{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z6ZNOE7SRDMRX5WCXQASFQRYF3","short_pith_number":"pith:Z6ZNOE7S","schema_version":"1.0","canonical_sha256":"cfb2d713f288d91bf6c2bc0122c2382ef93f86a18031035918aabcbec7c8c9af","source":{"kind":"arxiv","id":"2507.06272","version":3},"attestation_state":"computed","paper":{"title":"LIRA: Inferring Segmentation in Large Multi-modal Models with Local Interleaved Region Assistance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Biao Yang, Liang Yin, Linger Deng, Qiang Liu, Shuo Zhang, Xiang Bai, Yabo Sun, Yuliang Liu, Zhang Li, Zhiyin Ma","submitted_at":"2025-07-08T07:46:26Z","abstract_excerpt":"While large multi-modal models (LMMs) demonstrate promising capabilities in segmentation and comprehension, they still struggle with two limitations: inaccurate segmentation and hallucinated comprehension. These challenges stem primarily from constraints in weak visual comprehension and a lack of fine-grained perception. To alleviate these limitations, we propose LIRA, a framework that capitalizes on the complementary relationship between visual comprehension and segmentation via two key components: (1) Semantic-Enhanced Feature Extractor (SEFE) improves object attribute inference by fusing se"},"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":"2507.06272","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T07:46:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d5e6ba59b5542a7f80933266882416f7b11c0feab9b8a6781ff684666c1dfc4d","abstract_canon_sha256":"a4ee87a4e8ff8ff69810666f106750581c653aa982babe92b14176cdee6b0684"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:31.673756Z","signature_b64":"hxm8Omc8AtQJ6BEjLOARkNzveFQjFv54rDNt+eZy6Q9mPdvKWJN1URZw0ua6ux0G7wuIwEnj4Vf8BG71FPHfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfb2d713f288d91bf6c2bc0122c2382ef93f86a18031035918aabcbec7c8c9af","last_reissued_at":"2026-07-05T11:51:31.673244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:31.673244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LIRA: Inferring Segmentation in Large Multi-modal Models with Local Interleaved Region Assistance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Biao Yang, Liang Yin, Linger Deng, Qiang Liu, Shuo Zhang, Xiang Bai, Yabo Sun, Yuliang Liu, Zhang Li, Zhiyin Ma","submitted_at":"2025-07-08T07:46:26Z","abstract_excerpt":"While large multi-modal models (LMMs) demonstrate promising capabilities in segmentation and comprehension, they still struggle with two limitations: inaccurate segmentation and hallucinated comprehension. These challenges stem primarily from constraints in weak visual comprehension and a lack of fine-grained perception. To alleviate these limitations, we propose LIRA, a framework that capitalizes on the complementary relationship between visual comprehension and segmentation via two key components: (1) Semantic-Enhanced Feature Extractor (SEFE) improves object attribute inference by fusing se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06272","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/2507.06272/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":"2507.06272","created_at":"2026-07-05T11:51:31.673301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06272v3","created_at":"2026-07-05T11:51:31.673301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06272","created_at":"2026-07-05T11:51:31.673301+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6ZNOE7SRDMR","created_at":"2026-07-05T11:51:31.673301+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6ZNOE7SRDMRX5WC","created_at":"2026-07-05T11:51:31.673301+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6ZNOE7S","created_at":"2026-07-05T11:51:31.673301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"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":144,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6ZNOE7SRDMRX5WCXQASFQRYF3","json":"https://pith.science/pith/Z6ZNOE7SRDMRX5WCXQASFQRYF3.json","graph_json":"https://pith.science/api/pith-number/Z6ZNOE7SRDMRX5WCXQASFQRYF3/graph.json","events_json":"https://pith.science/api/pith-number/Z6ZNOE7SRDMRX5WCXQASFQRYF3/events.json","paper":"https://pith.science/paper/Z6ZNOE7S"},"agent_actions":{"view_html":"https://pith.science/pith/Z6ZNOE7SRDMRX5WCXQASFQRYF3","download_json":"https://pith.science/pith/Z6ZNOE7SRDMRX5WCXQASFQRYF3.json","view_paper":"https://pith.science/paper/Z6ZNOE7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06272&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6ZNOE7SRDMRX5WCXQASFQRYF3/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6ZNOE7SRDMRX5WCXQASFQRYF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6ZNOE7SRDMRX5WCXQASFQRYF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6ZNOE7SRDMRX5WCXQASFQRYF3/action/storage_attestation","attest_author":"https://pith.science/pith/Z6ZNOE7SRDMRX5WCXQASFQRYF3/action/author_attestation","sign_citation":"https://pith.science/pith/Z6ZNOE7SRDMRX5WCXQASFQRYF3/action/citation_signature","submit_replication":"https://pith.science/pith/Z6ZNOE7SRDMRX5WCXQASFQRYF3/action/replication_record"}},"created_at":"2026-07-05T11:51:31.673301+00:00","updated_at":"2026-07-05T11:51:31.673301+00:00"}