{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3YV4O7QGEZJKAI7DUGRBOV726R","short_pith_number":"pith:3YV4O7QG","canonical_record":{"source":{"id":"2401.03003","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-01-05T06:51:08Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"823961f620778bf17c8ddc876e0d50f171faaaa01959521abc9db0e6520daa29","abstract_canon_sha256":"632e07a0c99a18647cc83b760609217834f3c95f8d800c4774dac3dce5e3c876"},"schema_version":"1.0"},"canonical_sha256":"de2bc77e062652a023e3a1a21757faf454653a9066f597263ca0497495f4915c","source":{"kind":"arxiv","id":"2401.03003","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3YV4O7QGEZJKAI7DUGRBOV726R","target":"record","payload":{"canonical_record":{"source":{"id":"2401.03003","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-01-05T06:51:08Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"823961f620778bf17c8ddc876e0d50f171faaaa01959521abc9db0e6520daa29","abstract_canon_sha256":"632e07a0c99a18647cc83b760609217834f3c95f8d800c4774dac3dce5e3c876"},"schema_version":"1.0"},"canonical_sha256":"de2bc77e062652a023e3a1a21757faf454653a9066f597263ca0497495f4915c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:40.476396Z","signature_b64":"hNyZo5HRvEAE0R6+9NwnIoNEeZtbhgubiB1yO/2e1fte92Oah+ZdPuSegLn9kBJ20xgQBMaiNfKgVlc0+ZbSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de2bc77e062652a023e3a1a21757faf454653a9066f597263ca0497495f4915c","last_reissued_at":"2026-07-05T08:35:40.476001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:40.476001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.03003","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:35:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TPn//FuvpddpUSig1fEcGSwbZ0KyEtrmqtLncrHYkJKF8xn+iWFxNFxOlr9wyEwJKmF+0wa93ZVA6ZANYgk8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:52:14.531790Z"},"content_sha256":"535a984f4a9b995d42f984c9a54aea5cf035c9831a3d616b569cbbeeb66bacbf","schema_version":"1.0","event_id":"sha256:535a984f4a9b995d42f984c9a54aea5cf035c9831a3d616b569cbbeeb66bacbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3YV4O7QGEZJKAI7DUGRBOV726R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AST-T5: Structure-Aware Pretraining for Code Generation and Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Alvin Cheung, Linyuan Gong, Mostafa Elhoushi","submitted_at":"2024-01-05T06:51:08Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03003","kind":"arxiv","version":4},"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/2401.03003/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":"2026-07-05T08:35:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3JuxfWIc1cKomJkiVuCkvBaaI6HuMLvdPRHQkx05hgmEmuWQ0bNpC04dwF+qeQdsSqTsjCKOMomD/V6I/VwQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:52:14.532201Z"},"content_sha256":"a93ac145681e845fdc4049b508eed870cb0566cf5e37712290f9ec014807bdd0","schema_version":"1.0","event_id":"sha256:a93ac145681e845fdc4049b508eed870cb0566cf5e37712290f9ec014807bdd0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3YV4O7QGEZJKAI7DUGRBOV726R/bundle.json","state_url":"https://pith.science/pith/3YV4O7QGEZJKAI7DUGRBOV726R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3YV4O7QGEZJKAI7DUGRBOV726R/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":"2026-07-07T04:52:14Z","links":{"resolver":"https://pith.science/pith/3YV4O7QGEZJKAI7DUGRBOV726R","bundle":"https://pith.science/pith/3YV4O7QGEZJKAI7DUGRBOV726R/bundle.json","state":"https://pith.science/pith/3YV4O7QGEZJKAI7DUGRBOV726R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3YV4O7QGEZJKAI7DUGRBOV726R/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Am7aAn+n7srdxKeydDsKqAPG9uzcenRsYFLEoXzWdNurMG+UAFXqT9TNtm/Gu9hwyez0j4Up9ELdY/3487uOCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:52:14.534460Z","bundle_sha256":"79b2f1ec0ea7a10adcaafb84182af5db53ff59dd3b0b81e975d430c4384ab300"}}