{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NOEBP4JEAST6A5LXT6SMTXCC6V","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":"fe7889df4d4cd57a994f91d9311631d65d82641ada27db56949ecb7bb3fe638a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T13:45:46Z","title_canon_sha256":"aaf0d86f16d7973a581c07171cd04d058af2cd5dfb4f3738b22d0591e0998980"},"schema_version":"1.0","source":{"id":"2403.02969","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.02969","created_at":"2026-07-05T08:00:02Z"},{"alias_kind":"arxiv_version","alias_value":"2403.02969v2","created_at":"2026-07-05T08:00:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02969","created_at":"2026-07-05T08:00:02Z"},{"alias_kind":"pith_short_12","alias_value":"NOEBP4JEAST6","created_at":"2026-07-05T08:00:02Z"},{"alias_kind":"pith_short_16","alias_value":"NOEBP4JEAST6A5LX","created_at":"2026-07-05T08:00:02Z"},{"alias_kind":"pith_short_8","alias_value":"NOEBP4JE","created_at":"2026-07-05T08:00:02Z"}],"graph_snapshots":[{"event_id":"sha256:bfe67be4c29b9080f1041fd82ce462dcaad72b98aa9dc58dcb00d85517264e47","target":"graph","created_at":"2026-07-05T08:00:02Z","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/2403.02969/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Model (MLLMs) leverages Large Language Models as a cognitive framework for diverse visual-language tasks. Recent efforts have been made to equip MLLMs with visual perceiving and grounding capabilities. However, there still remains a gap in providing fine-grained pixel-level perceptions and extending interactions beyond text-specific inputs. In this work, we propose {\\bf{AnyRef}}, a general MLLM model that can generate pixel-wise object perceptions and natural language descriptions from multi-modality references, such as texts, boxes, images, or audio. This innovation ","authors_text":"Bin Luo, Huchuan Lu, Jin-Peng Lan, Junwen He, Jun-Yan He, Lijun Wang, Xuansong Xie, Yifan Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T13:45:46Z","title":"Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02969","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:dd95bcd5f6b376930decd466fa4adf78ff267c3907d8e2dc2d1157897402d929","target":"record","created_at":"2026-07-05T08:00:02Z","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":"fe7889df4d4cd57a994f91d9311631d65d82641ada27db56949ecb7bb3fe638a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T13:45:46Z","title_canon_sha256":"aaf0d86f16d7973a581c07171cd04d058af2cd5dfb4f3738b22d0591e0998980"},"schema_version":"1.0","source":{"id":"2403.02969","kind":"arxiv","version":2}},"canonical_sha256":"6b8817f12404a7e075779fa4c9dc42f546e792a63dfab6956c070aaffa899d45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b8817f12404a7e075779fa4c9dc42f546e792a63dfab6956c070aaffa899d45","first_computed_at":"2026-07-05T08:00:02.557013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:02.557013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z4l1OrM5jJUcIDyu5dpryLqqFqGhYg8e4iZ8+sGpw+Sgs5qyW3CIpPvw/h45u9Ml8ow1FEw/I/LICcOhlWeGBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:02.557617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.02969","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd95bcd5f6b376930decd466fa4adf78ff267c3907d8e2dc2d1157897402d929","sha256:bfe67be4c29b9080f1041fd82ce462dcaad72b98aa9dc58dcb00d85517264e47"],"state_sha256":"7eb09705732c80e78dc568b5127ffc9dccef69903fbd62f3e77d5f5a61234c0f"}