{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AT5KATNRRIDUPFV4LGY4DKPQZM","short_pith_number":"pith:AT5KATNR","schema_version":"1.0","canonical_sha256":"04faa04db18a074796bc59b1c1a9f0cb05afa7d66f668c697a8a1609fd1f85e7","source":{"kind":"arxiv","id":"2503.13881","version":1},"attestation_state":"computed","paper":{"title":"MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dae-shik Kim, Donggon Jang, Suin Lee, Taehyeon Kim, Yucheol Cho","submitted_at":"2025-03-18T04:23:09Z","abstract_excerpt":"The fusion of Large Language Models with vision models is pioneering new possibilities in user-interactive vision-language tasks. A notable application is reasoning segmentation, where models generate pixel-level segmentation masks by comprehending implicit meanings in human instructions. However, seamless human-AI interaction demands more than just object-level recognition; it requires understanding both objects and the functions of their detailed parts, particularly in multi-target scenarios. For example, when instructing a robot to \\textit{turn on the TV\"}, there could be various ways to ac"},"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":"2503.13881","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T04:23:09Z","cross_cats_sorted":[],"title_canon_sha256":"e4583d6730ef998ceaa7363c8dcfb898b4825b7bb6cf87c3a1b96ebad9b92855","abstract_canon_sha256":"b6b8ca9d4be89f93240131714d482e4b607233b87db26246bf0fc878257e509f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:20.557384Z","signature_b64":"4C8hckrb6PWRJL4pc759NLcnBD7qdMdnNkH2tu7uRwFZWM/CGdaQCO8+dEC5voBVQUbpOtA9hCt4wAwwRQHfAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04faa04db18a074796bc59b1c1a9f0cb05afa7d66f668c697a8a1609fd1f85e7","last_reissued_at":"2026-07-05T10:33:20.556912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:20.556912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dae-shik Kim, Donggon Jang, Suin Lee, Taehyeon Kim, Yucheol Cho","submitted_at":"2025-03-18T04:23:09Z","abstract_excerpt":"The fusion of Large Language Models with vision models is pioneering new possibilities in user-interactive vision-language tasks. A notable application is reasoning segmentation, where models generate pixel-level segmentation masks by comprehending implicit meanings in human instructions. However, seamless human-AI interaction demands more than just object-level recognition; it requires understanding both objects and the functions of their detailed parts, particularly in multi-target scenarios. For example, when instructing a robot to \\textit{turn on the TV\"}, there could be various ways to ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13881","kind":"arxiv","version":1},"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/2503.13881/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":"2503.13881","created_at":"2026-07-05T10:33:20.556973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.13881v1","created_at":"2026-07-05T10:33:20.556973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13881","created_at":"2026-07-05T10:33:20.556973+00:00"},{"alias_kind":"pith_short_12","alias_value":"AT5KATNRRIDU","created_at":"2026-07-05T10:33:20.556973+00:00"},{"alias_kind":"pith_short_16","alias_value":"AT5KATNRRIDUPFV4","created_at":"2026-07-05T10:33:20.556973+00:00"},{"alias_kind":"pith_short_8","alias_value":"AT5KATNR","created_at":"2026-07-05T10:33:20.556973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"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":95,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19410","citing_title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07141","citing_title":"Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AT5KATNRRIDUPFV4LGY4DKPQZM","json":"https://pith.science/pith/AT5KATNRRIDUPFV4LGY4DKPQZM.json","graph_json":"https://pith.science/api/pith-number/AT5KATNRRIDUPFV4LGY4DKPQZM/graph.json","events_json":"https://pith.science/api/pith-number/AT5KATNRRIDUPFV4LGY4DKPQZM/events.json","paper":"https://pith.science/paper/AT5KATNR"},"agent_actions":{"view_html":"https://pith.science/pith/AT5KATNRRIDUPFV4LGY4DKPQZM","download_json":"https://pith.science/pith/AT5KATNRRIDUPFV4LGY4DKPQZM.json","view_paper":"https://pith.science/paper/AT5KATNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.13881&json=true","fetch_graph":"https://pith.science/api/pith-number/AT5KATNRRIDUPFV4LGY4DKPQZM/graph.json","fetch_events":"https://pith.science/api/pith-number/AT5KATNRRIDUPFV4LGY4DKPQZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AT5KATNRRIDUPFV4LGY4DKPQZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AT5KATNRRIDUPFV4LGY4DKPQZM/action/storage_attestation","attest_author":"https://pith.science/pith/AT5KATNRRIDUPFV4LGY4DKPQZM/action/author_attestation","sign_citation":"https://pith.science/pith/AT5KATNRRIDUPFV4LGY4DKPQZM/action/citation_signature","submit_replication":"https://pith.science/pith/AT5KATNRRIDUPFV4LGY4DKPQZM/action/replication_record"}},"created_at":"2026-07-05T10:33:20.556973+00:00","updated_at":"2026-07-05T10:33:20.556973+00:00"}