{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RYD32IDNVNKOHUXUPCKYUZAFIL","short_pith_number":"pith:RYD32IDN","schema_version":"1.0","canonical_sha256":"8e07bd206dab54e3d2f478958a640542f07a0efb54ec9b0da310c1cd2ea7ca88","source":{"kind":"arxiv","id":"2606.29573","version":1},"attestation_state":"computed","paper":{"title":"Reliability-Prioritized Fine-Grained Generation in Multimodal Large","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Zhao, Lijia Feng, Mehrtash Harandi, Mingyang Gao, Shiyu Luo, Wu Wei, Xiaomeng Fan, Yunde Jia, Yuwei Wu, Yuxuan Ba, Zhenxin Diao, Zhi Gao","submitted_at":"2026-06-28T19:27:59Z","abstract_excerpt":"Multimodal large language models (MLLMs) are increasingly expected to generate fine-grained descriptions of visual content. However, we observe and theoretically show that generating fine-grained responses poses a reliability challenge, \\textit{i.e.}, fine-grained generation is more error-prone than coarse-grained generation. This phenomenon suggests that models should generate the finest description that remains reliable rather than simply produce more specific outputs. To investigate this problem, we develop \\textsc{GranFact}, a granularity-aware benchmark consisting of expert-verified multi"},"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":"2606.29573","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T19:27:59Z","cross_cats_sorted":[],"title_canon_sha256":"185e6fdc95e945f02b89af6068c0e0ee9071393bb164291e2066ebcf35ca9124","abstract_canon_sha256":"3d79fe281b6e3976f3cca930ace415fdc534c469af1f91627f251fabe11568b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:12.631123Z","signature_b64":"BckFj/xS4ihIAJnda/EEsDIQTmcYb3byfuaUBxz93LI3tNy7vGTMcaa1s6LjC9OGw02INTINzBIrh1rsYMjNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e07bd206dab54e3d2f478958a640542f07a0efb54ec9b0da310c1cd2ea7ca88","last_reissued_at":"2026-06-30T01:18:12.630548Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:12.630548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliability-Prioritized Fine-Grained Generation in Multimodal Large","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Zhao, Lijia Feng, Mehrtash Harandi, Mingyang Gao, Shiyu Luo, Wu Wei, Xiaomeng Fan, Yunde Jia, Yuwei Wu, Yuxuan Ba, Zhenxin Diao, Zhi Gao","submitted_at":"2026-06-28T19:27:59Z","abstract_excerpt":"Multimodal large language models (MLLMs) are increasingly expected to generate fine-grained descriptions of visual content. However, we observe and theoretically show that generating fine-grained responses poses a reliability challenge, \\textit{i.e.}, fine-grained generation is more error-prone than coarse-grained generation. This phenomenon suggests that models should generate the finest description that remains reliable rather than simply produce more specific outputs. To investigate this problem, we develop \\textsc{GranFact}, a granularity-aware benchmark consisting of expert-verified multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29573","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/2606.29573/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":"2606.29573","created_at":"2026-06-30T01:18:12.630628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29573v1","created_at":"2026-06-30T01:18:12.630628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29573","created_at":"2026-06-30T01:18:12.630628+00:00"},{"alias_kind":"pith_short_12","alias_value":"RYD32IDNVNKO","created_at":"2026-06-30T01:18:12.630628+00:00"},{"alias_kind":"pith_short_16","alias_value":"RYD32IDNVNKOHUXU","created_at":"2026-06-30T01:18:12.630628+00:00"},{"alias_kind":"pith_short_8","alias_value":"RYD32IDN","created_at":"2026-06-30T01:18:12.630628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RYD32IDNVNKOHUXUPCKYUZAFIL","json":"https://pith.science/pith/RYD32IDNVNKOHUXUPCKYUZAFIL.json","graph_json":"https://pith.science/api/pith-number/RYD32IDNVNKOHUXUPCKYUZAFIL/graph.json","events_json":"https://pith.science/api/pith-number/RYD32IDNVNKOHUXUPCKYUZAFIL/events.json","paper":"https://pith.science/paper/RYD32IDN"},"agent_actions":{"view_html":"https://pith.science/pith/RYD32IDNVNKOHUXUPCKYUZAFIL","download_json":"https://pith.science/pith/RYD32IDNVNKOHUXUPCKYUZAFIL.json","view_paper":"https://pith.science/paper/RYD32IDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29573&json=true","fetch_graph":"https://pith.science/api/pith-number/RYD32IDNVNKOHUXUPCKYUZAFIL/graph.json","fetch_events":"https://pith.science/api/pith-number/RYD32IDNVNKOHUXUPCKYUZAFIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RYD32IDNVNKOHUXUPCKYUZAFIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RYD32IDNVNKOHUXUPCKYUZAFIL/action/storage_attestation","attest_author":"https://pith.science/pith/RYD32IDNVNKOHUXUPCKYUZAFIL/action/author_attestation","sign_citation":"https://pith.science/pith/RYD32IDNVNKOHUXUPCKYUZAFIL/action/citation_signature","submit_replication":"https://pith.science/pith/RYD32IDNVNKOHUXUPCKYUZAFIL/action/replication_record"}},"created_at":"2026-06-30T01:18:12.630628+00:00","updated_at":"2026-06-30T01:18:12.630628+00:00"}