{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q4NY3TDSLUQV6AVHZR3V57FRXY","short_pith_number":"pith:Q4NY3TDS","canonical_record":{"source":{"id":"2402.02318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T02:09:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f05b8720a7c42d7527dd928d2fb7f204615bbd6e19cf811bd07a1144f4ce0d9a","abstract_canon_sha256":"7925fa38163c46a2f6c83af3a9f944c1161616f7130dbd3055ed8bfc86fec093"},"schema_version":"1.0"},"canonical_sha256":"871b8dcc725d215f02a7cc775efcb1be0597a1358fd73d90f91765efaf178abb","source":{"kind":"arxiv","id":"2402.02318","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02318","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02318v1","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02318","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"pith_short_12","alias_value":"Q4NY3TDSLUQV","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"pith_short_16","alias_value":"Q4NY3TDSLUQV6AVH","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"pith_short_8","alias_value":"Q4NY3TDS","created_at":"2026-07-05T07:41:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q4NY3TDSLUQV6AVHZR3V57FRXY","target":"record","payload":{"canonical_record":{"source":{"id":"2402.02318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T02:09:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f05b8720a7c42d7527dd928d2fb7f204615bbd6e19cf811bd07a1144f4ce0d9a","abstract_canon_sha256":"7925fa38163c46a2f6c83af3a9f944c1161616f7130dbd3055ed8bfc86fec093"},"schema_version":"1.0"},"canonical_sha256":"871b8dcc725d215f02a7cc775efcb1be0597a1358fd73d90f91765efaf178abb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:48.495942Z","signature_b64":"kNa5XNEvDnQl9srmeZgeM6M/eIggTZE5iv9xpIWHlqQejXRMKMBCw7xfk4o1HNWRodH+jksSw85deVULlxbsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"871b8dcc725d215f02a7cc775efcb1be0597a1358fd73d90f91765efaf178abb","last_reissued_at":"2026-07-05T07:41:48.495546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:48.495546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.02318","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":"2026-07-05T07:41:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uRg1FZIwU79t30q6yy9OzOnErnheyr+Ero1SC7X6pRusEdnwzY+lZ9zNH3OQbbyvznjJ1lSWWo2iU/I172/pAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T16:41:45.012703Z"},"content_sha256":"948bea7193537091ee3f9253f0a909d26c5ac709dd4e93a48e7fb0dffc0074bd","schema_version":"1.0","event_id":"sha256:948bea7193537091ee3f9253f0a909d26c5ac709dd4e93a48e7fb0dffc0074bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q4NY3TDSLUQV6AVHZR3V57FRXY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diversity Measurement and Subset Selection for Instruction Tuning Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Matthew Stallone, Peiqi Wang, Polina Golland, Rameswar Panda, Yikang Shen, Yoon Kim, Zhen Guo","submitted_at":"2024-02-04T02:09:43Z","abstract_excerpt":"We aim to select data subsets for the fine-tuning of large language models to more effectively follow instructions. Prior work has emphasized the importance of diversity in dataset curation but relied on heuristics such as the number of tasks. In this paper, we use determinantal point processes to capture the diversity and quality of instruction tuning datasets for subset selection. We propose to measure dataset diversity with log determinant distance that is the distance between the dataset of interest and a maximally diverse reference dataset. Our experiments demonstrate that the proposed di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02318","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/2402.02318/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":"2026-07-05T07:41:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B+10CIhDl0kyoKyC972OOLSZKAWaK0DzhuhUVVha65EHiQV8V7Fu2ecAp5vYDl7phHHBxRafJv69OdS84Qw3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T16:41:45.012992Z"},"content_sha256":"66bddc584d8853c3a22f831435ff94d1cdbe73f722ac7beaf88367d02c9ab861","schema_version":"1.0","event_id":"sha256:66bddc584d8853c3a22f831435ff94d1cdbe73f722ac7beaf88367d02c9ab861"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q4NY3TDSLUQV6AVHZR3V57FRXY/bundle.json","state_url":"https://pith.science