{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:D62G5RZCNJT2O2GLF6JD436MDY","short_pith_number":"pith:D62G5RZC","schema_version":"1.0","canonical_sha256":"1fb46ec7226a67a768cb2f923e6fcc1e32f9d5c0fea8af2a6c0770480e88e0e7","source":{"kind":"arxiv","id":"2308.00692","version":3},"attestation_state":"computed","paper":{"title":"LISA: Reasoning Segmentation via Large Language Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaya Jia, Shu Liu, Xin Lai, Yanwei Li, Yuhui Yuan, Yukang Chen, Zhuotao Tian","submitted_at":"2023-08-01T17:50:17Z","abstract_excerpt":"Although perception systems have made remarkable advancements in recent years, they still rely on explicit human instruction or pre-defined categories to identify the target objects before executing visual recognition tasks. Such systems cannot actively reason and comprehend implicit user intention. In this work, we propose a new segmentation task -- reasoning segmentation. The task is designed to output a segmentation mask given a complex and implicit query text. Furthermore, we establish a benchmark comprising over one thousand image-instruction-mask data samples, incorporating intricate rea"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.00692","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-01T17:50:17Z","cross_cats_sorted":[],"title_canon_sha256":"948ea1588e7152cf9ef9b20c00236fbc469a9a96b112e56a5fbab5121e7208e5","abstract_canon_sha256":"893ffb7450c9b9e3471dd14fcf69e9508eb3ce21e3991040dccfec66351d0f57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:00.349051Z","signature_b64":"Fn4DhDPYIs7h93KRa/SO8yyrvcU8zbyqIOrtTy3NulQVwtOcMgsCF72JIw86e+D/DJBMT9j2VQmixquAJHkVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fb46ec7226a67a768cb2f923e6fcc1e32f9d5c0fea8af2a6c0770480e88e0e7","last_reissued_at":"2026-07-05T08:14:00.348563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:00.348563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LISA: Reasoning Segmentation via Large Language Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaya Jia, Shu Liu, Xin Lai, Yanwei Li, Yuhui Yuan, Yukang Chen, Zhuotao Tian","submitted_at":"2023-08-01T17:50:17Z","abstract_excerpt":"Although perception systems have made remarkable advancements in recent years, they still rely on explicit human instruction or pre-defined categories to identify the target objects before executing visual recognition tasks. Such systems cannot actively reason and comprehend implicit user intention. In this work, we propose a new segmentation task -- reasoning segmentation. The task is designed to output a segmentation mask given a complex and implicit query text. Furthermore, we establish a benchmark comprising over one thousand image-instruction-mask data samples, incorporating intricate rea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.00692","kind":"arxiv","version":3},"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/2308.00692/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.00692","created_at":"2026-07-05T08:14:00.348617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.00692v3","created_at":"2026-07-05T08:14:00.348617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.00692","created_at":"2026-07-05T08:14:00.348617+00:00"},{"alias_kind":"pith_short_12","alias_value":"D62G5RZCNJT2","created_at":"2026-07-05T08:14:00.348617+00:00"},{"alias_kind":"pith_short_16","alias_value":"D62G5RZCNJT2O2GL","created_at":"2026-07-05T08:14:00.348617+00:00"},{"alias_kind":"pith_short_8","alias_value":"D62G5RZC","created_at":"2026-07-05T08:14:00.348617+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06534","citing_title":"CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00592","citing_title":"Through the PRISM: Principle-Aware, Interpretable, and Multi-Scale Evaluation of Visual Designs","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19410","citing_title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2509.13484","citing_title":"MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2402.03766","citing_title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2403.18814","citing_title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2601.10611","citing_title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2403.09611","citing_title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2401.15947","citing_title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2312.17090","citing_title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","ref_index":220,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27507","citing_title":"Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2312.14238","citing_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02593","citing_title":"Moondream Segmentation: From Words to Masks","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2404.16821","citing_title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2310.03744","citing_title":"Improved Baselines with Visual Instruction Tuning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08626","citing_title":"WildDet3D: Scaling Promptable 3D Detection in the Wild","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D62G5RZCNJT2O2GLF6JD436MDY","json":"https://pith.science/pith/D62G5RZCNJT2O2GLF6JD436MDY.json","graph_json":"https://pith.science/api/pith-number/D62G5RZCNJT2O2GLF6JD436MDY/graph.json","events_json":"https://pith.science/api/pith-number/D62G5RZCNJT2O2GLF6JD436MDY/events.json","paper":"https://pith.science/paper/D62G5RZC"},"agent_actions":{"view_html":"https://pith.science/pith/D62G5RZCNJT2O2GLF6JD436MDY","download_json":"https://pith.science/pith/D62G5RZCNJT2O2GLF6JD436MDY.json","view_paper":"https://pith.science/paper/D62G5RZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.00692&json=true","fetch_graph":"https://pith.science/api/pith-number/D62G5RZCNJT2O2GLF6JD436MDY/graph.json","fetch_events":"https://pith.science/api/pith-number/D62G5RZCNJT2O2GLF6JD436MDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D62G5RZCNJT2O2GLF6JD436MDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D62G5RZCNJT2O2GLF6JD436MDY/action/storage_attestation","attest_author":"https://pith.science/pith/D62G5RZCNJT2O2GLF6JD436MDY/action/author_attestation","sign_citation":"https://pith.science/pith/D62G5RZCNJT2O2GLF6JD436MDY/action/citation_signature","submit_replication":"https://pith.science/pith/D62G5RZCNJT2O2GLF6JD436MDY/action/replication_record"}},"created_at":"2026-07-05T08:14:00.348617+00:00","updated_at":"2026-07-05T08:14:00.348617+00:00"}