{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NHUJGXMKDUQPGCF5KEFBEJJ4KN","short_pith_number":"pith:NHUJGXMK","canonical_record":{"source":{"id":"2501.02189","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-04T04:59:33Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"f85498efff5748632c64b09be566c6d59547d3dfde655f5683c7df6b75ba9c5f","abstract_canon_sha256":"abde317e13d4e6e398269c21c83c5d705aade9c61890d09d67eb2ed166921b8b"},"schema_version":"1.0"},"canonical_sha256":"69e8935d8a1d20f308bd510a12253c53684f0c293f856a5488701526c8cae986","source":{"kind":"arxiv","id":"2501.02189","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02189","created_at":"2026-07-05T10:45:16Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02189v6","created_at":"2026-07-05T10:45:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02189","created_at":"2026-07-05T10:45:16Z"},{"alias_kind":"pith_short_12","alias_value":"NHUJGXMKDUQP","created_at":"2026-07-05T10:45:16Z"},{"alias_kind":"pith_short_16","alias_value":"NHUJGXMKDUQPGCF5","created_at":"2026-07-05T10:45:16Z"},{"alias_kind":"pith_short_8","alias_value":"NHUJGXMK","created_at":"2026-07-05T10:45:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NHUJGXMKDUQPGCF5KEFBEJJ4KN","target":"record","payload":{"canonical_record":{"source":{"id":"2501.02189","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-04T04:59:33Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"f85498efff5748632c64b09be566c6d59547d3dfde655f5683c7df6b75ba9c5f","abstract_canon_sha256":"abde317e13d4e6e398269c21c83c5d705aade9c61890d09d67eb2ed166921b8b"},"schema_version":"1.0"},"canonical_sha256":"69e8935d8a1d20f308bd510a12253c53684f0c293f856a5488701526c8cae986","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:16.094693Z","signature_b64":"IQK9TJKEGl99cwfnhA/5rF3raL94MTD6cVjpR8oDaDxb0QzbDRw56g02Ew1330h6N3fXx3V5WtEYhYTwBShMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69e8935d8a1d20f308bd510a12253c53684f0c293f856a5488701526c8cae986","last_reissued_at":"2026-07-05T10:45:16.094164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:16.094164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.02189","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:45:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"re3jetGEi+I6LwU0QIx8AJztpuyfvgC9UNCQdLw9/MNO3wXw9HHbFBnkt6tJ9A7MLGPgVwzQsIsnBaA6IdCpAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T23:52:18.597878Z"},"content_sha256":"f67dfccc476ef5a535d3f9d1d912709ecf24121b1600521f0860f72f15655ca4","schema_version":"1.0","event_id":"sha256:f67dfccc476ef5a535d3f9d1d912709ecf24121b1600521f0860f72f15655ca4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NHUJGXMKDUQPGCF5KEFBEJJ4KN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Fuxiao Liu, Guangyao Shi, Hongyang Du, Huy Nghiem, Xiyang Wu, Zongxia Li","submitted_at":"2025-01-04T04:59:33Z","abstract_excerpt":"Multimodal Vision Language Models (VLMs) have emerged as a transformative topic at the intersection of computer vision and natural language processing, enabling machines to perceive and reason about the world through both visual and textual modalities. For example, models such as CLIP, Claude, and GPT-4V demonstrate strong reasoning and understanding abilities on visual and textual data and beat classical single modality vision models on zero-shot classification [93]. With their rapid advancements in research and growing popularity in various applications, we provide a comprehensive survey of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02189","kind":"arxiv","version":6},"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/2501.02189/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":"2026-07-05T10:45:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A/ZnfhmvVtaqMzY0OmObC7dOOaVm4A14bkzPgnma21xxOf3Ple8O9RzxIvSvH3Mvj6hLtZo3T9jGwhCncO10Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T23:52:18.598230Z"},"content_sha256":"71d0c9af4c211d309d7612e86437d20f36998b004ce0ee1b0cebd792a19463b9","schema_version":"1.0","event_id":"sha256:71d0c9af4c211d309d7612e86437d20f36998b004ce0ee1b0cebd792a19463b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NHUJGXMKDUQPGCF5KEFBEJJ4KN/bundle.json","state_url":"https://pith.science/pith/NHUJGXMKDUQPGCF5KEFBEJJ4KN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NHUJGXMKDUQPGCF5KEFBEJJ4KN/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":"2026-08-21T23:52:18Z","links":{"resolver":"https://pith.science/pith/NHUJGXMKDUQPGCF5KEFBEJJ4KN","bundle":"https://pith.science/pith/NHUJGXMKDUQPGCF5KEFBEJJ4KN/bundle.json","state":"https://pith.science/pith/NHUJGXMKDUQPGCF5KEFBEJJ4KN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NHUJGXMKDUQPGCF5KEFBEJJ4KN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NHUJGXMKDUQPGCF5KEFBEJJ4KN","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":"abde317e13d4e6e398269c21c83c5d705aade9c61890d09d67eb2ed166921b8b","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-04T04:59:33Z","title_canon_sha256":"f85498efff5748632c64b09be566c6d59547d3dfde655f5683c7df6b75ba9c5f"},"schema_version":"1.0","source":{"id":"2501.02189","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02189","created_at":"2026-07-05T10:45:16Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02189v6","created_at":"2026-07-05T10:45:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02189","created_at":"2026-07-05T10:45:16Z"},{"alias_kind":"pith_short_12","alias_value":"NHUJGXMKDUQP","created_at":"2026-07-05T10:45:16Z"},{"alias_kind":"pith_short_16","alias_value":"NHUJGXMKDUQPGCF5","created_at":"2026-07-05T10:45:16Z"},{"alias_kind":"pith_short_8","alias_value":"NHUJGXMK","created_at":"2026-07-05T10:45:16Z"}],"graph_snapshots":[{"event_id":"sha256:71d0c9af4c211d309d7612e86437d20f36998b004ce0ee1b0cebd792a19463b9","target":"graph","created_at":"2026-07-05T10:45:16Z","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/2501.02189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Vision Language Models (VLMs) have emerged as a transformative topic at the intersection of computer vision and natural language processing, enabling machines to perceive and reason about the world through both visual and textual modalities. For example, models such as CLIP, Claude, and GPT-4V demonstrate strong reasoning and understanding abilities on visual and textual data and beat classical single modality vision models on zero-shot classification [93]. With their rapid advancements in research and growing popularity in various applications, we provide a comprehensive survey of ","authors_text":"Fuxiao Liu, Guangyao Shi, Hongyang Du, Huy Nghiem, Xiyang Wu, Zongxia Li","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-04T04:59:33Z","title":"A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02189","kind":"arxiv","version":6},"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:f67dfccc476ef5a535d3f9d1d912709ecf24121b1600521f0860f72f15655ca4","target":"record","created_at":"2026-07-05T10:45:16Z","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":"abde317e13d4e6e398269c21c83c5d705aade9c61890d09d67eb2ed166921b8b","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-04T04:59:33Z","title_canon_sha256":"f85498efff5748632c64b09be566c6d59547d3dfde655f5683c7df6b75ba9c5f"},"schema_version":"1.0","source":{"id":"2501.02189","kind":"arxiv","version":6}},"canonical_sha256":"69e8935d8a1d20f308bd510a12253c53684f0c293f856a5488701526c8cae986","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69e8935d8a1d20f308bd510a12253c53684f0c293f856a5488701526c8cae986","first_computed_at":"2026-07-05T10:45:16.094164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:16.094164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IQK9TJKEGl99cwfnhA/5rF3raL94MTD6cVjpR8oDaDxb0QzbDRw56g02Ew1330h6N3fXx3V5WtEYhYTwBShMCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:16.094693Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.02189","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f67dfccc476ef5a535d3f9d1d912709ecf24121b1600521f0860f72f15655ca4","sha256:71d0c9af4c211d309d7612e86437d20f36998b004ce0ee1b0cebd792a19463b9"],"state_sha256":"f1c227741f4a7145c5c45403d840d1b7c4ef20e81d9474751957bcc1a1d27bb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TyJf6aHyhxS18KUL4NmfVtMXHWwvd2k0b0oyFzw2lAlF+nlP0micwTQsIEKrd6iYtfa5qyMzBCLbdGK5Q3d7BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T23:52:18.601347Z","bundle_sha256":"644d2ba67c12068b402e71b01bf8ed9557eda8d9010e4f3945e4e27dde5bfe3e"}}