{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WXYLPT6SDHICNPWUQUSWCZ56G7","short_pith_number":"pith:WXYLPT6S","canonical_record":{"source":{"id":"2311.13133","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T03:37:01Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"20658f8b96dd3b69202ae14d374d64b679a7423292ed0a36ee1c3424d5e62942","abstract_canon_sha256":"2030a5a1b39ba3797c8d70405cf9b73917d5d380cfc10525fd7cf92a8e20d3f7"},"schema_version":"1.0"},"canonical_sha256":"b5f0b7cfd219d026bed485256167be37e90b2c6c0258be2d8339c8d93d084b6d","source":{"kind":"arxiv","id":"2311.13133","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13133","created_at":"2026-07-05T07:28:31Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13133v1","created_at":"2026-07-05T07:28:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13133","created_at":"2026-07-05T07:28:31Z"},{"alias_kind":"pith_short_12","alias_value":"WXYLPT6SDHIC","created_at":"2026-07-05T07:28:31Z"},{"alias_kind":"pith_short_16","alias_value":"WXYLPT6SDHICNPWU","created_at":"2026-07-05T07:28:31Z"},{"alias_kind":"pith_short_8","alias_value":"WXYLPT6S","created_at":"2026-07-05T07:28:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WXYLPT6SDHICNPWUQUSWCZ56G7","target":"record","payload":{"canonical_record":{"source":{"id":"2311.13133","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T03:37:01Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"20658f8b96dd3b69202ae14d374d64b679a7423292ed0a36ee1c3424d5e62942","abstract_canon_sha256":"2030a5a1b39ba3797c8d70405cf9b73917d5d380cfc10525fd7cf92a8e20d3f7"},"schema_version":"1.0"},"canonical_sha256":"b5f0b7cfd219d026bed485256167be37e90b2c6c0258be2d8339c8d93d084b6d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:31.546773Z","signature_b64":"yRP6vUi0Hvg/cgqEhMiWdvrtoOWVXNP3Oqhckw3FFCJeosa8JFsk8387uKe4cdIXCiF+YTnjaA/Oe7sQ9QvqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5f0b7cfd219d026bed485256167be37e90b2c6c0258be2d8339c8d93d084b6d","last_reissued_at":"2026-07-05T07:28:31.546343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:31.546343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.13133","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":"2026-07-05T07:28:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rPpbqKLtRpw9FY0Wyejdkj6YFpdaU4yqystRhITSmi8XkR+6LT2bkwFdVUkcOHL/VvU5KOqeKEEIcs7ReTSBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:54:40.757557Z"},"content_sha256":"04ecd5492260446399bec8106742f8cfb78ab0bcf9112ddae4f4ecee0ad2bd62","schema_version":"1.0","event_id":"sha256:04ecd5492260446399bec8106742f8cfb78ab0bcf9112ddae4f4ecee0ad2bd62"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WXYLPT6SDHICNPWUQUSWCZ56G7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aditi Jha, Alex Trott, Jacob Portes, Jeremy Dohmann, Sam Havens","submitted_at":"2023-11-22T03:37:01Z","abstract_excerpt":"Large Language Models are traditionally finetuned on large instruction datasets. However recent studies suggest that small, high-quality datasets can suffice for general purpose instruction following. This lack of consensus surrounding finetuning best practices is in part due to rapidly diverging approaches to LLM evaluation. In this study, we ask whether a small amount of diverse finetuning samples can improve performance on both traditional perplexity-based NLP benchmarks, and on open-ended, model-based evaluation. We finetune open-source MPT-7B and MPT-30B models on instruction finetuning d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13133","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/2311.13133/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":"2026-07-05T07:28:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0xO24vE8dTeEo/6mJw5sz3joheLxa8p0tU3sdzE/3QhX0TEEmJA1LUi6uAUtFPhI6B4WV7sSY4weY+5HmgP/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:54:40.758056Z"},"content_sha256":"e9c8f40d38c7bf917d8514c80817dc61c632cb2dfd77c7c38f06639a5fb70b1e","schema_version":"1.0","event_id":"sha256:e9c8f40d38c7bf917d8514c80817dc61c632cb2dfd77c7c38f06639a5fb70b1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WXYLPT6SDHICNPWUQUSWCZ56G7/bundle.json","state_url":"https://pith.science/pith/WXYLPT6SDHICNPWUQUSWCZ56G7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WXYLPT6SDHICNPWUQUSWCZ56G7/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":"2026-08-07T23:54:40Z","links":{"resolver":"https://pith.science/pith/WXYLPT6SDHICNPWUQUSWCZ56G7","bundle":"https://pith.science/pith/WXYLPT6SDHICNPWUQUSWCZ56G7/bundle.json","state":"https://pith.science/pith/WXYLPT6SDHICNPWUQUSWCZ56G7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WXYLPT6SDHICNPWUQUSWCZ56G7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WXYLPT6SDHICNPWUQUSWCZ56G7","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":"2030a5a1b39ba3797c8d70405cf9b73917d5d380cfc10525fd7cf92a8e20d3f7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T03:37:01Z","title_canon_sha256":"20658f8b96dd3b69202ae14d374d64b679a7423292ed0a36ee1c3424d5e62942"},"schema_version":"1.0","source":{"id":"2311.13133","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13133","created_at":"2026-07-05T07:28:31Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13133v1","created_at":"2026-07-05T07:28:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13133","created_at":"2026-07-05T07:28:31Z"},{"alias_kind":"pith_short_12","alias_value":"WXYLPT6SDHIC","created_at":"2026-07-05T07:28:31Z"},{"alias_kind":"pith_short_16","alias_value":"WXYLPT6SDHICNPWU","created_at":"2026-07-05T07:28:31Z"},{"alias_kind":"pith_short_8","alias_value":"WXYLPT6S","created_at":"2026-07-05T07:28:31Z"}],"graph_snapshots":[{"event_id":"sha256:e9c8f40d38c7bf917d8514c80817dc61c632cb2dfd77c7c38f06639a5fb70b1e","target":"graph","created_at":"2026-07-05T07:28:31Z","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/2311.13133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models are traditionally finetuned on large instruction datasets. However recent studies suggest that small, high-quality datasets can suffice for general purpose instruction following. This lack of consensus surrounding finetuning best practices is in part due to rapidly diverging approaches to LLM evaluation. In this study, we ask whether a small amount of diverse finetuning samples can improve performance on both traditional perplexity-based NLP benchmarks, and on open-ended, model-based evaluation. We finetune open-source MPT-7B and MPT-30B models on instruction finetuning d","authors_text":"Aditi Jha, Alex Trott, Jacob Portes, Jeremy Dohmann, Sam Havens","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T03:37:01Z","title":"LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13133","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":"sha256:04ecd5492260446399bec8106742f8cfb78ab0bcf9112ddae4f4ecee0ad2bd62","target":"record","created_at":"2026-07-05T07:28:31Z","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":"2030a5a1b39ba3797c8d70405cf9b73917d5d380cfc10525fd7cf92a8e20d3f7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T03:37:01Z","title_canon_sha256":"20658f8b96dd3b69202ae14d374d64b679a7423292ed0a36ee1c3424d5e62942"},"schema_version":"1.0","source":{"id":"2311.13133","kind":"arxiv","version":1}},"canonical_sha256":"b5f0b7cfd219d026bed485256167be37e90b2c6c0258be2d8339c8d93d084b6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5f0b7cfd219d026bed485256167be37e90b2c6c0258be2d8339c8d93d084b6d","first_computed_at":"2026-07-05T07:28:31.546343Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:31.546343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yRP6vUi0Hvg/cgqEhMiWdvrtoOWVXNP3Oqhckw3FFCJeosa8JFsk8387uKe4cdIXCiF+YTnjaA/Oe7sQ9QvqAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:31.546773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.13133","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04ecd5492260446399bec8106742f8cfb78ab0bcf9112ddae4f4ecee0ad2bd62","sha256:e9c8f40d38c7bf917d8514c80817dc61c632cb2dfd77c7c38f06639a5fb70b1e"],"state_sha256":"49082840795c4a13ae0f36418a89e240a7de6a03adb65d48d270ddfaa25ee443"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fuIUYRERxtrroxMGdxwj1m5Q/YSJSA15SfLl84fMtLlAjOHKdNsIsmY6QqnCUeTNenEvrOJGYwRodYrxwBcIAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:54:40.761655Z","bundle_sha256":"f1467b0bb8e2e489b59cfa21925a6878fa6b654fb73680b5744d1a8bc699a172"}}