{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HEUKQMNYONJ3WPLCZCAN5DB2QI","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":"3d623de2562222772e49c891006299d5310c23a541fd80c09c566a47e4cfb9cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T12:42:37Z","title_canon_sha256":"c7e17c6066fda355f44a22a9e8a5db92231c7fdef4fad6aef89bfeb87452b462"},"schema_version":"1.0","source":{"id":"2503.20502","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.20502","created_at":"2026-07-05T10:41:23Z"},{"alias_kind":"arxiv_version","alias_value":"2503.20502v2","created_at":"2026-07-05T10:41:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20502","created_at":"2026-07-05T10:41:23Z"},{"alias_kind":"pith_short_12","alias_value":"HEUKQMNYONJ3","created_at":"2026-07-05T10:41:23Z"},{"alias_kind":"pith_short_16","alias_value":"HEUKQMNYONJ3WPLC","created_at":"2026-07-05T10:41:23Z"},{"alias_kind":"pith_short_8","alias_value":"HEUKQMNY","created_at":"2026-07-05T10:41:23Z"}],"graph_snapshots":[{"event_id":"sha256:3dd3db60cdb8e46ce127f1e9579e388e131368b5040abbf7498d139807eed77d","target":"graph","created_at":"2026-07-05T10:41:23Z","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/2503.20502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual instruction tuning (VIT) has emerged as a crucial technique for enabling multi-modal large language models (MLLMs) to follow user instructions adeptly. Yet, a significant gap persists in understanding the attributes of high-quality instruction tuning data and frameworks for its automated selection. To address this, we introduce MLLM-Selector, an automated approach that identifies valuable data for VIT by weighing necessity and diversity. Our process starts by randomly sampling a subset from the VIT data pool to fine-tune a pretrained model, thus creating a seed model with an initial abi","authors_text":"Debing Zhang, Guohai Xu, Jiayi Ji, Jie Lou, Rongrong Ji, Xiaoshuai Sun, Yiwei Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T12:42:37Z","title":"MLLM-Selector: Necessity and Diversity-driven High-Value Data Selection for Enhanced Visual Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20502","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:cd4649250303f299b5ba024073e7bdfe2d52af53244da2d92f60a3caf0689ac9","target":"record","created_at":"2026-07-05T10:41:23Z","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":"3d623de2562222772e49c891006299d5310c23a541fd80c09c566a47e4cfb9cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T12:42:37Z","title_canon_sha256":"c7e17c6066fda355f44a22a9e8a5db92231c7fdef4fad6aef89bfeb87452b462"},"schema_version":"1.0","source":{"id":"2503.20502","kind":"arxiv","version":2}},"canonical_sha256":"3928a831b87353bb3d62c880de8c3a823894906b730eac4cf2e768f6bd4ff3f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3928a831b87353bb3d62c880de8c3a823894906b730eac4cf2e768f6bd4ff3f9","first_computed_at":"2026-07-05T10:41:23.414647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:23.414647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"puznyK2+2qUfPRpGLEraRdzHtIA0/YyXF46B9lmm2pUpxcdj+YvxUzLKY3P5vFC6POQJmxsoDOL5/VLdMZRqBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:23.415159Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.20502","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd4649250303f299b5ba024073e7bdfe2d52af53244da2d92f60a3caf0689ac9","sha256:3dd3db60cdb8e46ce127f1e9579e388e131368b5040abbf7498d139807eed77d"],"state_sha256":"645b3547534e819588cd5195340a20ae739c5cf7e173065cfdc65143d828e7a1"}