{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z6ZNOE7SRDMRX5WCXQASFQRYF3","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":"a4ee87a4e8ff8ff69810666f106750581c653aa982babe92b14176cdee6b0684","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T07:46:26Z","title_canon_sha256":"d5e6ba59b5542a7f80933266882416f7b11c0feab9b8a6781ff684666c1dfc4d"},"schema_version":"1.0","source":{"id":"2507.06272","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06272","created_at":"2026-07-05T11:51:31Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06272v3","created_at":"2026-07-05T11:51:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06272","created_at":"2026-07-05T11:51:31Z"},{"alias_kind":"pith_short_12","alias_value":"Z6ZNOE7SRDMR","created_at":"2026-07-05T11:51:31Z"},{"alias_kind":"pith_short_16","alias_value":"Z6ZNOE7SRDMRX5WC","created_at":"2026-07-05T11:51:31Z"},{"alias_kind":"pith_short_8","alias_value":"Z6ZNOE7S","created_at":"2026-07-05T11:51:31Z"}],"graph_snapshots":[{"event_id":"sha256:77944e1273534e6dffc0cd40ad90e1140070bf920b19e5caec579a40cf9eaf3b","target":"graph","created_at":"2026-07-05T11:51:31Z","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/2507.06272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Biao Yang, Liang Yin, Linger Deng, Qiang Liu, Shuo Zhang, Xiang Bai, Yabo Sun, Yuliang Liu, Zhang Li, Zhiyin Ma","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T07:46:26Z","title":"LIRA: Inferring Segmentation in Large Multi-modal Models with Local Interleaved Region Assistance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06272","kind":"arxiv","version":3},"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":"sha256:0e672ea7a8ac9203e5cff29a84924ca713809947b748d9bb3573bd4332746b95","target":"record","created_at":"2026-07-05T11:51:31Z","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":"a4ee87a4e8ff8ff69810666f106750581c653aa982babe92b14176cdee6b0684","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T07:46:26Z","title_canon_sha256":"d5e6ba59b5542a7f80933266882416f7b11c0feab9b8a6781ff684666c1dfc4d"},"schema_version":"1.0","source":{"id":"2507.06272","kind":"arxiv","version":3}},"canonical_sha256":"cfb2d713f288d91bf6c2bc0122c2382ef93f86a18031035918aabcbec7c8c9af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfb2d713f288d91bf6c2bc0122c2382ef93f86a18031035918aabcbec7c8c9af","first_computed_at":"2026-07-05T11:51:31.673244Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:31.673244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hxm8Omc8AtQJ6BEjLOARkNzveFQjFv54rDNt+eZy6Q9mPdvKWJN1URZw0ua6ux0G7wuIwEnj4Vf8BG71FPHfDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:31.673756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06272","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e672ea7a8ac9203e5cff29a84924ca713809947b748d9bb3573bd4332746b95","sha256:77944e1273534e6dffc0cd40ad90e1140070bf920b19e5caec579a40cf9eaf3b"],"state_sha256":"8c9cdcd6e7ce0fa3aa01c00ed16dc3614e4598e54e216f627b1e3bb5e5c51d15"}