{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RYD32IDNVNKOHUXUPCKYUZAFIL","short_pith_number":"pith:RYD32IDN","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"},"canonical_sha256":"8e07bd206dab54e3d2f478958a640542f07a0efb54ec9b0da310c1cd2ea7ca88","source":{"kind":"arxiv","id":"2606.29573","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29573","created_at":"2026-06-30T01:18:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29573v1","created_at":"2026-06-30T01:18:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29573","created_at":"2026-06-30T01:18:12Z"},{"alias_kind":"pith_short_12","alias_value":"RYD32IDNVNKO","created_at":"2026-06-30T01:18:12Z"},{"alias_kind":"pith_short_16","alias_value":"RYD32IDNVNKOHUXU","created_at":"2026-06-30T01:18:12Z"},{"alias_kind":"pith_short_8","alias_value":"RYD32IDN","created_at":"2026-06-30T01:18:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RYD32IDNVNKOHUXUPCKYUZAFIL","target":"record","payload":{"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"},"canonical_sha256":"8e07bd206dab54e3d2f478958a640542f07a0efb54ec9b0da310c1cd2ea7ca88","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"},"source_kind":"arxiv","source_id":"2606.29573","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:18:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BVWMdYqduqzO6x0Grco9uxMXVfYANUbaztHXwVVPiIhIRjLHVmGmvR4h/1o/iZ17SuHhVErkk3I+pGhUdJVgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T17:27:13.371266Z"},"content_sha256":"b3e3616b49bef0f746430ab602d9e05de7139b88f7723e8070d5e5872e6efd62","schema_version":"1.0","event_id":"sha256:b3e3616b49bef0f746430ab602d9e05de7139b88f7723e8070d5e5872e6efd62"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RYD32IDNVNKOHUXUPCKYUZAFIL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:18:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RxExtZ6foDvfVrENrVCT1OkgKEtShBMeRdMQlqGB72i+KGrvoM5vL+QtM2SlFvSMyULPHJ2aKMsk//avSY7VDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T17:27:13.371657Z"},"content_sha256":"173a8cab67148da5cad60f64592f4e5e90cd17d358d16a1cc34be11c1d6e1549","schema_version":"1.0","event_id":"sha256:173a8cab67148da5cad60f64592f4e5e90cd17d358d16a1cc34be11c1d6e1549"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RYD32IDNVNKOHUXUPCKYUZAFIL/bundle.json","state_url":"https://pith.science/pith/RYD32IDNVNKOHUXUPCKYUZAFIL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RYD32IDNVNKOHUXUPCKYUZAFIL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-30T17:27:13Z","links":{"resolver":"https://pith.science/pith/RYD32IDNVNKOHUXUPCKYUZAFIL","bundle":"https://pith.science/pith/RYD32IDNVNKOHUXUPCKYUZAFIL/bundle.json","state":"https://pith.science/pith/RYD32IDNVNKOHUXUPCKYUZAFIL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RYD32IDNVNKOHUXUPCKYUZAFIL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RYD32IDNVNKOHUXUPCKYUZAFIL","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":"3d79fe281b6e3976f3cca930ace415fdc534c469af1f91627f251fabe11568b2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T19:27:59Z","title_canon_sha256":"185e6fdc95e945f02b89af6068c0e0ee9071393bb164291e2066ebcf35ca9124"},"schema_version":"1.0","source":{"id":"2606.29573","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29573","created_at":"2026-06-30T01:18:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29573v1","created_at":"2026-06-30T01:18:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29573","created_at":"2026-06-30T01:18:12Z"},{"alias_kind":"pith_short_12","alias_value":"RYD32IDNVNKO","created_at":"2026-06-30T01:18:12Z"},{"alias_kind":"pith_short_16","alias_value":"RYD32IDNVNKOHUXU","created_at":"2026-06-30T01:18:12Z"},{"alias_kind":"pith_short_8","alias_value":"RYD32IDN","created_at":"2026-06-30T01:18:12Z"}],"graph_snapshots":[{"event_id":"sha256:173a8cab67148da5cad60f64592f4e5e90cd17d358d16a1cc34be11c1d6e1549","target":"graph","created_at":"2026-06-30T01:18:12Z","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/2606.29573/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T19:27:59Z","title":"Reliability-Prioritized Fine-Grained Generation in Multimodal Large"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29573","kind":"arxiv","version":1},"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:b3e3616b49bef0f746430ab602d9e05de7139b88f7723e8070d5e5872e6efd62","target":"record","created_at":"2026-06-30T01:18:12Z","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":"3d79fe281b6e3976f3cca930ace415fdc534c469af1f91627f251fabe11568b2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T19:27:59Z","title_canon_sha256":"185e6fdc95e945f02b89af6068c0e0ee9071393bb164291e2066ebcf35ca9124"},"schema_version":"1.0","source":{"id":"2606.29573","kind":"arxiv","version":1}},"canonical_sha256":"8e07bd206dab54e3d2f478958a640542f07a0efb54ec9b0da310c1cd2ea7ca88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e07bd206dab54e3d2f478958a640542f07a0efb54ec9b0da310c1cd2ea7ca88","first_computed_at":"2026-06-30T01:18:12.630548Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:12.630548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BckFj/xS4ihIAJnda/EEsDIQTmcYb3byfuaUBxz93LI3tNy7vGTMcaa1s6LjC9OGw02INTINzBIrh1rsYMjNAw==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:12.631123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29573","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3e3616b49bef0f746430ab602d9e05de7139b88f7723e8070d5e5872e6efd62","sha256:173a8cab67148da5cad60f64592f4e5e90cd17d358d16a1cc34be11c1d6e1549"],"state_sha256":"afbbd3c08e7ae3a2e39ed894658d7c9609bd84574ece3ecbdb1a3452ab5b71ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IKE6PdBEGX/hkOmh7QbWHJSqdNz/D+oNADG/IRW3lmiZxzm5sjW7+clok67J+Org1BlNQNsk9eyAPJBMwYACAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T17:27:13.373657Z","bundle_sha256":"b24e0c58a0a094a6e283e23eed2d0524b897e21a0c9cf8061cdc46b92de722d2"}}