{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2V3P2YFK32CBBPGWRIPBAAJKZM","short_pith_number":"pith:2V3P2YFK","canonical_record":{"source":{"id":"2402.18191","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T09:27:29Z","cross_cats_sorted":[],"title_canon_sha256":"881473ee043ec8172c1d3f8aa3a7cb5839e5f5c4a479402d090edeb038ddc62d","abstract_canon_sha256":"96a1b3862852cac032694f3709d4eb2947fb441c7395cd777bb12c052160cbb4"},"schema_version":"1.0"},"canonical_sha256":"d576fd60aade8410bcd68a1e10012acb2788457be98b23f1d8d586b2bbe64eab","source":{"kind":"arxiv","id":"2402.18191","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18191","created_at":"2026-07-05T09:36:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18191v3","created_at":"2026-07-05T09:36:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18191","created_at":"2026-07-05T09:36:39Z"},{"alias_kind":"pith_short_12","alias_value":"2V3P2YFK32CB","created_at":"2026-07-05T09:36:39Z"},{"alias_kind":"pith_short_16","alias_value":"2V3P2YFK32CBBPGW","created_at":"2026-07-05T09:36:39Z"},{"alias_kind":"pith_short_8","alias_value":"2V3P2YFK","created_at":"2026-07-05T09:36:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2V3P2YFK32CBBPGWRIPBAAJKZM","target":"record","payload":{"canonical_record":{"source":{"id":"2402.18191","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T09:27:29Z","cross_cats_sorted":[],"title_canon_sha256":"881473ee043ec8172c1d3f8aa3a7cb5839e5f5c4a479402d090edeb038ddc62d","abstract_canon_sha256":"96a1b3862852cac032694f3709d4eb2947fb441c7395cd777bb12c052160cbb4"},"schema_version":"1.0"},"canonical_sha256":"d576fd60aade8410bcd68a1e10012acb2788457be98b23f1d8d586b2bbe64eab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:39.065873Z","signature_b64":"tBpvRrzzDCc6tqJJbqwg8jxLkhNIUfGBUVwNU9pe5ez90B20cb01jfJscIgL3eu83rF8qRvKI14mv2xbRQcJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d576fd60aade8410bcd68a1e10012acb2788457be98b23f1d8d586b2bbe64eab","last_reissued_at":"2026-07-05T09:36:39.065381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:39.065381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.18191","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:36:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HJt+XdDNvieDIoBXY9Kn448S+So1VP2Oomtv2vM2siUs75eJd+pLERJhTRJ1wk1gmq5O77hJqOcCyweckChGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:07:06.981153Z"},"content_sha256":"43a0e454a989cc025dc28c6d2f3dd68ca7475797ae8d4af95c8b9049093089d5","schema_version":"1.0","event_id":"sha256:43a0e454a989cc025dc28c6d2f3dd68ca7475797ae8d4af95c8b9049093089d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2V3P2YFK32CBBPGWRIPBAAJKZM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bei Li, Boxing Chen, Chi Hu, Hao Yang, Hongxia Ma, Jingbo Zhu, Li Zhang, Shimin Tao, Tong Xiao, Weibin Meng, Xiaofeng Zhao, Yilun Liu, Yuan Ge","submitted_at":"2024-02-28T09:27:29Z","abstract_excerpt":"With contributions from the open-source community, a vast amount of instruction tuning (IT) data has emerged. Given the significant resource allocation required for training and evaluating models, it is advantageous to have an efficient method for selecting high-quality IT data. However, existing methods for instruction data selection have limitations such as relying on fragile external APIs, being affected by biases in GPT models, or reducing the diversity of the selected instruction dataset. In this paper, we propose an industrial-friendly, expert-aligned and diversity-preserved instruction "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18191","kind":"arxiv","version":3},"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/2402.18191/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":"2026-07-05T09:36:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xo91I6cTvgo9SGstcrF3GRDznyhzkR5cflq2Na1ehhocXRVJQfz9ELK3s4mtDVHrXzQ3zUbpux5jjtaLXBptBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:07:06.981648Z"},"content_sha256":"67dd74ac607cccf4ec0646000e653941df65523340b26e842ac6c4d6f4814bff","schema_version":"1.0","event_id":"sha256:67dd74ac607cccf4ec0646000e653941df65523340b26e842ac6c4d6f4814bff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2V3P2YFK32CBBPGWRIPBAAJKZM/bundle.json","state_url":"https://pith.science/pith/2V3P2YFK32CBBPGWRIPBAAJKZM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2V3P2YFK32CBBPGWRIPBAAJKZM/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":"2026-08-06T09:07:06Z","links":{"resolver":"https://pith.science/pith/2V3P2YFK32CBBPGWRIPBAAJKZM","bundle":"https://pith.science/pith/2V3P2YFK32CBBPGWRIPBAAJKZM/bundle.json","state":"https://pith.science/pith/2V3P2YFK32CBBPGWRIPBAAJKZM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2V3P2YFK32CBBPGWRIPBAAJKZM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2V3P2YFK32CBBPGWRIPBAAJKZM","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":"96a1b3862852cac032694f3709d4eb2947fb441c7395cd777bb12c052160cbb4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T09:27:29Z","title_canon_sha256":"881473ee043ec8172c1d3f8aa3a7cb5839e5f5c4a479402d090edeb038ddc62d"},"schema_version":"1.0","source":{"id":"2402.18191","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18191","created_at":"2026-07-05T09:36:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18191v3","created_at":"2026-07-05T09:36:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18191","created_at":"2026-07-05T09:36:39Z"},{"alias_kind":"pith_short_12","alias_value":"2V3P2YFK32CB","created_at":"2026-07-05T09:36:39Z"},{"alias_kind":"pith_short_16","alias_value":"2V3P2YFK32CBBPGW","created_at":"2026-07-05T09:36:39Z"},{"alias_kind":"pith_short_8","alias_value":"2V3P2YFK","created_at":"2026-07-05T09:36:39Z"}],"graph_snapshots":[{"event_id":"sha256:67dd74ac607cccf4ec0646000e653941df65523340b26e842ac6c4d6f4814bff","target":"graph","created_at":"2026-07-05T09:36:39Z","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/2402.18191/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With contributions from the open-source community, a vast amount of instruction tuning (IT) data has emerged. Given the significant resource allocation required for training and evaluating models, it is advantageous to have an efficient method for selecting high-quality IT data. However, existing methods for instruction data selection have limitations such as relying on fragile external APIs, being affected by biases in GPT models, or reducing the diversity of the selected instruction dataset. In this paper, we propose an industrial-friendly, expert-aligned and diversity-preserved instruction ","authors_text":"Bei Li, Boxing Chen, Chi Hu, Hao Yang, Hongxia Ma, Jingbo Zhu, Li Zhang, Shimin Tao, Tong Xiao, Weibin Meng, Xiaofeng Zhao, Yilun Liu, Yuan Ge","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T09:27:29Z","title":"Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18191","kind":"arxiv","version":3},"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":"sha256:43a0e454a989cc025dc28c6d2f3dd68ca7475797ae8d4af95c8b9049093089d5","target":"record","created_at":"2026-07-05T09:36:39Z","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":"96a1b3862852cac032694f3709d4eb2947fb441c7395cd777bb12c052160cbb4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T09:27:29Z","title_canon_sha256":"881473ee043ec8172c1d3f8aa3a7cb5839e5f5c4a479402d090edeb038ddc62d"},"schema_version":"1.0","source":{"id":"2402.18191","kind":"arxiv","version":3}},"canonical_sha256":"d576fd60aade8410bcd68a1e10012acb2788457be98b23f1d8d586b2bbe64eab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d576fd60aade8410bcd68a1e10012acb2788457be98b23f1d8d586b2bbe64eab","first_computed_at":"2026-07-05T09:36:39.065381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:39.065381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tBpvRrzzDCc6tqJJbqwg8jxLkhNIUfGBUVwNU9pe5ez90B20cb01jfJscIgL3eu83rF8qRvKI14mv2xbRQcJCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:39.065873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.18191","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43a0e454a989cc025dc28c6d2f3dd68ca7475797ae8d4af95c8b9049093089d5","sha256:67dd74ac607cccf4ec0646000e653941df65523340b26e842ac6c4d6f4814bff"],"state_sha256":"1ffaf875a1a4bcc10818e2361f688d0642c5f3c9807642ab2d7a27d3b40c9563"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t6jGLB9E5GN07HcSD36wbeyOtb2zBJvjFh6I5hDWF9w1xEvfwuaHjnxLtUN4t561aCwxLr7x/6jbJHKv8dfcCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:07:06.985308Z","bundle_sha256":"57b5ddb770b7afd68b60128f49132d5f844d0887b9114c45144c7e59ab837a67"}}