{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5KGG4QPBA3JRU65T7BVLYNVFPO","short_pith_number":"pith:5KGG4QPB","schema_version":"1.0","canonical_sha256":"ea8c6e41e106d31a7bb3f86abc36a57ba69524f88d75e42365feec9374ce7287","source":{"kind":"arxiv","id":"2312.17240","version":3},"attestation_state":"computed","paper":{"title":"LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohao Peng, Jiaya Jia, Senqiao Yang, Shu Liu, Tianyuan Qu, Xin Lai, Zhuotao Tian","submitted_at":"2023-12-28T18:58:33Z","abstract_excerpt":"While LISA effectively bridges the gap between segmentation and large language models to enable reasoning segmentation, it poses certain limitations: unable to distinguish different instances of the target region, and constrained by the pre-defined textual response formats. In this work, we introduce LISA++, an update to the existing LISA model, focusing on improving core functionalities while keeping the base architecture intact. The main enhancements in LISA++ include: \\textbf{1) Enhanced Segmentation}: The instance segmentation ability has been added, providing a more detailed scene analysi"},"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":"2312.17240","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T18:58:33Z","cross_cats_sorted":[],"title_canon_sha256":"c1ab303672fd64cdadf96d71264ec550d2145bb6503b0f341d140267495fdeeb","abstract_canon_sha256":"20d36c72523bf370775b936dbd7b82fdab4e75ddacdf7c86c3502ab53e170be5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:05.269093Z","signature_b64":"aBmlHqnhjHVgcEvVoUQwyiJBW7Be1AXw/YxqyLMOBxH19Iu6rdH89ZvQmSbd40x8SC0DvtHd48Q8wI5KyQLNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea8c6e41e106d31a7bb3f86abc36a57ba69524f88d75e42365feec9374ce7287","last_reissued_at":"2026-07-05T07:36:05.268687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:05.268687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohao Peng, Jiaya Jia, Senqiao Yang, Shu Liu, Tianyuan Qu, Xin Lai, Zhuotao Tian","submitted_at":"2023-12-28T18:58:33Z","abstract_excerpt":"While LISA effectively bridges the gap between segmentation and large language models to enable reasoning segmentation, it poses certain limitations: unable to distinguish different instances of the target region, and constrained by the pre-defined textual response formats. In this work, we introduce LISA++, an update to the existing LISA model, focusing on improving core functionalities while keeping the base architecture intact. The main enhancements in LISA++ include: \\textbf{1) Enhanced Segmentation}: The instance segmentation ability has been added, providing a more detailed scene analysi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17240","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/2312.17240/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":"2312.17240","created_at":"2026-07-05T07:36:05.268743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17240v3","created_at":"2026-07-05T07:36:05.268743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17240","created_at":"2026-07-05T07:36:05.268743+00:00"},{"alias_kind":"pith_short_12","alias_value":"5KGG4QPBA3JR","created_at":"2026-07-05T07:36:05.268743+00:00"},{"alias_kind":"pith_short_16","alias_value":"5KGG4QPBA3JRU65T","created_at":"2026-07-05T07:36:05.268743+00:00"},{"alias_kind":"pith_short_8","alias_value":"5KGG4QPB","created_at":"2026-07-05T07:36:05.268743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06560","citing_title":"Vision as Unified Multimodal Generation","ref_index":204,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19258","citing_title":"CABLE: Cloud-Assisted Bandwidth-efficient LMM-based Encoding for V2X Systems","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09303","citing_title":"Reason Twice: Segmentation via Candidate Discovery and Comparative Reasoning","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06760","citing_title":"MedSIGHT: Towards Grounded Visual Comprehension in Medical Large Vision-Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00987","citing_title":"An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31924","citing_title":"InstanceControl: Controllable Complex Image Generation without Instance Labeling","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23500","citing_title":"B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28724","citing_title":"CCRC: A Change-Aware Captioning and Reasoning Chain for Image Change Captioning and Segmentation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26102","citing_title":"InstructSAM: Segment Any Instance with Any Instructions","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26120","citing_title":"Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2507.12455","citing_title":"Mitigating Object Hallucinations via Sentence-Level Early Intervention","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23500","citing_title":"B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15951","citing_title":"From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19410","citing_title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16903","citing_title":"WOW-Seg: A Word-free Open World Segmentation Model","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10554","citing_title":"Grounding Everything in Tokens for Multimodal Large Language Models","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2601.03054","citing_title":"IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2503.06520","citing_title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2603.16024","citing_title":"Speak, Segment, Track, Navigate: An Interactive System for Video-Guided Skull-Base Surgery","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11411","citing_title":"Online Reasoning Video Object Segmentation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08626","citing_title":"WildDet3D: Scaling Promptable 3D Detection in the Wild","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07916","citing_title":"Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15670","citing_title":"PixDLM: A Dual-Path Multimodal Language Model for UAV Reasoning Segmentation","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5KGG4QPBA3JRU65T7BVLYNVFPO","json":"https://pith.science/pith/5KGG4QPBA3JRU65T7BVLYNVFPO.json","graph_json":"https://pith.science/api/pith-number/5KGG4QPBA3JRU65T7BVLYNVFPO/graph.json","events_json":"https://pith.science/api/pith-number/5KGG4QPBA3JRU65T7BVLYNVFPO/events.json","paper":"https://pith.science/paper/5KGG4QPB"},"agent_actions":{"view_html":"https://pith.science/pith/5KGG4QPBA3JRU65T7BVLYNVFPO","download_json":"https://pith.science/pith/5KGG4QPBA3JRU65T7BVLYNVFPO.json","view_paper":"https://pith.science/paper/5KGG4QPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17240&json=true","fetch_graph":"https://pith.science/api/pith-number/5KGG4QPBA3JRU65T7BVLYNVFPO/graph.json","fetch_events":"https://pith.science/api/pith-number/5KGG4QPBA3JRU65T7BVLYNVFPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5KGG4QPBA3JRU65T7BVLYNVFPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5KGG4QPBA3JRU65T7BVLYNVFPO/action/storage_attestation","attest_author":"https://pith.science/pith/5KGG4QPBA3JRU65T7BVLYNVFPO/action/author_attestation","sign_citation":"https://pith.science/pith/5KGG4QPBA3JRU65T7BVLYNVFPO/action/citation_signature","submit_replication":"https://pith.science/pith/5KGG4QPBA3JRU65T7BVLYNVFPO/action/replication_record"}},"created_at":"2026-07-05T07:36:05.268743+00:00","updated_at":"2026-07-05T07:36:05.268743+00:00"}