{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3YV4O7QGEZJKAI7DUGRBOV726R","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":"632e07a0c99a18647cc83b760609217834f3c95f8d800c4774dac3dce5e3c876","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-01-05T06:51:08Z","title_canon_sha256":"823961f620778bf17c8ddc876e0d50f171faaaa01959521abc9db0e6520daa29"},"schema_version":"1.0","source":{"id":"2401.03003","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.03003","created_at":"2026-07-05T08:35:40Z"},{"alias_kind":"arxiv_version","alias_value":"2401.03003v4","created_at":"2026-07-05T08:35:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03003","created_at":"2026-07-05T08:35:40Z"},{"alias_kind":"pith_short_12","alias_value":"3YV4O7QGEZJK","created_at":"2026-07-05T08:35:40Z"},{"alias_kind":"pith_short_16","alias_value":"3YV4O7QGEZJKAI7D","created_at":"2026-07-05T08:35:40Z"},{"alias_kind":"pith_short_8","alias_value":"3YV4O7QG","created_at":"2026-07-05T08:35:40Z"}],"graph_snapshots":[{"event_id":"sha256:a93ac145681e845fdc4049b508eed870cb0566cf5e37712290f9ec014807bdd0","target":"graph","created_at":"2026-07-05T08:35:40Z","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/2401.03003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have made significant advancements in code-related tasks, yet many LLMs treat code as simple sequences, neglecting its structured nature. We introduce AST-T5, a novel pretraining paradigm that leverages the Abstract Syntax Tree (AST) for enhanced code generation, transpilation, and understanding. Using dynamic programming, our AST-Aware Segmentation retains code structure, while our AST-Aware Span Corruption objective equips the model to reconstruct various code structures. Unlike other models, AST-T5 avoids intricate program analyses or architectural changes, so i","authors_text":"Alvin Cheung, Linyuan Gong, Mostafa Elhoushi","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-01-05T06:51:08Z","title":"AST-T5: Structure-Aware Pretraining for Code Generation and Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03003","kind":"arxiv","version":4},"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":"sha256:535a984f4a9b995d42f984c9a54aea5cf035c9831a3d616b569cbbeeb66bacbf","target":"record","created_at":"2026-07-05T08:35:40Z","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":"632e07a0c99a18647cc83b760609217834f3c95f8d800c4774dac3dce5e3c876","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-01-05T06:51:08Z","title_canon_sha256":"823961f620778bf17c8ddc876e0d50f171faaaa01959521abc9db0e6520daa29"},"schema_version":"1.0","source":{"id":"2401.03003","kind":"arxiv","version":4}},"canonical_sha256":"de2bc77e062652a023e3a1a21757faf454653a9066f597263ca0497495f4915c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de2bc77e062652a023e3a1a21757faf454653a9066f597263ca0497495f4915c","first_computed_at":"2026-07-05T08:35:40.476001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:40.476001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hNyZo5HRvEAE0R6+9NwnIoNEeZtbhgubiB1yO/2e1fte92Oah+ZdPuSegLn9kBJ20xgQBMaiNfKgVlc0+ZbSBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:40.476396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.03003","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:535a984f4a9b995d42f984c9a54aea5cf035c9831a3d616b569cbbeeb66bacbf","sha256:a93ac145681e845fdc4049b508eed870cb0566cf5e37712290f9ec014807bdd0"],"state_sha256":"8fcbf3ee0a0fb9c74b891e9d73393388040ee662c43cb5a96614c1041897a4c4"}