{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YTD2BKHM4UX3KUZ3ZFNMB7QI22","short_pith_number":"pith:YTD2BKHM","canonical_record":{"source":{"id":"2410.10877","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T10:07:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3bc598cf64b4e68524fe87ded419fd91925130e094cc0a1e679e354f025c9b81","abstract_canon_sha256":"8f46ff15397471b0e2206e506fc92cd931ef8142693d545835bcf8878599f557"},"schema_version":"1.0"},"canonical_sha256":"c4c7a0a8ece52fb5533bc95ac0fe08d6812c818d56eeb33c995851201e9b9239","source":{"kind":"arxiv","id":"2410.10877","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10877","created_at":"2026-07-05T10:25:11Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10877v2","created_at":"2026-07-05T10:25:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10877","created_at":"2026-07-05T10:25:11Z"},{"alias_kind":"pith_short_12","alias_value":"YTD2BKHM4UX3","created_at":"2026-07-05T10:25:11Z"},{"alias_kind":"pith_short_16","alias_value":"YTD2BKHM4UX3KUZ3","created_at":"2026-07-05T10:25:11Z"},{"alias_kind":"pith_short_8","alias_value":"YTD2BKHM","created_at":"2026-07-05T10:25:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YTD2BKHM4UX3KUZ3ZFNMB7QI22","target":"record","payload":{"canonical_record":{"source":{"id":"2410.10877","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T10:07:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3bc598cf64b4e68524fe87ded419fd91925130e094cc0a1e679e354f025c9b81","abstract_canon_sha256":"8f46ff15397471b0e2206e506fc92cd931ef8142693d545835bcf8878599f557"},"schema_version":"1.0"},"canonical_sha256":"c4c7a0a8ece52fb5533bc95ac0fe08d6812c818d56eeb33c995851201e9b9239","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:11.745925Z","signature_b64":"pZgM0kjElEBCBaCbDu08ODfbdeTGQ30nzLndF0osHAsVFoVn56O6psYyiveMBIZRPhQX/vclsk6oxTZgu+mXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4c7a0a8ece52fb5533bc95ac0fe08d6812c818d56eeb33c995851201e9b9239","last_reissued_at":"2026-07-05T10:25:11.745050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:11.745050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.10877","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:25:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Nu4s0hz0Wsmgxla+3zcxRHXa36wRpl8Oy9ORm5BqIu5dxUZpd0NSIF3iErYF3XIgL63iiMhuEwlK7PIiyF3Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:06:46.053008Z"},"content_sha256":"4aa9b730a2e56ac27338831622efd1321c74f5d1e7da6322383d9608ff0eb713","schema_version":"1.0","event_id":"sha256:4aa9b730a2e56ac27338831622efd1321c74f5d1e7da6322383d9608ff0eb713"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YTD2BKHM4UX3KUZ3ZFNMB7QI22","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Data Efficiency via Curating LLM-Driven Rating Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ankit Parag Shah, Chen Qian, Jiaheng Wei, Jinlong Pang, Wei Wei, Yang Liu, Yaxuan Wang, Yujia Bao, Zhaowei Zhu","submitted_at":"2024-10-09T10:07:55Z","abstract_excerpt":"Instruction tuning is critical for adapting large language models (LLMs) to downstream tasks, and recent studies have demonstrated that small amounts of human-curated data can outperform larger datasets, challenging traditional data scaling laws. While LLM-based data quality rating systems offer a cost-effective alternative to human annotation, they often suffer from inaccuracies and biases, even in powerful models like GPT-4. In this work, we introduce DS2, a Diversity-aware Score curation method for Data Selection. By systematically modeling error patterns through a score transition matrix, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10877","kind":"arxiv","version":2},"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/2410.10877/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":"2026-07-05T10:25:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QP3h5xRSKBDgolXV0ks6tnmZKA2pEHRvmgr4Cd0ubvw8DnEboWgwZrZFiO+b277gAaJoB+Q6bDmXIQyC4Fh6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:06:46.053521Z"},"content_sha256":"d6e328978c732ecc027306cfb49c0dd1d53bdf9e0e845ff88fcd5d44ed225e35","schema_version":"1.0","event_id":"sha256:d6e328978c732ecc027306cfb49c0dd1d53bdf9e0e845ff88fcd5d44ed225e35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YTD2BKHM4UX3KUZ3ZFNMB7QI22/bundle.json","state_url":"https://pith.science