{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PZWUNNEBUPB5CVL7DN3M56TZNY","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":"7fcb0932f59d572c82ed86ea51403956b7c5b048ffbeb8ac3a6d59693bac06e1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-06T18:59:57Z","title_canon_sha256":"f4973fe02805686cb45d4d70c82489c52290025117e1a489fab30e630eec68e3"},"schema_version":"1.0","source":{"id":"2311.03356","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.03356","created_at":"2026-07-05T08:26:15Z"},{"alias_kind":"arxiv_version","alias_value":"2311.03356v3","created_at":"2026-07-05T08:26:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03356","created_at":"2026-07-05T08:26:15Z"},{"alias_kind":"pith_short_12","alias_value":"PZWUNNEBUPB5","created_at":"2026-07-05T08:26:15Z"},{"alias_kind":"pith_short_16","alias_value":"PZWUNNEBUPB5CVL7","created_at":"2026-07-05T08:26:15Z"},{"alias_kind":"pith_short_8","alias_value":"PZWUNNEB","created_at":"2026-07-05T08:26:15Z"}],"graph_snapshots":[{"event_id":"sha256:dd87237fb83b58b30d9dd26af61fe1682b6cae94339005799873295920573b9c","target":"graph","created_at":"2026-07-05T08:26:15Z","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/2311.03356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Multimodal Models (LMMs) extend Large Language Models to the vision domain. Initial LMMs used holistic images and text prompts to generate ungrounded textual responses. Recently, region-level LMMs have been used to generate visually grounded responses. However, they are limited to only referring to a single object category at a time, require users to specify the regions, or cannot offer dense pixel-wise object grounding. In this work, we present Grounding LMM (GLaMM), the first model that can generate natural language responses seamlessly intertwined with corresponding object segmentatio","authors_text":"Abdelrahman Shaker, Erix Xing, Fahad S. Khan, Hanoona Rasheed, Hisham Cholakkal, Ming-Hsuan Yang, Muhammad Maaz, Rao M. Anwer, Sahal Shaji Mullappilly, Salman Khan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-06T18:59:57Z","title":"GLaMM: Pixel Grounding Large Multimodal Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03356","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:d3bf1a38b23ec1a26898f90d993697e2a2a7e3a096a052257cc36c7f71510d0d","target":"record","created_at":"2026-07-05T08:26:15Z","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":"7fcb0932f59d572c82ed86ea51403956b7c5b048ffbeb8ac3a6d59693bac06e1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-06T18:59:57Z","title_canon_sha256":"f4973fe02805686cb45d4d70c82489c52290025117e1a489fab30e630eec68e3"},"schema_version":"1.0","source":{"id":"2311.03356","kind":"arxiv","version":3}},"canonical_sha256":"7e6d46b481a3c3d1557f1b76cefa796e14cacb70de599e322436ee778bf0d6da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e6d46b481a3c3d1557f1b76cefa796e14cacb70de599e322436ee778bf0d6da","first_computed_at":"2026-07-05T08:26:15.167442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:15.167442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P5qX5OaLxGSW7b50t901KXXMYsL/xN0RPDy8dkAe/VR3Cf9spDO750fGkZdEqR8DCAWf4ZwXino1/Vb8dBiwAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:15.167926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.03356","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3bf1a38b23ec1a26898f90d993697e2a2a7e3a096a052257cc36c7f71510d0d","sha256:dd87237fb83b58b30d9dd26af61fe1682b6cae94339005799873295920573b9c"],"state_sha256":"75f0130608fa522184f219e012bd4c7e083cceb4a1fde9c7a7c0296b502e2a94"}