0978b34a542d509591060a953ed2a3814b9151385141694728885b5a7a"},"schema_version":"1.0","source":{"id":"2210.14473","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.14473","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"arxiv_version","alias_value":"2210.14473v1","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14473","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"pith_short_12","alias_value":"7CRKLLFA46S6","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"pith_short_16","alias_value":"7CRKLLFA46S6UJF4","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"pith_short_8","alias_value":"7CRKLLFA","created_at":"2026-07-05T05:10:45Z"}],"graph_snapshots":[{"event_id":"sha256:699450650a1f1b8e1e1b14e9cfec66dda5f2578dd3539b0365176d09d4b9ab63","target":"graph","created_at":"2026-07-05T05:10:45Z","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/2210.14473/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained language models have demonstrated impressive performance in both natural language processing and program understanding, which represent the input as a token sequence without explicitly modeling its structure. Some prior works show that pre-trained language models can capture the syntactic rules of natural languages without finetuning on syntax understanding tasks. However, there is limited understanding of how well pre-trained models understand the code structure so far. In this work, we perform the first thorough benchmarking of the state-of-the-art pre-trained models for identify","authors_text":"Chenguang Wang, Da Shen, Dawn Song, Koushik Sen, Xinyun Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T04:47:18Z","title":"Benchmarking Language Models for Code Syntax Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14473","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":"sha256:542a616d74497dde1dc53ec97a9074e980c84a9d4fa35753a5b3533b53aaa3fb","target":"record","created_at":"2026-07-05T05:10:45Z","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":"1e76747594e9318a4bd50e0c3ec504a5580b3480d9f03a971e9f45c2036e5946","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T04:47:18Z","title_canon_sha256":"74a3fb0978b34a542d509591060a953ed2a3814b9151385141694728885b5a7a"},"schema_version":"1.0","source":{"id":"2210.14473","kind":"arxiv","version":1}},"canonical_sha256":"f8a2a5aca0e7a5ea24bc751f7de0adbb00c7ae5ffb62fb797fbbd65655bf9012","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8a2a5aca0e7a5ea24bc751f7de0adbb00c7ae5ffb62fb797fbbd65655bf9012","first_computed_at":"2026-07-05T05:10:45.556372Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:45.556372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hBsdchj05eNlWAEaARG816t4kjbp3puDym2uN501mc3jDjyn55EUyveZkbVhDOMMPxuCbS0ppXfB4e0O+oqqDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:45.556737Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.14473","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:542a616d74497dde1dc53ec97a9074e980c84a9d4fa35753a5b3533b53aaa3fb","sha256:699450650a1f1b8e1e1b14e9cfec66dda5f2578dd3539b0365176d09d4b9ab63"],"state_sha256":"00801e83b6057a2b5987c86ba55a35af6dce984eb24b75dee7895323627562f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gFjeweMqVOV3x/Muq8zycPup2KbzSseTwFW2FmxXY9pdZj54RL+rm0an7XyYdx/rqQy9p++nUyLdaAupJJnjBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:37:21.352792Z","bundle_sha256":"3eb8c01f7bd875479c54c91cb733072bbea0630384f1c4dbc8f43f83ad670803"}}