{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MSNILLIYUB6YZZZ3GPQEZR4FTU","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":"c508331177c0fcfdeb3819c71f31712d8e96056530820a779596b599df9096ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T20:08:48Z","title_canon_sha256":"c0cfd2039903060e43d9236a3aa6e537f23bf9ff451b78c71f0b6d2fa495096e"},"schema_version":"1.0","source":{"id":"2402.12501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12501","created_at":"2026-07-05T07:47:12Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12501v1","created_at":"2026-07-05T07:47:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12501","created_at":"2026-07-05T07:47:12Z"},{"alias_kind":"pith_short_12","alias_value":"MSNILLIYUB6Y","created_at":"2026-07-05T07:47:12Z"},{"alias_kind":"pith_short_16","alias_value":"MSNILLIYUB6YZZZ3","created_at":"2026-07-05T07:47:12Z"},{"alias_kind":"pith_short_8","alias_value":"MSNILLIY","created_at":"2026-07-05T07:47:12Z"}],"graph_snapshots":[{"event_id":"sha256:3e724f35da4bea3b87dcbf539f8b375b60335e946e8cc30cfcaa26bd2f0dff70","target":"graph","created_at":"2026-07-05T07:47:12Z","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/2402.12501/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data selection in instruction tuning emerges as a pivotal process for acquiring high-quality data and training instruction-following large language models (LLMs), but it is still a new and unexplored research area for vision-language models (VLMs). Existing data selection approaches on LLMs either rely on single unreliable scores, or use downstream tasks for selection, which is time-consuming and can lead to potential over-fitting on the chosen evaluation datasets. To address this challenge, we introduce a novel dataset selection method, Self-Filter, that utilizes the VLM itself as a filter. T","authors_text":"Chenxi Liu, Guodong Liu, Heng Huang, Junfeng Guo, Lichang Chen, Qi He, Ruibo Chen, Tianyi Xiong, Yihan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T20:08:48Z","title":"Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12501","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:f5fbc016b3bf7ebd89a681cf72e2ca452bf3f6a1b0f26da23901981b359f814e","target":"record","created_at":"2026-07-05T07:47:12Z","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":"c508331177c0fcfdeb3819c71f31712d8e96056530820a779596b599df9096ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T20:08:48Z","title_canon_sha256":"c0cfd2039903060e43d9236a3aa6e537f23bf9ff451b78c71f0b6d2fa495096e"},"schema_version":"1.0","source":{"id":"2402.12501","kind":"arxiv","version":1}},"canonical_sha256":"649a85ad18a07d8ce73b33e04cc7859d32ab8d6fbf0cef732f8c7f1042a0875f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"649a85ad18a07d8ce73b33e04cc7859d32ab8d6fbf0cef732f8c7f1042a0875f","first_computed_at":"2026-07-05T07:47:12.215549Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:12.215549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pw9ujIIhVMTt0SbgxPLwFch9b8DXjhnvi2pogwrmRtxBtLMXC7oqkdaPdQLv/B0C9yncGUZW5LNX1doDi8HiCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:12.215935Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5fbc016b3bf7ebd89a681cf72e2ca452bf3f6a1b0f26da23901981b359f814e","sha256:3e724f35da4bea3b87dcbf539f8b375b60335e946e8cc30cfcaa26bd2f0dff70"],"state_sha256":"d0380b14616a9b9f8830bd934baaebd847c3508b644a6d813212fffed08e40c4"}