{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EH26436L4TFESI4GRXQSC6KCZA","short_pith_number":"pith:EH26436L","schema_version":"1.0","canonical_sha256":"21f5ee6fcbe4ca4923868de1217942c80917815b9c72bae0b5148fedf824457f","source":{"kind":"arxiv","id":"2402.16846","version":2},"attestation_state":"computed","paper":{"title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Joyce Chai, Qiaozi Gao, Suhaila Shakiah, Xiaofeng Gao, Yichi Zhang, Ziqiao Ma","submitted_at":"2024-02-26T18:59:33Z","abstract_excerpt":"Most multimodal large language models (MLLMs) learn language-to-object grounding through causal language modeling where grounded objects are captured by bounding boxes as sequences of location tokens. This paradigm lacks pixel-level representations that are important for fine-grained visual understanding and diagnosis. In this work, we introduce GROUNDHOG, an MLLM developed by grounding Large Language Models to holistic segmentation. GROUNDHOG incorporates a masked feature extractor and converts extracted features into visual entity tokens for the MLLM backbone, which then connects groundable "},"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":"2402.16846","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-26T18:59:33Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0aa5d2b6ff82272367f0df42466c39c99b7d45313a85560b2b62e718978195fd","abstract_canon_sha256":"325b2c2d4eefb618c84eee75af21b8ae5a46654e6256210ca3ad948bccf0f971"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:41.024680Z","signature_b64":"nM5+KzDZ0ez9dcc9Pto+P85LmJiuovvDqj6sGUYeddcD5ttG7CBN+yseuHn0FJsj6TPgGRJslMh34xQMra8kDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21f5ee6fcbe4ca4923868de1217942c80917815b9c72bae0b5148fedf824457f","last_reissued_at":"2026-07-05T08:08:41.024196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:41.024196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Joyce Chai, Qiaozi Gao, Suhaila Shakiah, Xiaofeng Gao, Yichi Zhang, Ziqiao Ma","submitted_at":"2024-02-26T18:59:33Z","abstract_excerpt":"Most multimodal large language models (MLLMs) learn language-to-object grounding through causal language modeling where grounded objects are captured by bounding boxes as sequences of location tokens. This paradigm lacks pixel-level representations that are important for fine-grained visual understanding and diagnosis. In this work, we introduce GROUNDHOG, an MLLM developed by grounding Large Language Models to holistic segmentation. GROUNDHOG incorporates a masked feature extractor and converts extracted features into visual entity tokens for the MLLM backbone, which then connects groundable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16846","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/2402.16846/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":"2402.16846","created_at":"2026-07-05T08:08:41.024263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16846v2","created_at":"2026-07-05T08:08:41.024263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16846","created_at":"2026-07-05T08:08:41.024263+00:00"},{"alias_kind":"pith_short_12","alias_value":"EH26436L4TFE","created_at":"2026-07-05T08:08:41.024263+00:00"},{"alias_kind":"pith_short_16","alias_value":"EH26436L4TFESI4G","created_at":"2026-07-05T08:08:41.024263+00:00"},{"alias_kind":"pith_short_8","alias_value":"EH26436L","created_at":"2026-07-05T08:08:41.024263+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/EH26436L4TFESI4GRXQSC6KCZA","json":"https://pith.science/pith/EH26436L4TFESI4GRXQSC6KCZA.json","graph_json":"https://pith.science/api/pith-number/EH26436L4TFESI4GRXQSC6KCZA/graph.json","events_json":"https://pith.science/api/pith-number/EH26436L4TFESI4GRXQSC6KCZA/events.json","paper":"https://pith.science/paper/EH26436L"},"agent_actions":{"view_html":"https://pith.science/pith/EH26436L4TFESI4GRXQSC6KCZA","download_json":"https://pith.science/pith/EH26436L4TFESI4GRXQSC6KCZA.json","view_paper":"https://pith.science/paper/EH26436L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16846&json=true","fetch_graph":"https://pith.science/api/pith-number/EH26436L4TFESI4GRXQSC6KCZA/graph.json","fetch_events":"https://pith.science/api/pith-number/EH26436L4TFESI4GRXQSC6KCZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EH26436L4TFESI4GRXQSC6KCZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EH26436L4TFESI4GRXQSC6KCZA/action/storage_attestation","attest_author":"https://pith.science/pith/EH26436L4TFESI4GRXQSC6KCZA/action/author_attestation","sign_citation":"https://pith.science/pith/EH26436L4TFESI4GRXQSC6KCZA/action/citation_signature","submit_replication":"https://pith.science/pith/EH26436L4TFESI4GRXQSC6KCZA/action/replication_record"}},"created_at":"2026-07-05T08:08:41.024263+00:00","updated_at":"2026-07-05T08:08:41.024263+00:00"}