{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q65S5ERWN3ZBMXNTK66SRKACID","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":"4b22facfa9301417f3da7928f04a5c1d135ad8e0456d5a5e15dd715eeb2be1db","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T19:26:49Z","title_canon_sha256":"a0bc00dfb7156eebdaef3999fd45133da6ea0ec7176ff248e2e45132d0bca1ee"},"schema_version":"1.0","source":{"id":"2402.11684","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11684","created_at":"2026-05-23T22:17:25Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11684v2","created_at":"2026-05-23T22:17:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11684","created_at":"2026-05-23T22:17:25Z"},{"alias_kind":"pith_short_12","alias_value":"Q65S5ERWN3ZB","created_at":"2026-05-23T22:17:25Z"},{"alias_kind":"pith_short_16","alias_value":"Q65S5ERWN3ZBMXNT","created_at":"2026-05-23T22:17:25Z"},{"alias_kind":"pith_short_8","alias_value":"Q65S5ERW","created_at":"2026-05-23T22:17:25Z"}],"graph_snapshots":[{"event_id":"sha256:2b013d14788d8028fea2804442308150af42a6b2df0b4d5eb1abfb3939d68f79","target":"graph","created_at":"2026-05-23T22:17:25Z","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/2402.11684/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision-language models (LVLMs) have shown premise in a broad range of vision-language tasks with their strong reasoning and generalization capabilities. However, they require considerable computational resources for training and deployment. This study aims to bridge the performance gap between traditional-scale LVLMs and resource-friendly lite versions by adopting high-quality training data. To this end, we propose a comprehensive pipeline for generating a synthetic dataset. The key idea is to leverage strong proprietary models to generate (i) fine-grained image annotations for vision-la","authors_text":"Benyou Wang, Guiming Hardy Chen, Jianquan Li, Junying Chen, Ruifei Zhang, Shunian Chen, Xiangbo Wu, Xiang Wan, Zhihong Chen, Zhiyi Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T19:26:49Z","title":"ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11684","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:e552c92c2a94c74883933e58fe07dee52eacefdbe9857db88648b7d5e74716ec","target":"record","created_at":"2026-05-23T22:17:25Z","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":"4b22facfa9301417f3da7928f04a5c1d135ad8e0456d5a5e15dd715eeb2be1db","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T19:26:49Z","title_canon_sha256":"a0bc00dfb7156eebdaef3999fd45133da6ea0ec7176ff248e2e45132d0bca1ee"},"schema_version":"1.0","source":{"id":"2402.11684","kind":"arxiv","version":2}},"canonical_sha256":"87bb2e92366ef2165db357bd28a80240e79b5ac5ec2d4efb435bbb79a45b75e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87bb2e92366ef2165db357bd28a80240e79b5ac5ec2d4efb435bbb79a45b75e6","first_computed_at":"2026-05-23T22:17:25.756870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-23T22:17:25.756870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1JeO/fKtZ8mmHg+t+rdMWjVFuXgrX0KkKeA5WkQDqc/kWIcO1XeIOzI6LA0DSyKGZByIclCWeSHf99ZoJAV9Dg==","signature_status":"signed_v1","signed_at":"2026-05-23T22:17:25.760227Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11684","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e552c92c2a94c74883933e58fe07dee52eacefdbe9857db88648b7d5e74716ec","sha256:2b013d14788d8028fea2804442308150af42a6b2df0b4d5eb1abfb3939d68f79"],"state_sha256":"b0077c094b1369350f5c3d30c20151beb084efab9aa46bad882e471ade310ecc"}