{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XBUSGJVZIX5LAQV37D4WILTNQ4","short_pith_number":"pith:XBUSGJVZ","canonical_record":{"source":{"id":"2412.09990","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T09:23:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c8f11c520252b10337c49eb15239370c2f504a267662cb6fcd7571e99ef83b4","abstract_canon_sha256":"1d311f0162ddc07f2bb1384595ce70ba0b0fdd03fa711f7951ce31fc4c8099b4"},"schema_version":"1.0"},"canonical_sha256":"b8692326b945fab042bbf8f9642e6d8738b5c1b1d0a03605a3d6dd5c0ceaffee","source":{"kind":"arxiv","id":"2412.09990","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09990","created_at":"2026-07-05T09:48:45Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09990v1","created_at":"2026-07-05T09:48:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09990","created_at":"2026-07-05T09:48:45Z"},{"alias_kind":"pith_short_12","alias_value":"XBUSGJVZIX5L","created_at":"2026-07-05T09:48:45Z"},{"alias_kind":"pith_short_16","alias_value":"XBUSGJVZIX5LAQV3","created_at":"2026-07-05T09:48:45Z"},{"alias_kind":"pith_short_8","alias_value":"XBUSGJVZ","created_at":"2026-07-05T09:48:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XBUSGJVZIX5LAQV37D4WILTNQ4","target":"record","payload":{"canonical_record":{"source":{"id":"2412.09990","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T09:23:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c8f11c520252b10337c49eb15239370c2f504a267662cb6fcd7571e99ef83b4","abstract_canon_sha256":"1d311f0162ddc07f2bb1384595ce70ba0b0fdd03fa711f7951ce31fc4c8099b4"},"schema_version":"1.0"},"canonical_sha256":"b8692326b945fab042bbf8f9642e6d8738b5c1b1d0a03605a3d6dd5c0ceaffee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:45.077913Z","signature_b64":"eHE1rpwwWlQmdhcTilSq+y5ntdqJiUqHw8M/h/th+PgUO53ke0qPaksw2is+JmCsov4/ZO+ezbl72frCnDSMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8692326b945fab042bbf8f9642e6d8738b5c1b1d0a03605a3d6dd5c0ceaffee","last_reissued_at":"2026-07-05T09:48:45.077377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:45.077377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.09990","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":"2026-07-05T09:48:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FLiTlbm3b+nuK1yJKIQaJ/r+nLnI1hXZaFQRZGkpMqBDhKhnzKODvM2nJsF9qoEXXFdWUn6odb3XCnJ30uvMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:55:37.608848Z"},"content_sha256":"845e7d5983702a513c681491b75f91cc5b2e1da750d48d2d661434465957ac8c","schema_version":"1.0","event_id":"sha256:845e7d5983702a513c681491b75f91cc5b2e1da750d48d2d661434465957ac8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XBUSGJVZIX5LAQV37D4WILTNQ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Small Language Model as Data Prospector for Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Di Yang, Haihong Wu, Hamid Alinejad-Rokny, Min Yang, Qiang Qu, Shiwen Ni","submitted_at":"2024-12-13T09:23:58Z","abstract_excerpt":"The quality of instruction data directly affects the performance of fine-tuned Large Language Models (LLMs). Previously, \\cite{li2023one} proposed \\texttt{NUGGETS}, which identifies and selects high-quality quality data from a large dataset by identifying those individual instruction examples that can significantly improve the performance of different tasks after being learnt as one-shot instances. In this work, we propose \\texttt{SuperNUGGETS}, an improved variant of \\texttt{NUGGETS} optimised for efficiency and performance. Our \\texttt{SuperNUGGETS} uses a small language model (SLM) instead "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09990","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/2412.09990/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":"2026-07-05T09:48:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CJ0BpXEAJ0obRVmi01IlAcYxx2TrNbCeTNfVu6MZAmhJN+PD+Y07fgiXrtzQIfJpHVv0jMFhVDKiGObQxfM8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:55:37.610530Z"},"content_sha256":"d1d0f78dd71b1c1d88f86e9d7c5c54f59865f49fd4196a20db3cc7ee625b019c","schema_version":"1.0","event_id":"sha256:d1d0f78dd71b1c1d88f86e9d7c5c54f59865f49fd4196a20db3cc7ee625b019c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XBUSGJVZIX5LAQV37D4WILTNQ4/bundle.json","state_url":"https://pith