/pith/Q4NY3TDSLUQV6AVHZR3V57FRXY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q4NY3TDSLUQV6AVHZR3V57FRXY/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":"2026-07-31T16:41:45Z","links":{"resolver":"https://pith.science/pith/Q4NY3TDSLUQV6AVHZR3V57FRXY","bundle":"https://pith.science/pith/Q4NY3TDSLUQV6AVHZR3V57FRXY/bundle.json","state":"https://pith.science/pith/Q4NY3TDSLUQV6AVHZR3V57FRXY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q4NY3TDSLUQV6AVHZR3V57FRXY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q4NY3TDSLUQV6AVHZR3V57FRXY","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":"7925fa38163c46a2f6c83af3a9f944c1161616f7130dbd3055ed8bfc86fec093","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T02:09:43Z","title_canon_sha256":"f05b8720a7c42d7527dd928d2fb7f204615bbd6e19cf811bd07a1144f4ce0d9a"},"schema_version":"1.0","source":{"id":"2402.02318","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02318","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02318v1","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02318","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"pith_short_12","alias_value":"Q4NY3TDSLUQV","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"pith_short_16","alias_value":"Q4NY3TDSLUQV6AVH","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"pith_short_8","alias_value":"Q4NY3TDS","created_at":"2026-07-05T07:41:48Z"}],"graph_snapshots":[{"event_id":"sha256:66bddc584d8853c3a22f831435ff94d1cdbe73f722ac7beaf88367d02c9ab861","target":"graph","created_at":"2026-07-05T07:41:48Z","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/2402.02318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We aim to select data subsets for the fine-tuning of large language models to more effectively follow instructions. Prior work has emphasized the importance of diversity in dataset curation but relied on heuristics such as the number of tasks. In this paper, we use determinantal point processes to capture the diversity and quality of instruction tuning datasets for subset selection. We propose to measure dataset diversity with log determinant distance that is the distance between the dataset of interest and a maximally diverse reference dataset. Our experiments demonstrate that the proposed di","authors_text":"Matthew Stallone, Peiqi Wang, Polina Golland, Rameswar Panda, Yikang Shen, Yoon Kim, Zhen Guo","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T02:09:43Z","title":"Diversity Measurement and Subset Selection for Instruction Tuning Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02318","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":"sha256:948bea7193537091ee3f9253f0a909d26c5ac709dd4e93a48e7fb0dffc0074bd","target":"record","created_at":"2026-07-05T07:41:48Z","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":"7925fa38163c46a2f6c83af3a9f944c1161616f7130dbd3055ed8bfc86fec093","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T02:09:43Z","title_canon_sha256":"f05b8720a7c42d7527dd928d2fb7f204615bbd6e19cf811bd07a1144f4ce0d9a"},"schema_version":"1.0","source":{"id":"2402.02318","kind":"arxiv","version":1}},"canonical_sha256":"871b8dcc725d215f02a7cc775efcb1be0597a1358fd73d90f91765efaf178abb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"871b8dcc725d215f02a7cc775efcb1be0597a1358fd73d90f91765efaf178abb","first_computed_at":"2026-07-05T07:41:48.495546Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:48.495546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kNa5XNEvDnQl9srmeZgeM6M/eIggTZE5iv9xpIWHlqQejXRMKMBCw7xfk4o1HNWRodH+jksSw85deVULlxbsBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:48.495942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.02318","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:948bea7193537091ee3f9253f0a909d26c5ac709dd4e93a48e7fb0dffc0074bd","sha256:66bddc584d8853c3a22f831435ff94d1cdbe73f722ac7beaf88367d02c9ab861"],"state_sha256":"184529d94c71ba8c24218462a76e182483d71d87891e537f62e727f91e97e77e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lCacUfhS9IBkFIbqKwMit40XL785Bc7xMm2C1kgoWz+2fnt1hLGzQmqnbGGerEAZivjNZsmn6BQHx+pWRMmLCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T16:41:45.016353Z","bundle_sha256":"8d0273fe61a14c04051f53fd761b6c3ca96bad627c88450dc1c21e65e62ed72d"}}