{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UJKPKJAETCDSC4KUZJRIIJZGRZ","short_pith_number":"pith:UJKPKJAE","canonical_record":{"source":{"id":"2310.12962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T17:57:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"115a78eb1edcac53fb67e4288a4ca1fb289c116739f8334148cfb239424ede0e","abstract_canon_sha256":"24d6c1e9aba659623d7e8384e789ad7062ab7cfb4e6e1b9dc0e1347d2510965c"},"schema_version":"1.0"},"canonical_sha256":"a254f524049887217154ca628427268e79eb0e93a38e13e4bfa4ec0dc96f1a09","source":{"kind":"arxiv","id":"2310.12962","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12962","created_at":"2026-07-05T07:02:44Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12962v1","created_at":"2026-07-05T07:02:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12962","created_at":"2026-07-05T07:02:44Z"},{"alias_kind":"pith_short_12","alias_value":"UJKPKJAETCDS","created_at":"2026-07-05T07:02:44Z"},{"alias_kind":"pith_short_16","alias_value":"UJKPKJAETCDSC4KU","created_at":"2026-07-05T07:02:44Z"},{"alias_kind":"pith_short_8","alias_value":"UJKPKJAE","created_at":"2026-07-05T07:02:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UJKPKJAETCDSC4KUZJRIIJZGRZ","target":"record","payload":{"canonical_record":{"source":{"id":"2310.12962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T17:57:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"115a78eb1edcac53fb67e4288a4ca1fb289c116739f8334148cfb239424ede0e","abstract_canon_sha256":"24d6c1e9aba659623d7e8384e789ad7062ab7cfb4e6e1b9dc0e1347d2510965c"},"schema_version":"1.0"},"canonical_sha256":"a254f524049887217154ca628427268e79eb0e93a38e13e4bfa4ec0dc96f1a09","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:44.925387Z","signature_b64":"s4oaDJGDpF8EBM6QMi6P4tnNczZ0AORzj+bIVGdeji1BWto4aU1G42xRD2yFhvYAdSUJ1a/QvLE7MXRLFJ2rAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a254f524049887217154ca628427268e79eb0e93a38e13e4bfa4ec0dc96f1a09","last_reissued_at":"2026-07-05T07:02:44.924861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:44.924861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.12962","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":"2026-07-05T07:02:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gTZ/mL90Tco8t1OhN7PJ2pkLivoPL6PnQpZnCRwa+K8gOPmkuuRIPlk3CvfhsdDtnOGvV6Ei0eWoXLvfbiIqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:20:38.437139Z"},"content_sha256":"967288b47e157c6253a7671b95e7e8a588368c59da6924d49116b9802f3d7193","schema_version":"1.0","event_id":"sha256:967288b47e157c6253a7671b95e7e8a588368c59da6924d49116b9802f3d7193"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UJKPKJAETCDSC4KUZJRIIJZGRZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Emulator for Fine-Tuning Large Language Models using Small Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Archit Sharma, Chelsea Finn, Christopher D. Manning, Eric Mitchell, Rafael Rafailov","submitted_at":"2023-10-19T17:57:16Z","abstract_excerpt":"Widely used language models (LMs) are typically built by scaling up a two-stage training pipeline: a pre-training stage that uses a very large, diverse dataset of text and a fine-tuning (sometimes, 'alignment') stage that uses targeted examples or other specifications of desired behaviors. While it has been hypothesized that knowledge and skills come from pre-training, and fine-tuning mostly filters this knowledge and skillset, this intuition has not been extensively tested. To aid in doing so, we introduce a novel technique for decoupling the knowledge and skills gained in these two stages, e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12962","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/2310.12962/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":"2026-07-05T07:02:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dt3LhECBPuw+MQetyNYNH5FPyEQzc/6zS5C6mGSqKMo9iOKAmgTp/tMT11HN+xVL3S9b32/i2+I87ORQvX61Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:20:38.437776Z"},"content_sha256":"6e44bebf6455b4463d0620bf7ba2122ba2d0dd6ff91c972b6b4f99ad984c8eb4","schema_version":"1.0","event_id":"sha256:6e44bebf6455b4463d0620bf7ba2122ba2d0dd6ff91c972b6b4f99ad984c8eb4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UJKPKJAETCDSC4KUZJRIIJZGRZ/bundle.json","state_url":"https://pith.science