{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JVPCAU3PIHJFXMCGDCC4W6TYPR","short_pith_number":"pith:JVPCAU3P","schema_version":"1.0","canonical_sha256":"4d5e20536f41d25bb0461885cb7a787c6ddba1467253b0b87eae88c65b95cca8","source":{"kind":"arxiv","id":"2508.08066","version":2},"attestation_state":"computed","paper":{"title":"ExpVG: Investigating the Design Space of Visual Grounding in Multimodal Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Lingjuan Lyu, Weiming Zhuang, Weitai Kang, Yan Yan, Zhizhong Li","submitted_at":"2025-08-11T15:10:52Z","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"},"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":"2508.08066","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T15:10:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"e466373403868b1e86748adc84235be7c0d15c35e58a539c256a7e057e86ec24","abstract_canon_sha256":"941efe69524162778d730e8ef5b8e1f9515c8a96d178e227bb19d7f9e2de291a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:22.450949Z","signature_b64":"gX+U68ctg6TcFOpRrH3memoIt6NF4MuislsRSdw29aAwa7CskHlbr4sNoyJGOH6z8lVqikV1fgfkT5pHU1teCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d5e20536f41d25bb0461885cb7a787c6ddba1467253b0b87eae88c65b95cca8","last_reissued_at":"2026-07-05T11:56:22.450521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:22.450521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ExpVG: Investigating the Design Space of Visual Grounding in Multimodal Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Lingjuan Lyu, Weiming Zhuang, Weitai Kang, Yan Yan, Zhizhong Li","submitted_at":"2025-08-11T15:10:52Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08066","kind":"arxiv","version":2},"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/2508.08066/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":"2508.08066","created_at":"2026-07-05T11:56:22.450576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08066v2","created_at":"2026-07-05T11:56:22.450576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08066","created_at":"2026-07-05T11:56:22.450576+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVPCAU3PIHJF","created_at":"2026-07-05T11:56:22.450576+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVPCAU3PIHJFXMCG","created_at":"2026-07-05T11:56:22.450576+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVPCAU3P","created_at":"2026-07-05T11:56:22.450576+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/JVPCAU3PIHJFXMCGDCC4W6TYPR","json":"https://pith.science/pith/JVPCAU3PIHJFXMCGDCC4W6TYPR.json","graph_json":"https://pith.science/api/pith-number/JVPCAU3PIHJFXMCGDCC4W6TYPR/graph.json","events_json":"https://pith.science/api/pith-number/JVPCAU3PIHJFXMCGDCC4W6TYPR/events.json","paper":"https://pith.science/paper/JVPCAU3P"},"agent_actions":{"view_html":"https://pith.science/pith/JVPCAU3PIHJFXMCGDCC4W6TYPR","download_json":"https://pith.science/pith/JVPCAU3PIHJFXMCGDCC4W6TYPR.json","view_paper":"https://pith.science/paper/JVPCAU3P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08066&json=true","fetch_graph":"https://pith.science/api/pith-number/JVPCAU3PIHJFXMCGDCC4W6TYPR/graph.json","fetch_events":"https://pith.science/api/pith-number/JVPCAU3PIHJFXMCGDCC4W6TYPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVPCAU3PIHJFXMCGDCC4W6TYPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVPCAU3PIHJFXMCGDCC4W6TYPR/action/storage_attestation","attest_author":"https://pith.science/pith/JVPCAU3PIHJFXMCGDCC4W6TYPR/action/author_attestation","sign_citation":"https://pith.science/pith/JVPCAU3PIHJFXMCGDCC4W6TYPR/action/citation_signature","submit_replication":"https://pith.science/pith/JVPCAU3PIHJFXMCGDCC4W6TYPR/action/replication_record"}},"created_at":"2026-07-05T11:56:22.450576+00:00","updated_at":"2026-07-05T11:56:22.450576+00:00"}