{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JVPCAU3PIHJFXMCGDCC4W6TYPR","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":"941efe69524162778d730e8ef5b8e1f9515c8a96d178e227bb19d7f9e2de291a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T15:10:52Z","title_canon_sha256":"e466373403868b1e86748adc84235be7c0d15c35e58a539c256a7e057e86ec24"},"schema_version":"1.0","source":{"id":"2508.08066","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.08066","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"arxiv_version","alias_value":"2508.08066v2","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08066","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"pith_short_12","alias_value":"JVPCAU3PIHJF","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"pith_short_16","alias_value":"JVPCAU3PIHJFXMCG","created_at":"2026-07-05T11:56:22Z"},{"alias_kind":"pith_short_8","alias_value":"JVPCAU3P","created_at":"2026-07-05T11:56:22Z"}],"graph_snapshots":[{"event_id":"sha256:15eb9ad208a665f905b6941117bcf823268e15879211b437a6d4f4d90aa3728f","target":"graph","created_at":"2026-07-05T11:56:22Z","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/2508.08066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-grained multimodal capability in Multimodal Large Language Models (MLLMs) has emerged as a critical research direction, particularly for tackling the visual grounding (VG) problem. Despite the strong performance achieved by existing approaches, they often employ disparate design choices when fine-tuning MLLMs for VG, lacking systematic verification to support these designs. To bridge this gap, this paper presents a comprehensive study of various design choices that impact the VG performance of MLLMs. We conduct our analysis using LLaVA-1.5, which has been widely adopted in prior empirical","authors_text":"Lingjuan Lyu, Weiming Zhuang, Weitai Kang, Yan Yan, Zhizhong Li","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T15:10:52Z","title":"ExpVG: Investigating the Design Space of Visual Grounding in Multimodal Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08066","kind":"arxiv","version":2},"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":"sha256:50e2d7eff2ae76164346025ed0dac61d25efefaa186825cc4e45ebc083590502","target":"record","created_at":"2026-07-05T11:56:22Z","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":"941efe69524162778d730e8ef5b8e1f9515c8a96d178e227bb19d7f9e2de291a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T15:10:52Z","title_canon_sha256":"e466373403868b1e86748adc84235be7c0d15c35e58a539c256a7e057e86ec24"},"schema_version":"1.0","source":{"id":"2508.08066","kind":"arxiv","version":2}},"canonical_sha256":"4d5e20536f41d25bb0461885cb7a787c6ddba1467253b0b87eae88c65b95cca8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d5e20536f41d25bb0461885cb7a787c6ddba1467253b0b87eae88c65b95cca8","first_computed_at":"2026-07-05T11:56:22.450521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:22.450521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gX+U68ctg6TcFOpRrH3memoIt6NF4MuislsRSdw29aAwa7CskHlbr4sNoyJGOH6z8lVqikV1fgfkT5pHU1teCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:22.450949Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.08066","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50e2d7eff2ae76164346025ed0dac61d25efefaa186825cc4e45ebc083590502","sha256:15eb9ad208a665f905b6941117bcf823268e15879211b437a6d4f4d90aa3728f"],"state_sha256":"af1a44dd48ad274a3dc339707bfb584a48fd61cd6d672dd4cfd0fc75bad62781"}