{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YREXNXSENIPZAV7ONWI26N46LM","short_pith_number":"pith:YREXNXSE","canonical_record":{"source":{"id":"2311.05348","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-09T13:18:27Z","cross_cats_sorted":[],"title_canon_sha256":"fb093f2daa35ab5b5907f8ff6a1e11a04f5cfae3f30b46d240dc56d73de65c71","abstract_canon_sha256":"360b608bc0daa999c1a32e531b4e1207466fc68163aa0e65e59caac75484623b"},"schema_version":"1.0"},"canonical_sha256":"c44976de446a1f9057ee6d91af379e5b2b48f20a720ab9b09e90e9864277d05e","source":{"kind":"arxiv","id":"2311.05348","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05348","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05348v4","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05348","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"pith_short_12","alias_value":"YREXNXSENIPZ","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"pith_short_16","alias_value":"YREXNXSENIPZAV7O","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"pith_short_8","alias_value":"YREXNXSE","created_at":"2026-07-05T09:00:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YREXNXSENIPZAV7ONWI26N46LM","target":"record","payload":{"canonical_record":{"source":{"id":"2311.05348","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-09T13:18:27Z","cross_cats_sorted":[],"title_canon_sha256":"fb093f2daa35ab5b5907f8ff6a1e11a04f5cfae3f30b46d240dc56d73de65c71","abstract_canon_sha256":"360b608bc0daa999c1a32e531b4e1207466fc68163aa0e65e59caac75484623b"},"schema_version":"1.0"},"canonical_sha256":"c44976de446a1f9057ee6d91af379e5b2b48f20a720ab9b09e90e9864277d05e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:00.439053Z","signature_b64":"O4pjlrifUq0C+j+en5IgTzYTr8rSmcgeN4cmFC9NOEik44Q1LEbpZOJ4Ss4uM0grHHYsjFhoPPF+JJqcajkJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c44976de446a1f9057ee6d91af379e5b2b48f20a720ab9b09e90e9864277d05e","last_reissued_at":"2026-07-05T09:00:00.438534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:00.438534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.05348","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:00:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d8y1F02/4fzCVDIn0rKvbExI3qpq0ovnsoBszsTAfCrZHPzE31nZIu3x9hFdLjpBcpXbq7D5gJqYilMCbbqSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:05:54.335581Z"},"content_sha256":"0684501c8a298ab9631ed44bf7c7a3c87ce041aa75c872e207a6c42e886605f8","schema_version":"1.0","event_id":"sha256:0684501c8a298ab9631ed44bf7c7a3c87ce041aa75c872e207a6c42e886605f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YREXNXSENIPZAV7ONWI26N46LM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanyi Wang, Jinjin Xu, Liwu Xu, Xiang Li, Yanchun Xie, Yaqian Li, Yi-Jie Huang, Yuzhe Yang","submitted_at":"2023-11-09T13:18:27Z","abstract_excerpt":"Recent advancements in multi-modal large language models (MLLMs) have led to substantial improvements in visual understanding, primarily driven by sophisticated modality alignment strategies. However, predominant approaches prioritize global or regional comprehension, with less focus on fine-grained, pixel-level tasks. To address this gap, we introduce u-LLaVA, an innovative unifying multi-task framework that integrates pixel, regional, and global features to refine the perceptual faculties of MLLMs. We commence by leveraging an efficient modality alignment approach, harnessing both image and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05348","kind":"arxiv","version":4},"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/2311.05348/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":"2026-07-05T09:00:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"81fqZXHkwfPgbfhgBRlOmki6PA6rZcJhgDkV24wo+rOjt2ZPP5zoetZlqWx8Uv9M7oinQfg8jdG9QDxZ7yqmAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:05:54.336149Z"},"content_sha256":"50bab7f552104c17e8b807aefe57fce5973331e0856a9bbf3dba16c1ca102b30","schema_version":"1.0","event_id":"sha256:50bab7f552104c17e8b807aefe57fce5973331e0856a9bbf3dba16c1ca102b30"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YREXNXSENIPZAV7ONWI26N46LM/bundle.json","state_url":"https://pith.science/pith/YREXNXSENIPZAV7ONWI26N46LM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YREXNXSENIPZAV7ONWI26N46LM/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":"2026-08-09T06:05:54Z","links":{"resolver":"https://pith.science/pith/YREXNXSENIPZAV7ONWI26N46LM","bundle":"https://pith.science/pith/YREXNXSENIPZAV7ONWI26N46LM/bundle.json","state":"https://pith.science/pith/YREXNXSENIPZAV7ONWI26N46LM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YREXNXSENIPZAV7ONWI26N46LM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YREXNXSENIPZAV7ONWI26N46LM","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":"360b608bc0daa999c1a32e531b4e1207466fc68163aa0e65e59caac75484623b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-09T13:18:27Z","title_canon_sha256":"fb093f2daa35ab5b5907f8ff6a1e11a04f5cfae3f30b46d240dc56d73de65c71"},"schema_version":"1.0","source":{"id":"2311.05348","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05348","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05348v4","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05348","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"pith_short_12","alias_value":"YREXNXSENIPZ","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"pith_short_16","alias_value":"YREXNXSENIPZAV7O","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"pith_short_8","alias_value":"YREXNXSE","created_at":"2026-07-05T09:00:00Z"}],"graph_snapshots":[{"event_id":"sha256:50bab7f552104c17e8b807aefe57fce5973331e0856a9bbf3dba16c1ca102b30","target":"graph","created_at":"2026-07-05T09:00:00Z","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/2311.05348/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in multi-modal large language models (MLLMs) have led to substantial improvements in visual understanding, primarily driven by sophisticated modality alignment strategies. However, predominant approaches prioritize global or regional comprehension, with less focus on fine-grained, pixel-level tasks. To address this gap, we introduce u-LLaVA, an innovative unifying multi-task framework that integrates pixel, regional, and global features to refine the perceptual faculties of MLLMs. We commence by leveraging an efficient modality alignment approach, harnessing both image and ","authors_text":"Fanyi Wang, Jinjin Xu, Liwu Xu, Xiang Li, Yanchun Xie, Yaqian Li, Yi-Jie Huang, Yuzhe Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-09T13:18:27Z","title":"u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05348","kind":"arxiv","version":4},"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":"sha256:0684501c8a298ab9631ed44bf7c7a3c87ce041aa75c872e207a6c42e886605f8","target":"record","created_at":"2026-07-05T09:00:00Z","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":"360b608bc0daa999c1a32e531b4e1207466fc68163aa0e65e59caac75484623b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-09T13:18:27Z","title_canon_sha256":"fb093f2daa35ab5b5907f8ff6a1e11a04f5cfae3f30b46d240dc56d73de65c71"},"schema_version":"1.0","source":{"id":"2311.05348","kind":"arxiv","version":4}},"canonical_sha256":"c44976de446a1f9057ee6d91af379e5b2b48f20a720ab9b09e90e9864277d05e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c44976de446a1f9057ee6d91af379e5b2b48f20a720ab9b09e90e9864277d05e","first_computed_at":"2026-07-05T09:00:00.438534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:00.438534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O4pjlrifUq0C+j+en5IgTzYTr8rSmcgeN4cmFC9NOEik44Q1LEbpZOJ4Ss4uM0grHHYsjFhoPPF+JJqcajkJBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:00.439053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.05348","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0684501c8a298ab9631ed44bf7c7a3c87ce041aa75c872e207a6c42e886605f8","sha256:50bab7f552104c17e8b807aefe57fce5973331e0856a9bbf3dba16c1ca102b30"],"state_sha256":"345398dc341ebdbfec09da389c739760f262d049efecade0815962b27a1db3b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PDAw6sFrkpwq/TWN6cFZjSLdTump1saGuWvIdVgc2KFbbCoE6vsdVOOzcCPOfvFIo9R64inrG9SmB9v7LJnnAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:05:54.341291Z","bundle_sha256":"294000ef0c68d9334107f3d5f34eef9255944e89f337b5d418fc8fc374247134"}}