{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CNESJFSW5P5J5UEI7QNG4KYES4","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":"cd8670ce67a71d24731cc0ca873418a3d8dd0dc8ebe01a47a5c8936995bc20da","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-13T17:17:11Z","title_canon_sha256":"cae9e2f2f042f04f5f2d64266c97877489e5b8b6d0934641fdbab22ca477394e"},"schema_version":"1.0","source":{"id":"2303.07295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.07295","created_at":"2026-07-05T05:50:34Z"},{"alias_kind":"arxiv_version","alias_value":"2303.07295v1","created_at":"2026-07-05T05:50:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07295","created_at":"2026-07-05T05:50:34Z"},{"alias_kind":"pith_short_12","alias_value":"CNESJFSW5P5J","created_at":"2026-07-05T05:50:34Z"},{"alias_kind":"pith_short_16","alias_value":"CNESJFSW5P5J5UEI","created_at":"2026-07-05T05:50:34Z"},{"alias_kind":"pith_short_8","alias_value":"CNESJFSW","created_at":"2026-07-05T05:50:34Z"}],"graph_snapshots":[{"event_id":"sha256:df605b65a1cb9ec222733606cad877e8cf68eef9a249eeca77a70a59c25612e2","target":"graph","created_at":"2026-07-05T05:50:34Z","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/2303.07295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most language models (LMs) are trained and applied in an autoregressive left-to-right fashion, assuming that the next token only depends on the preceding ones. However, this assumption ignores the potential benefits of using the full sequence information during training, and the possibility of having context from both sides during inference. In this paper, we propose a new pre-training paradigm with techniques that jointly improve the training data efficiency and the capabilities of the LMs in the infilling task. The first is a training objective that aligns the predictions of a left-to-right ","authors_text":"Anh Nguyen, Nikos Karampatziakis, Weizhu Chen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-13T17:17:11Z","title":"Meet in the Middle: A New Pre-training Paradigm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07295","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":"sha256:95e94894b8c502de192b9c67f2fcb01688807038f5ad17da0e38ec7fab8299ac","target":"record","created_at":"2026-07-05T05:50:34Z","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":"cd8670ce67a71d24731cc0ca873418a3d8dd0dc8ebe01a47a5c8936995bc20da","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-13T17:17:11Z","title_canon_sha256":"cae9e2f2f042f04f5f2d64266c97877489e5b8b6d0934641fdbab22ca477394e"},"schema_version":"1.0","source":{"id":"2303.07295","kind":"arxiv","version":1}},"canonical_sha256":"1349249656ebfa9ed088fc1a6e2b049729830c201223b215eb27faef2169f343","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1349249656ebfa9ed088fc1a6e2b049729830c201223b215eb27faef2169f343","first_computed_at":"2026-07-05T05:50:34.654618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:50:34.654618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v/dFuJp7UtVbXLOLZRelgWQ+v4uDm0W3/Lu8R4IZND2wP55hKxh2CF8/eeDtT4voxCIOppqmS8sySwoHF04sCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:50:34.655005Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.07295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95e94894b8c502de192b9c67f2fcb01688807038f5ad17da0e38ec7fab8299ac","sha256:df605b65a1cb9ec222733606cad877e8cf68eef9a249eeca77a70a59c25612e2"],"state_sha256":"ce614928776d91ee48cf92bc162df051f5fc943d29119ce8227123cd8fd10365"}