{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CNESJFSW5P5J5UEI7QNG4KYES4","short_pith_number":"pith:CNESJFSW","canonical_record":{"source":{"id":"2303.07295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-13T17:17:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cae9e2f2f042f04f5f2d64266c97877489e5b8b6d0934641fdbab22ca477394e","abstract_canon_sha256":"cd8670ce67a71d24731cc0ca873418a3d8dd0dc8ebe01a47a5c8936995bc20da"},"schema_version":"1.0"},"canonical_sha256":"1349249656ebfa9ed088fc1a6e2b049729830c201223b215eb27faef2169f343","source":{"kind":"arxiv","id":"2303.07295","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CNESJFSW5P5J5UEI7QNG4KYES4","target":"record","payload":{"canonical_record":{"source":{"id":"2303.07295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-13T17:17:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cae9e2f2f042f04f5f2d64266c97877489e5b8b6d0934641fdbab22ca477394e","abstract_canon_sha256":"cd8670ce67a71d24731cc0ca873418a3d8dd0dc8ebe01a47a5c8936995bc20da"},"schema_version":"1.0"},"canonical_sha256":"1349249656ebfa9ed088fc1a6e2b049729830c201223b215eb27faef2169f343","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:34.655005Z","signature_b64":"v/dFuJp7UtVbXLOLZRelgWQ+v4uDm0W3/Lu8R4IZND2wP55hKxh2CF8/eeDtT4voxCIOppqmS8sySwoHF04sCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1349249656ebfa9ed088fc1a6e2b049729830c201223b215eb27faef2169f343","last_reissued_at":"2026-07-05T05:50:34.654618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:34.654618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.07295","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":"2026-07-05T05:50:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"56Yy5z4nanpGQ5+JRJhO7nYMJBvoNyDFCsZDDPyIsieyehkQwqzzeyexRT1iVgrp/05ljJKV/jnFbku/4PLHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:30:27.052773Z"},"content_sha256":"95e94894b8c502de192b9c67f2fcb01688807038f5ad17da0e38ec7fab8299ac","schema_version":"1.0","event_id":"sha256:95e94894b8c502de192b9c67f2fcb01688807038f5ad17da0e38ec7fab8299ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CNESJFSW5P5J5UEI7QNG4KYES4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meet in the Middle: A New Pre-training Paradigm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anh Nguyen, Nikos Karampatziakis, Weizhu Chen","submitted_at":"2023-03-13T17:17:11Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07295","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/2303.07295/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":"2026-07-05T05:50:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7AF4wlxcGkztZ0SE05Ae3+LmVeJK0Rnc0g9Q5ERx+GJMmLyThdYmBaQBh3OIj4ExDH0IeJ0a3qqPcJWeyKvlBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:30:27.053837Z"},"content_sha256":"df605b65a1cb9ec222733606cad877e8cf68eef9a249eeca77a70a59c25612e2","schema_version":"1.0","event_id":"sha256:df605b65a1cb9ec222733606cad877e8cf68eef9a249eeca77a70a59c25612e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CNESJFSW5P5J5UEI7QNG4KYES4/bundle.json","state_url":"https://pith.science/pith/CNESJFSW5P5J5UEI7QNG4KYES4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CNESJFSW5P5J5UEI7QNG4KYES4/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":"2026-08-09T16:30:27Z","links":{"resolver":"https://pith.science/pith/CNESJFSW5P5J5UEI7QNG4KYES4","bundle":"https://pith.science/pith/CNESJFSW5P5J5UEI7QNG4KYES4/bundle.json","state":"https://pith.science/pith/CNESJFSW5P5J5UEI7QNG4KYES4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CNESJFSW5P5J5UEI7QNG4KYES4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wF01taINA7pOqjpSPWmauuDKZh+U8fIZ9sjRlOG9M5MqnSBi6nfAUpqh3OxyInpACFpR8GEqnuA8xtzvfUb/AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T16:30:27.057710Z","bundle_sha256":"90ecfd8a31d8c9f5904b4b2b4b0f2cfba9ea24bbeb60d458a51ed45afede2ac2"}}