/pith/UJKPKJAETCDSC4KUZJRIIJZGRZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UJKPKJAETCDSC4KUZJRIIJZGRZ/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":"2026-08-10T07:20:38Z","links":{"resolver":"https://pith.science/pith/UJKPKJAETCDSC4KUZJRIIJZGRZ","bundle":"https://pith.science/pith/UJKPKJAETCDSC4KUZJRIIJZGRZ/bundle.json","state":"https://pith.science/pith/UJKPKJAETCDSC4KUZJRIIJZGRZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UJKPKJAETCDSC4KUZJRIIJZGRZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UJKPKJAETCDSC4KUZJRIIJZGRZ","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":"24d6c1e9aba659623d7e8384e789ad7062ab7cfb4e6e1b9dc0e1347d2510965c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T17:57:16Z","title_canon_sha256":"115a78eb1edcac53fb67e4288a4ca1fb289c116739f8334148cfb239424ede0e"},"schema_version":"1.0","source":{"id":"2310.12962","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12962","created_at":"2026-07-05T07:02:44Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12962v1","created_at":"2026-07-05T07:02:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12962","created_at":"2026-07-05T07:02:44Z"},{"alias_kind":"pith_short_12","alias_value":"UJKPKJAETCDS","created_at":"2026-07-05T07:02:44Z"},{"alias_kind":"pith_short_16","alias_value":"UJKPKJAETCDSC4KU","created_at":"2026-07-05T07:02:44Z"},{"alias_kind":"pith_short_8","alias_value":"UJKPKJAE","created_at":"2026-07-05T07:02:44Z"}],"graph_snapshots":[{"event_id":"sha256:6e44bebf6455b4463d0620bf7ba2122ba2d0dd6ff91c972b6b4f99ad984c8eb4","target":"graph","created_at":"2026-07-05T07:02:44Z","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/2310.12962/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Widely used language models (LMs) are typically built by scaling up a two-stage training pipeline: a pre-training stage that uses a very large, diverse dataset of text and a fine-tuning (sometimes, 'alignment') stage that uses targeted examples or other specifications of desired behaviors. While it has been hypothesized that knowledge and skills come from pre-training, and fine-tuning mostly filters this knowledge and skillset, this intuition has not been extensively tested. To aid in doing so, we introduce a novel technique for decoupling the knowledge and skills gained in these two stages, e","authors_text":"Archit Sharma, Chelsea Finn, Christopher D. Manning, Eric Mitchell, Rafael Rafailov","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T17:57:16Z","title":"An Emulator for Fine-Tuning Large Language Models using Small Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12962","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":"sha256:967288b47e157c6253a7671b95e7e8a588368c59da6924d49116b9802f3d7193","target":"record","created_at":"2026-07-05T07:02:44Z","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":"24d6c1e9aba659623d7e8384e789ad7062ab7cfb4e6e1b9dc0e1347d2510965c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T17:57:16Z","title_canon_sha256":"115a78eb1edcac53fb67e4288a4ca1fb289c116739f8334148cfb239424ede0e"},"schema_version":"1.0","source":{"id":"2310.12962","kind":"arxiv","version":1}},"canonical_sha256":"a254f524049887217154ca628427268e79eb0e93a38e13e4bfa4ec0dc96f1a09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a254f524049887217154ca628427268e79eb0e93a38e13e4bfa4ec0dc96f1a09","first_computed_at":"2026-07-05T07:02:44.924861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:44.924861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s4oaDJGDpF8EBM6QMi6P4tnNczZ0AORzj+bIVGdeji1BWto4aU1G42xRD2yFhvYAdSUJ1a/QvLE7MXRLFJ2rAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:44.925387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.12962","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:967288b47e157c6253a7671b95e7e8a588368c59da6924d49116b9802f3d7193","sha256:6e44bebf6455b4463d0620bf7ba2122ba2d0dd6ff91c972b6b4f99ad984c8eb4"],"state_sha256":"94dc46dc29941b71798384c2766ae5aea5979690344db96906fb83499ca3329c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UAd53BsB8sCqJ9woxWzPoxW9GknFhgTRU08uqMj0EBj9nnTwMUIkCk0hdXr1/6S67lLW/uCrl8oI9P7i6oTzAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:20:38.442729Z","bundle_sha256":"a129de638ce989b99d33602ce5288b342974affede1a8d8ab94068a60b237fa7"}}