{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L65HYKBXLN2I6SRFPQKZSN6DQZ","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":"abb0203ae4ed67e9d3ad7fe812eb24a919d1dcd6a78068e5eef109cf1117a9f5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T03:43:20Z","title_canon_sha256":"a4bfd0d4b9f61ebdacc4b6b71eb0c4e94a3fe6b1cc7b461096555b7066c445b4"},"schema_version":"1.0","source":{"id":"2503.00034","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00034","created_at":"2026-07-05T10:22:16Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00034v1","created_at":"2026-07-05T10:22:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00034","created_at":"2026-07-05T10:22:16Z"},{"alias_kind":"pith_short_12","alias_value":"L65HYKBXLN2I","created_at":"2026-07-05T10:22:16Z"},{"alias_kind":"pith_short_16","alias_value":"L65HYKBXLN2I6SRF","created_at":"2026-07-05T10:22:16Z"},{"alias_kind":"pith_short_8","alias_value":"L65HYKBX","created_at":"2026-07-05T10:22:16Z"}],"graph_snapshots":[{"event_id":"sha256:d5145dd5d022cbcf878f29062e1700502357e5de1e6e850ff248f5f3777e0d15","target":"graph","created_at":"2026-07-05T10:22:16Z","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/2503.00034/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning is crucial for optimizing Large Language Models (LLMs), yet mainstream data selection methods heavily rely on LLMs as instruction quality scorers, leading to high computational costs and reduced data diversity. To address these limitations, we propose MergeIT, a novel LLM-based Merging strategy for better Instruction Tuning that shifts the focus from selection to synthesis. MergeIT operates in two stages: first, topic-aware filtering clusters and refines the dataset, preserving diversity while eliminating redundancy without relying on LLM-based scoring. Second, LLM-based mer","authors_text":"Bo Zhao, Hongming Fu, Hongyi Cai, Yuqian Fu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T03:43:20Z","title":"MergeIT: From Selection to Merging for Efficient Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00034","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":"sha256:6f8def25bfbfc39698c058abc938de9d3d3f59e78efa2052551b585d19e921b7","target":"record","created_at":"2026-07-05T10:22:16Z","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":"abb0203ae4ed67e9d3ad7fe812eb24a919d1dcd6a78068e5eef109cf1117a9f5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T03:43:20Z","title_canon_sha256":"a4bfd0d4b9f61ebdacc4b6b71eb0c4e94a3fe6b1cc7b461096555b7066c445b4"},"schema_version":"1.0","source":{"id":"2503.00034","kind":"arxiv","version":1}},"canonical_sha256":"5fba7c28375b748f4a257c159937c3865a526c25fcccbc2fbd35294068c181c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fba7c28375b748f4a257c159937c3865a526c25fcccbc2fbd35294068c181c3","first_computed_at":"2026-07-05T10:22:16.425514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:16.425514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rFZO2x0L13s38h9khGtEN+BeN4G/vmOaKyIgYjGX5ZqrHFnnocb3/5zeaa03Z7lY4SdEsq6BvgMo4Jw/8E6pBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:16.426079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.00034","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f8def25bfbfc39698c058abc938de9d3d3f59e78efa2052551b585d19e921b7","sha256:d5145dd5d022cbcf878f29062e1700502357e5de1e6e850ff248f5f3777e0d15"],"state_sha256":"ce0138ec40da4ed92400a6c8f3221b4a443b97ad5562b6f19b96d23cba19bb26"}