{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BSEDKFO4REU5MIFC3FXZEP2GJK","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":"621db11bc7042bc15b0cffdd9d00c03e45631dd9e26568cac2529deeddf946e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-09T15:14:26Z","title_canon_sha256":"1a9fbd6051f35a964c21150d15c20e1b6cd4a05c939174e93c2590564db513d2"},"schema_version":"1.0","source":{"id":"2406.05821","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05821","created_at":"2026-07-05T10:47:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05821v3","created_at":"2026-07-05T10:47:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05821","created_at":"2026-07-05T10:47:29Z"},{"alias_kind":"pith_short_12","alias_value":"BSEDKFO4REU5","created_at":"2026-07-05T10:47:29Z"},{"alias_kind":"pith_short_16","alias_value":"BSEDKFO4REU5MIFC","created_at":"2026-07-05T10:47:29Z"},{"alias_kind":"pith_short_8","alias_value":"BSEDKFO4","created_at":"2026-07-05T10:47:29Z"}],"graph_snapshots":[{"event_id":"sha256:4cb0f5e5a4f6c97f2b8b9959c2730ad568606c48fd132f0d33ff916ee883cdc2","target":"graph","created_at":"2026-07-05T10:47:29Z","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/2406.05821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Endowing Large Multimodal Models (LMMs) with visual grounding capability can significantly enhance AIs' understanding of the visual world and their interaction with humans. However, existing methods typically fine-tune the parameters of LMMs to learn additional segmentation tokens and overfit grounding and segmentation datasets. Such a design would inevitably cause a catastrophic diminution in the indispensable conversational capability of general AI assistants. In this paper, we comprehensively evaluate state-of-the-art grounding LMMs across a suite of multimodal question-answering benchmarks","authors_text":"Chen Change Loy, Lumin Xu, Sheng Jin, Size Wu, Wei Li, Wentao Liu, Wenwei Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-09T15:14:26Z","title":"F-LMM: Grounding Frozen Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05821","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":"sha256:9f724b40531e13a835662df2b42602a6b690ab88468f4a1a1bda0707d1ebaf54","target":"record","created_at":"2026-07-05T10:47:29Z","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":"621db11bc7042bc15b0cffdd9d00c03e45631dd9e26568cac2529deeddf946e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-09T15:14:26Z","title_canon_sha256":"1a9fbd6051f35a964c21150d15c20e1b6cd4a05c939174e93c2590564db513d2"},"schema_version":"1.0","source":{"id":"2406.05821","kind":"arxiv","version":3}},"canonical_sha256":"0c883515dc8929d620a2d96f923f464a808cfa519a63059c11b8ab19b465b2ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c883515dc8929d620a2d96f923f464a808cfa519a63059c11b8ab19b465b2ea","first_computed_at":"2026-07-05T10:47:29.286362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:29.286362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kQ60nnTaqRnorOrqfwDklpM4w0rlztMcbAMMdzNtpycz96WmI7TOGx5y0tXC0PBlZUyAmbdMn+jzpmqEbj+5BA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:29.286866Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.05821","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f724b40531e13a835662df2b42602a6b690ab88468f4a1a1bda0707d1ebaf54","sha256:4cb0f5e5a4f6c97f2b8b9959c2730ad568606c48fd132f0d33ff916ee883cdc2"],"state_sha256":"034b18b3c637ab023e1062ea1bd9d13e65247f01beb733329650600b9955785c"}