{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FB5JQX5UAE5FSVJFWHE5Q4BOBC","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":"dee095e9fa75bea685fa1fa46dff2ac9fc3407a9c72bf447c543c2a137a782ea","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-03T17:50:56Z","title_canon_sha256":"5da5918948ac3443d91f6343d40495382da60ee1dde34469622d771d6a1923a8"},"schema_version":"1.0","source":{"id":"2305.02301","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.02301","created_at":"2026-05-21T20:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2305.02301v2","created_at":"2026-05-21T20:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02301","created_at":"2026-05-21T20:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"FB5JQX5UAE5F","created_at":"2026-05-21T20:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"FB5JQX5UAE5FSVJF","created_at":"2026-05-21T20:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"FB5JQX5U","created_at":"2026-05-21T20:43:58Z"}],"graph_snapshots":[{"event_id":"sha256:1c747184238d33577cf87e3d360f7e19528c09405865e77cd4583455bc182a4f","target":"graph","created_at":"2026-05-21T20:43:58Z","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/2305.02301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deploying large language models (LLMs) is challenging because they are memory inefficient and compute-intensive for practical applications. In reaction, researchers train smaller task-specific models by either finetuning with human labels or distilling using LLM-generated labels. However, finetuning and distillation require large amounts of training data to achieve comparable performance to LLMs. We introduce Distilling step-by-step, a new mechanism that (a) trains smaller models that outperform LLMs, and (b) achieves so by leveraging less training data needed by finetuning or distillation. Ou","authors_text":"Alexander Ratner, Cheng-Yu Hsieh, Chen-Yu Lee, Chih-Kuan Yeh, Chun-Liang Li, Hootan Nakhost, Ranjay Krishna, Tomas Pfister, Yasuhisa Fujii","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-03T17:50:56Z","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02301","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":"sha256:43202dec567ea7a082cc7db2a43fd7a5ffba46cc7c1b56efe301006b3f79a5be","target":"record","created_at":"2026-05-21T20:43:58Z","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":"dee095e9fa75bea685fa1fa46dff2ac9fc3407a9c72bf447c543c2a137a782ea","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-03T17:50:56Z","title_canon_sha256":"5da5918948ac3443d91f6343d40495382da60ee1dde34469622d771d6a1923a8"},"schema_version":"1.0","source":{"id":"2305.02301","kind":"arxiv","version":2}},"canonical_sha256":"287a985fb4013a595525b1c9d8702e08bd93485ef7d137fb5d9312946b40422b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"287a985fb4013a595525b1c9d8702e08bd93485ef7d137fb5d9312946b40422b","first_computed_at":"2026-05-21T20:43:58.373761Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T20:43:58.373761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qr0VDtHStr8rByyVxRat5oF3LQHN9yU5TGSFJqvRkkp9pwFzer1EzUVmPZat2v59Zp9L+371Bi4B3MPEvzySCw==","signature_status":"signed_v1","signed_at":"2026-05-21T20:43:58.375927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.02301","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43202dec567ea7a082cc7db2a43fd7a5ffba46cc7c1b56efe301006b3f79a5be","sha256:1c747184238d33577cf87e3d360f7e19528c09405865e77cd4583455bc182a4f"],"state_sha256":"886793fd751e342a373029dee206e2df4870e10ce0cecace17167160da010717"}