{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PZWUNNEBUPB5CVL7DN3M56TZNY","short_pith_number":"pith:PZWUNNEB","schema_version":"1.0","canonical_sha256":"7e6d46b481a3c3d1557f1b76cefa796e14cacb70de599e322436ee778bf0d6da","source":{"kind":"arxiv","id":"2311.03356","version":3},"attestation_state":"computed","paper":{"title":"GLaMM: Pixel Grounding Large Multimodal Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","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","submitted_at":"2023-11-06T18:59:57Z","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"},"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":"2311.03356","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-06T18:59:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f4973fe02805686cb45d4d70c82489c52290025117e1a489fab30e630eec68e3","abstract_canon_sha256":"7fcb0932f59d572c82ed86ea51403956b7c5b048ffbeb8ac3a6d59693bac06e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:15.167926Z","signature_b64":"P5qX5OaLxGSW7b50t901KXXMYsL/xN0RPDy8dkAe/VR3Cf9spDO750fGkZdEqR8DCAWf4ZwXino1/Vb8dBiwAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e6d46b481a3c3d1557f1b76cefa796e14cacb70de599e322436ee778bf0d6da","last_reissued_at":"2026-07-05T08:26:15.167442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:15.167442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLaMM: Pixel Grounding Large Multimodal Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","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","submitted_at":"2023-11-06T18:59:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03356","kind":"arxiv","version":3},"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/2311.03356/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":"2311.03356","created_at":"2026-07-05T08:26:15.167500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.03356v3","created_at":"2026-07-05T08:26:15.167500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03356","created_at":"2026-07-05T08:26:15.167500+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZWUNNEBUPB5","created_at":"2026-07-05T08:26:15.167500+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZWUNNEBUPB5CVL7","created_at":"2026-07-05T08:26:15.167500+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZWUNNEB","created_at":"2026-07-05T08:26:15.167500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00592","citing_title":"Through the PRISM: Principle-Aware, Interpretable, and Multi-Scale Evaluation of Visual Designs","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2509.13484","citing_title":"MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":142,"is_internal_anchor":false},{"citing_arxiv_id":"2401.15947","citing_title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00270","citing_title":"OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18562","citing_title":"AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation","ref_index":195,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PZWUNNEBUPB5CVL7DN3M56TZNY","json":"https://pith.science/pith/PZWUNNEBUPB5CVL7DN3M56TZNY.json","graph_json":"https://pith.science/api/pith-number/PZWUNNEBUPB5CVL7DN3M56TZNY/graph.json","events_json":"https://pith.science/api/pith-number/PZWUNNEBUPB5CVL7DN3M56TZNY/events.json","paper":"https://pith.science/paper/PZWUNNEB"},"agent_actions":{"view_html":"https://pith.science/pith/PZWUNNEBUPB5CVL7DN3M56TZNY","download_json":"https://pith.science/pith/PZWUNNEBUPB5CVL7DN3M56TZNY.json","view_paper":"https://pith.science/paper/PZWUNNEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.03356&json=true","fetch_graph":"https://pith.science/api/pith-number/PZWUNNEBUPB5CVL7DN3M56TZNY/graph.json","fetch_events":"https://pith.science/api/pith-number/PZWUNNEBUPB5CVL7DN3M56TZNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZWUNNEBUPB5CVL7DN3M56TZNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZWUNNEBUPB5CVL7DN3M56TZNY/action/storage_attestation","attest_author":"https://pith.science/pith/PZWUNNEBUPB5CVL7DN3M56TZNY/action/author_attestation","sign_citation":"https://pith.science/pith/PZWUNNEBUPB5CVL7DN3M56TZNY/action/citation_signature","submit_replication":"https://pith.science/pith/PZWUNNEBUPB5CVL7DN3M56TZNY/action/replication_record"}},"created_at":"2026-07-05T08:26:15.167500+00:00","updated_at":"2026-07-05T08:26:15.167500+00:00"}