{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q65S5ERWN3ZBMXNTK66SRKACID","short_pith_number":"pith:Q65S5ERW","canonical_record":{"source":{"id":"2402.11684","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T19:26:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a0bc00dfb7156eebdaef3999fd45133da6ea0ec7176ff248e2e45132d0bca1ee","abstract_canon_sha256":"4b22facfa9301417f3da7928f04a5c1d135ad8e0456d5a5e15dd715eeb2be1db"},"schema_version":"1.0"},"canonical_sha256":"87bb2e92366ef2165db357bd28a80240e79b5ac5ec2d4efb435bbb79a45b75e6","source":{"kind":"arxiv","id":"2402.11684","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q65S5ERWN3ZBMXNTK66SRKACID","target":"record","payload":{"canonical_record":{"source":{"id":"2402.11684","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T19:26:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a0bc00dfb7156eebdaef3999fd45133da6ea0ec7176ff248e2e45132d0bca1ee","abstract_canon_sha256":"4b22facfa9301417f3da7928f04a5c1d135ad8e0456d5a5e15dd715eeb2be1db"},"schema_version":"1.0"},"canonical_sha256":"87bb2e92366ef2165db357bd28a80240e79b5ac5ec2d4efb435bbb79a45b75e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-23T22:17:25.760227Z","signature_b64":"1JeO/fKtZ8mmHg+t+rdMWjVFuXgrX0KkKeA5WkQDqc/kWIcO1XeIOzI6LA0DSyKGZByIclCWeSHf99ZoJAV9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87bb2e92366ef2165db357bd28a80240e79b5ac5ec2d4efb435bbb79a45b75e6","last_reissued_at":"2026-05-23T22:17:25.756870Z","signature_status":"signed_v1","first_computed_at":"2026-05-23T22:17:25.756870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.11684","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-23T22:17:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SDDJNW+zhKQcvEma6YcB8/0n2Zz1xogIL8+WTewe1pBUmK2rWzgNC3FtPvugzGARALBBwUZuou2oVONncaCOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:52:34.019836Z"},"content_sha256":"e552c92c2a94c74883933e58fe07dee52eacefdbe9857db88648b7d5e74716ec","schema_version":"1.0","event_id":"sha256:e552c92c2a94c74883933e58fe07dee52eacefdbe9857db88648b7d5e74716ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q65S5ERWN3ZBMXNTK66SRKACID","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Guiming Hardy Chen, Jianquan Li, Junying Chen, Ruifei Zhang, Shunian Chen, Xiangbo Wu, Xiang Wan, Zhihong Chen, Zhiyi Zhang","submitted_at":"2024-02-18T19:26:49Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11684","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.11684/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-23T22:17:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zeXoFY58SBAziVwxpcFIwtlZAazmnWz7IfCpakQTR5eNTN++yvO/sRYeOPA45jR45mFcynlLV1V/0mSQaK3UDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:52:34.020558Z"},"content_sha256":"2b013d14788d8028fea2804442308150af42a6b2df0b4d5eb1abfb3939d68f79","schema_version":"1.0","event_id":"sha256:2b013d14788d8028fea2804442308150af42a6b2df0b4d5eb1abfb3939d68f79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q65S5ERWN3ZBMXNTK66SRKACID/bundle.json","state_url":"https://pith.science/pith/Q65S5ERWN3ZBMXNTK66SRKACID/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q65S5ERWN3ZBMXNTK66SRKACID/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T19:52:34Z","links":{"resolver":"https://pith.science/pith/Q65S5ERWN3ZBMXNTK66SRKACID","bundle":"https://pith.science/pith/Q65S5ERWN3ZBMXNTK66SRKACID/bundle.json","state":"https://pith.science/pith/Q65S5ERWN3ZBMXNTK66SRKACID/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q65S5ERWN3ZBMXNTK66SRKACID/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NJhwqb4Cy0eIE+gzgbMmjPdh4SQEgkD0l2MPJJgRIP8D5GiwH9bOOdepK50n+l/mHWiN1dHUnVZJBdB8XMWHCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:52:34.023866Z","bundle_sha256":"cb62cd450f9c8d989547dca3e8db2594d0e72bcd4af64b1cc3144badd0a0c18e"}}