.science/pith/XBUSGJVZIX5LAQV37D4WILTNQ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XBUSGJVZIX5LAQV37D4WILTNQ4/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":"2026-08-09T13:55:37Z","links":{"resolver":"https://pith.science/pith/XBUSGJVZIX5LAQV37D4WILTNQ4","bundle":"https://pith.science/pith/XBUSGJVZIX5LAQV37D4WILTNQ4/bundle.json","state":"https://pith.science/pith/XBUSGJVZIX5LAQV37D4WILTNQ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XBUSGJVZIX5LAQV37D4WILTNQ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XBUSGJVZIX5LAQV37D4WILTNQ4","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":"1d311f0162ddc07f2bb1384595ce70ba0b0fdd03fa711f7951ce31fc4c8099b4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T09:23:58Z","title_canon_sha256":"3c8f11c520252b10337c49eb15239370c2f504a267662cb6fcd7571e99ef83b4"},"schema_version":"1.0","source":{"id":"2412.09990","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09990","created_at":"2026-07-05T09:48:45Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09990v1","created_at":"2026-07-05T09:48:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09990","created_at":"2026-07-05T09:48:45Z"},{"alias_kind":"pith_short_12","alias_value":"XBUSGJVZIX5L","created_at":"2026-07-05T09:48:45Z"},{"alias_kind":"pith_short_16","alias_value":"XBUSGJVZIX5LAQV3","created_at":"2026-07-05T09:48:45Z"},{"alias_kind":"pith_short_8","alias_value":"XBUSGJVZ","created_at":"2026-07-05T09:48:45Z"}],"graph_snapshots":[{"event_id":"sha256:d1d0f78dd71b1c1d88f86e9d7c5c54f59865f49fd4196a20db3cc7ee625b019c","target":"graph","created_at":"2026-07-05T09:48:45Z","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/2412.09990/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The quality of instruction data directly affects the performance of fine-tuned Large Language Models (LLMs). Previously, \\cite{li2023one} proposed \\texttt{NUGGETS}, which identifies and selects high-quality quality data from a large dataset by identifying those individual instruction examples that can significantly improve the performance of different tasks after being learnt as one-shot instances. In this work, we propose \\texttt{SuperNUGGETS}, an improved variant of \\texttt{NUGGETS} optimised for efficiency and performance. Our \\texttt{SuperNUGGETS} uses a small language model (SLM) instead ","authors_text":"Di Yang, Haihong Wu, Hamid Alinejad-Rokny, Min Yang, Qiang Qu, Shiwen Ni","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T09:23:58Z","title":"Small Language Model as Data Prospector for Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09990","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":"sha256:845e7d5983702a513c681491b75f91cc5b2e1da750d48d2d661434465957ac8c","target":"record","created_at":"2026-07-05T09:48:45Z","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":"1d311f0162ddc07f2bb1384595ce70ba0b0fdd03fa711f7951ce31fc4c8099b4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T09:23:58Z","title_canon_sha256":"3c8f11c520252b10337c49eb15239370c2f504a267662cb6fcd7571e99ef83b4"},"schema_version":"1.0","source":{"id":"2412.09990","kind":"arxiv","version":1}},"canonical_sha256":"b8692326b945fab042bbf8f9642e6d8738b5c1b1d0a03605a3d6dd5c0ceaffee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8692326b945fab042bbf8f9642e6d8738b5c1b1d0a03605a3d6dd5c0ceaffee","first_computed_at":"2026-07-05T09:48:45.077377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:45.077377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eHE1rpwwWlQmdhcTilSq+y5ntdqJiUqHw8M/h/th+PgUO53ke0qPaksw2is+JmCsov4/ZO+ezbl72frCnDSMDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:45.077913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09990","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:845e7d5983702a513c681491b75f91cc5b2e1da750d48d2d661434465957ac8c","sha256:d1d0f78dd71b1c1d88f86e9d7c5c54f59865f49fd4196a20db3cc7ee625b019c"],"state_sha256":"84fdb73e1a88e41b8ce88582575bcb98f7107177be2eccbc1633652970ee2ea8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X4JZWzRObtu45lreDa5Amn8xtiVlwShUH4Ng9s5GwLkY+8Frg+BVg49FwaGVyx3NfpBpHrXDcapNp4vOb0EaBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:55:37.617233Z","bundle_sha256":"8012ce13588c329b17628d71d301e461aa7d46961ab21b80c790aa5b2d5c924e"}}