{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ELYJIHBD2RXK7GCHLEOFHXX3OB","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":"2ee3434b69843835386285dc02eacb289ee1ce403d57c7a04ea9b1ea9d38fd02","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T16:55:33Z","title_canon_sha256":"4e1a4c1de3d856a2bae66895c6403c411729b8ed390c29c5c7ddd8137fd8b45c"},"schema_version":"1.0","source":{"id":"2406.14491","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14491","created_at":"2026-07-05T09:41:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14491v2","created_at":"2026-07-05T09:41:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14491","created_at":"2026-07-05T09:41:38Z"},{"alias_kind":"pith_short_12","alias_value":"ELYJIHBD2RXK","created_at":"2026-07-05T09:41:38Z"},{"alias_kind":"pith_short_16","alias_value":"ELYJIHBD2RXK7GCH","created_at":"2026-07-05T09:41:38Z"},{"alias_kind":"pith_short_8","alias_value":"ELYJIHBD","created_at":"2026-07-05T09:41:38Z"}],"graph_snapshots":[{"event_id":"sha256:0605128878b313b65f0b18215d08faeb4e8965dd0cb5b7a2fa5a3736e3bc8271","target":"graph","created_at":"2026-07-05T09:41:38Z","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/2406.14491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised multitask pre-training has been the critical method behind the recent success of language models (LMs). However, supervised multitask learning still holds significant promise, as scaling it in the post-training stage trends towards better generalization. In this paper, we explore supervised multitask pre-training by proposing Instruction Pre-Training, a framework that scalably augments massive raw corpora with instruction-response pairs to pre-train LMs. The instruction-response pairs are generated by an efficient instruction synthesizer built on open-source models. In our experim","authors_text":"Daixuan Cheng, Furu Wei, Junyu Bi, Minlie Huang, Shaohan Huang, Yuxian Gu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T16:55:33Z","title":"Instruction Pre-Training: Language Models are Supervised Multitask Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14491","kind":"arxiv","version":2},"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":"sha256:78b68aeacc514db359579a975570ff600fe0f728abbadbe7ac5e9205c4bd1add","target":"record","created_at":"2026-07-05T09:41:38Z","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":"2ee3434b69843835386285dc02eacb289ee1ce403d57c7a04ea9b1ea9d38fd02","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T16:55:33Z","title_canon_sha256":"4e1a4c1de3d856a2bae66895c6403c411729b8ed390c29c5c7ddd8137fd8b45c"},"schema_version":"1.0","source":{"id":"2406.14491","kind":"arxiv","version":2}},"canonical_sha256":"22f0941c23d46eaf9847591c53defb7067fd2a1135b2db9b6e1c0f51a7aa8522","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22f0941c23d46eaf9847591c53defb7067fd2a1135b2db9b6e1c0f51a7aa8522","first_computed_at":"2026-07-05T09:41:38.251911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:38.251911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hM9bDIbE2Z8vSg85yQRHseNVolgu8cyZY/iTf2/pn0LXXaMfqbwGUHIkX69ydvZr2hSvcp0XVLheTEfM+vjiAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:38.252413Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14491","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78b68aeacc514db359579a975570ff600fe0f728abbadbe7ac5e9205c4bd1add","sha256:0605128878b313b65f0b18215d08faeb4e8965dd0cb5b7a2fa5a3736e3bc8271"],"state_sha256":"da0b51078a1040a3953045258aeb4ba44a7feb5d2a519643c13d25b75b515f86"}