/pith/YTD2BKHM4UX3KUZ3ZFNMB7QI22/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YTD2BKHM4UX3KUZ3ZFNMB7QI22/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":"2026-08-11T01:06:46Z","links":{"resolver":"https://pith.science/pith/YTD2BKHM4UX3KUZ3ZFNMB7QI22","bundle":"https://pith.science/pith/YTD2BKHM4UX3KUZ3ZFNMB7QI22/bundle.json","state":"https://pith.science/pith/YTD2BKHM4UX3KUZ3ZFNMB7QI22/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YTD2BKHM4UX3KUZ3ZFNMB7QI22/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YTD2BKHM4UX3KUZ3ZFNMB7QI22","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":"8f46ff15397471b0e2206e506fc92cd931ef8142693d545835bcf8878599f557","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T10:07:55Z","title_canon_sha256":"3bc598cf64b4e68524fe87ded419fd91925130e094cc0a1e679e354f025c9b81"},"schema_version":"1.0","source":{"id":"2410.10877","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10877","created_at":"2026-07-05T10:25:11Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10877v2","created_at":"2026-07-05T10:25:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10877","created_at":"2026-07-05T10:25:11Z"},{"alias_kind":"pith_short_12","alias_value":"YTD2BKHM4UX3","created_at":"2026-07-05T10:25:11Z"},{"alias_kind":"pith_short_16","alias_value":"YTD2BKHM4UX3KUZ3","created_at":"2026-07-05T10:25:11Z"},{"alias_kind":"pith_short_8","alias_value":"YTD2BKHM","created_at":"2026-07-05T10:25:11Z"}],"graph_snapshots":[{"event_id":"sha256:d6e328978c732ecc027306cfb49c0dd1d53bdf9e0e845ff88fcd5d44ed225e35","target":"graph","created_at":"2026-07-05T10:25:11Z","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/2410.10877/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning is critical for adapting large language models (LLMs) to downstream tasks, and recent studies have demonstrated that small amounts of human-curated data can outperform larger datasets, challenging traditional data scaling laws. While LLM-based data quality rating systems offer a cost-effective alternative to human annotation, they often suffer from inaccuracies and biases, even in powerful models like GPT-4. In this work, we introduce DS2, a Diversity-aware Score curation method for Data Selection. By systematically modeling error patterns through a score transition matrix, ","authors_text":"Ankit Parag Shah, Chen Qian, Jiaheng Wei, Jinlong Pang, Wei Wei, Yang Liu, Yaxuan Wang, Yujia Bao, Zhaowei Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T10:07:55Z","title":"Improving Data Efficiency via Curating LLM-Driven Rating Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10877","kind":"arxiv","version":2},"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":"sha256:4aa9b730a2e56ac27338831622efd1321c74f5d1e7da6322383d9608ff0eb713","target":"record","created_at":"2026-07-05T10:25:11Z","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":"8f46ff15397471b0e2206e506fc92cd931ef8142693d545835bcf8878599f557","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T10:07:55Z","title_canon_sha256":"3bc598cf64b4e68524fe87ded419fd91925130e094cc0a1e679e354f025c9b81"},"schema_version":"1.0","source":{"id":"2410.10877","kind":"arxiv","version":2}},"canonical_sha256":"c4c7a0a8ece52fb5533bc95ac0fe08d6812c818d56eeb33c995851201e9b9239","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4c7a0a8ece52fb5533bc95ac0fe08d6812c818d56eeb33c995851201e9b9239","first_computed_at":"2026-07-05T10:25:11.745050Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:11.745050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pZgM0kjElEBCBaCbDu08ODfbdeTGQ30nzLndF0osHAsVFoVn56O6psYyiveMBIZRPhQX/vclsk6oxTZgu+mXCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:11.745925Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10877","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4aa9b730a2e56ac27338831622efd1321c74f5d1e7da6322383d9608ff0eb713","sha256:d6e328978c732ecc027306cfb49c0dd1d53bdf9e0e845ff88fcd5d44ed225e35"],"state_sha256":"18cc763926704c85b77e04e652631702146c7f01ced16f338afaca060be14e41"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ASFDBTRjPc1C3UKmRJO8DYf+dmJXXUAQaW9wc1pudMuD/O8q4X2g6sV8I/fGt+1IjMBr/Zy7DimDDJfStwFGCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:06:46.057376Z","bundle_sha256":"18cfdc554244493f6c161e8b8b7da624a1b00ad99cf2c3be6f7844658f4408c6"}}