{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5H6X6ZCV63ZMAH5LCOC7WBKBVX","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":"0317ae8016f4ba8fea98d022ccdd3e0b4c4e711bd6365f40a7e466bf70f20685","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T05:15:59Z","title_canon_sha256":"5c0f66a8238d045762ad45fdd876b19ce9e22893d3cfaa8a04320895e0cd104e"},"schema_version":"1.0","source":{"id":"2501.02765","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02765","created_at":"2026-07-05T09:57:11Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02765v1","created_at":"2026-07-05T09:57:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02765","created_at":"2026-07-05T09:57:11Z"},{"alias_kind":"pith_short_12","alias_value":"5H6X6ZCV63ZM","created_at":"2026-07-05T09:57:11Z"},{"alias_kind":"pith_short_16","alias_value":"5H6X6ZCV63ZMAH5L","created_at":"2026-07-05T09:57:11Z"},{"alias_kind":"pith_short_8","alias_value":"5H6X6ZCV","created_at":"2026-07-05T09:57:11Z"}],"graph_snapshots":[{"event_id":"sha256:d981d03656fa131bf57c609f97953b1a39332c174de7eaa6e90b0cdf814f7549","target":"graph","created_at":"2026-07-05T09:57:11Z","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/2501.02765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual-language models (VLM) have emerged as a powerful tool for learning a unified embedding space for vision and language. Inspired by large language models, which have demonstrated strong reasoning and multi-task capabilities, visual large language models (VLLMs) are gaining increasing attention for building general-purpose VLMs. Despite the significant progress made in VLLMs, the related literature remains limited, particularly from a comprehensive application perspective, encompassing generalized and specialized applications across vision (image, video, depth), action, and language modali","authors_text":"Anh Dao, Dong Liu, Huan Liu, Jiayi Shen, Kewei Sui, Wentao Bao, Yifan Li, Yu Kong, Zhen Tan, Zhixin Lai","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T05:15:59Z","title":"Visual Large Language Models for Generalized and Specialized Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02765","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":"sha256:389fbc664c054646dff159f93846bc9a3a530e0567907ecbabea3d2b73544a49","target":"record","created_at":"2026-07-05T09:57:11Z","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":"0317ae8016f4ba8fea98d022ccdd3e0b4c4e711bd6365f40a7e466bf70f20685","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T05:15:59Z","title_canon_sha256":"5c0f66a8238d045762ad45fdd876b19ce9e22893d3cfaa8a04320895e0cd104e"},"schema_version":"1.0","source":{"id":"2501.02765","kind":"arxiv","version":1}},"canonical_sha256":"e9fd7f6455f6f2c01fab1385fb0541ade1384e869ff8cd88d11b0172d70eca3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9fd7f6455f6f2c01fab1385fb0541ade1384e869ff8cd88d11b0172d70eca3a","first_computed_at":"2026-07-05T09:57:11.850532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:11.850532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1tUFIDb0dK4pIJDhswanepKTyJRlXqoGihjdnRTI0DIoE/betwpFMNOf8qJs2y4WYAeW+yFUxkXZkUev6YMbDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:11.850989Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.02765","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:389fbc664c054646dff159f93846bc9a3a530e0567907ecbabea3d2b73544a49","sha256:d981d03656fa131bf57c609f97953b1a39332c174de7eaa6e90b0cdf814f7549"],"state_sha256":"ba24b53f5cd279ab76a6ba5636ea72f9636f53dee14a8efbb5abb9d90d127737"}