{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:L55F7NMRYN7VIPPN5R7ECR4N24","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":"5db40195e49bd354901f5ce043114730eac375fbcd2c6f352304fe1e78319e39","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-15T11:50:47Z","title_canon_sha256":"cd459ed0d8a447ca61a00ced9ffaab873440f21d8042417092c7191948107161"},"schema_version":"1.0","source":{"id":"2102.07492","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.07492","created_at":"2026-07-05T03:26:38Z"},{"alias_kind":"arxiv_version","alias_value":"2102.07492v3","created_at":"2026-07-05T03:26:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07492","created_at":"2026-07-05T03:26:38Z"},{"alias_kind":"pith_short_12","alias_value":"L55F7NMRYN7V","created_at":"2026-07-05T03:26:38Z"},{"alias_kind":"pith_short_16","alias_value":"L55F7NMRYN7VIPPN","created_at":"2026-07-05T03:26:38Z"},{"alias_kind":"pith_short_8","alias_value":"L55F7NMR","created_at":"2026-07-05T03:26:38Z"}],"graph_snapshots":[{"event_id":"sha256:902e6ef6e7bc95a7f80d2580d1705114cff3f4d2d8ba2bf1cb42ff0bd2f52ae1","target":"graph","created_at":"2026-07-05T03:26:38Z","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/2102.07492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in self-supervised learning have dramatically improved the state of the art on a wide variety of tasks. However, research in language model pre-training has mostly focused on natural languages, and it is unclear whether models like BERT and its variants provide the best pre-training when applied to other modalities, such as source code. In this paper, we introduce a new pre-training objective, DOBF, that leverages the structural aspect of programming languages and pre-trains a model to recover the original version of obfuscated source code. We show that models pre-trained with ","authors_text":"Baptiste Roziere, Guillaume Lample, Marc Szafraniec, Marie-Anne Lachaux","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-15T11:50:47Z","title":"DOBF: A Deobfuscation Pre-Training Objective for Programming Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07492","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:b9a0356997ad660589cc85d3e4b8ed226c7586a6ed730bf92823d3abd7debb10","target":"record","created_at":"2026-07-05T03:26:38Z","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":"5db40195e49bd354901f5ce043114730eac375fbcd2c6f352304fe1e78319e39","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-15T11:50:47Z","title_canon_sha256":"cd459ed0d8a447ca61a00ced9ffaab873440f21d8042417092c7191948107161"},"schema_version":"1.0","source":{"id":"2102.07492","kind":"arxiv","version":3}},"canonical_sha256":"5f7a5fb591c37f543dedec7e41478dd71ebde67e78d6b9e6a16cf05d739f6460","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f7a5fb591c37f543dedec7e41478dd71ebde67e78d6b9e6a16cf05d739f6460","first_computed_at":"2026-07-05T03:26:38.831922Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:38.831922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6GrQJvacQcUr2RpZlmgJGz1EhA4PP6WrWfE871lvJ0+VdhcO2TVkCfE2ZYoyhat9KqOfdDBciEa0k5+cSJNOCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:38.832351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.07492","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9a0356997ad660589cc85d3e4b8ed226c7586a6ed730bf92823d3abd7debb10","sha256:902e6ef6e7bc95a7f80d2580d1705114cff3f4d2d8ba2bf1cb42ff0bd2f52ae1"],"state_sha256":"d9ebac0f613f40ea75c8a79da8be231a2263826bb15d6661c2c1285ff05ea502"}