{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GHRDJXCJERPWLOEIP5BXEC6JFH","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":"4788dfd63f15617f688b783afcd17870354827820bc7bdc81f2ad26ee5599129","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T11:16:34Z","title_canon_sha256":"f5fe922d4b4a602de78e7793738d339a516e06eea7060d1c7bb1ee27929810d0"},"schema_version":"1.0","source":{"id":"2410.12458","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12458","created_at":"2026-07-05T11:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12458v2","created_at":"2026-07-05T11:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12458","created_at":"2026-07-05T11:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"GHRDJXCJERPW","created_at":"2026-07-05T11:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"GHRDJXCJERPWLOEI","created_at":"2026-07-05T11:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"GHRDJXCJ","created_at":"2026-07-05T11:10:01Z"}],"graph_snapshots":[{"event_id":"sha256:ae21cd2d3907fda9587091645052fe8ad7f48a4f225897993e4f477578b4e218","target":"graph","created_at":"2026-07-05T11:10:01Z","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/2410.12458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The performance of large language models (LLMs) is strongly influenced by the quality and diversity of data used during supervised fine-tuning (SFT). However, current data selection methods often prioritize one aspect over the other, resulting in suboptimal training outcomes. To address this, we formulate data selection as a set cover problem and present GraphFilter, a novel approach that balances both quality and diversity in data selection. GraphFilter models the dataset as a bipartite graph connecting sentences to their constituent n-grams, then employs a priority function that combines qua","authors_text":"Gholamreza Haffari, Lizhen Qu, Minghao Wu, Thuy-Trang Vu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T11:16:34Z","title":"The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12458","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":"sha256:25350cad68747ad25c570086bad5f14b45000b1908852de43a1995f0e55cdcb2","target":"record","created_at":"2026-07-05T11:10:01Z","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":"4788dfd63f15617f688b783afcd17870354827820bc7bdc81f2ad26ee5599129","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T11:16:34Z","title_canon_sha256":"f5fe922d4b4a602de78e7793738d339a516e06eea7060d1c7bb1ee27929810d0"},"schema_version":"1.0","source":{"id":"2410.12458","kind":"arxiv","version":2}},"canonical_sha256":"31e234dc49245f65b8887f43720bc929cf5acd19cd7b2dfa6070404184079a51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31e234dc49245f65b8887f43720bc929cf5acd19cd7b2dfa6070404184079a51","first_computed_at":"2026-07-05T11:10:01.636775Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:01.636775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PgRuoVKov7q5NeuuyObjhEKojVJV5Co9SGWi09swvfvd3iw8uVFgG0YE2C8gqeYQGXpI3/JwleVxCrEyscQOAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:01.637833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12458","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25350cad68747ad25c570086bad5f14b45000b1908852de43a1995f0e55cdcb2","sha256:ae21cd2d3907fda9587091645052fe8ad7f48a4f225897993e4f477578b4e218"],"state_sha256":"36171ad6110eeeb5387cdd4c1ada3fb9fe0093d020c4f3575d20507cc37efff7"}