{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EH26436L4TFESI4GRXQSC6KCZA","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":"325b2c2d4eefb618c84eee75af21b8ae5a46654e6256210ca3ad948bccf0f971","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-26T18:59:33Z","title_canon_sha256":"0aa5d2b6ff82272367f0df42466c39c99b7d45313a85560b2b62e718978195fd"},"schema_version":"1.0","source":{"id":"2402.16846","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16846","created_at":"2026-07-05T08:08:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16846v2","created_at":"2026-07-05T08:08:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16846","created_at":"2026-07-05T08:08:41Z"},{"alias_kind":"pith_short_12","alias_value":"EH26436L4TFE","created_at":"2026-07-05T08:08:41Z"},{"alias_kind":"pith_short_16","alias_value":"EH26436L4TFESI4G","created_at":"2026-07-05T08:08:41Z"},{"alias_kind":"pith_short_8","alias_value":"EH26436L","created_at":"2026-07-05T08:08:41Z"}],"graph_snapshots":[{"event_id":"sha256:479a700593a175fd2d48bb658a9ca79b02f676cb6fcd845f13c541c7c0e41b8c","target":"graph","created_at":"2026-07-05T08:08:41Z","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/2402.16846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Joyce Chai, Qiaozi Gao, Suhaila Shakiah, Xiaofeng Gao, Yichi Zhang, Ziqiao Ma","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-26T18:59:33Z","title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16846","kind":"arxiv","version":2},"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":"sha256:75d9d322e8276cdeb28c48dd6fc2e3906918f534738f2777dbacc1a2a9d54040","target":"record","created_at":"2026-07-05T08:08:41Z","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":"325b2c2d4eefb618c84eee75af21b8ae5a46654e6256210ca3ad948bccf0f971","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-26T18:59:33Z","title_canon_sha256":"0aa5d2b6ff82272367f0df42466c39c99b7d45313a85560b2b62e718978195fd"},"schema_version":"1.0","source":{"id":"2402.16846","kind":"arxiv","version":2}},"canonical_sha256":"21f5ee6fcbe4ca4923868de1217942c80917815b9c72bae0b5148fedf824457f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21f5ee6fcbe4ca4923868de1217942c80917815b9c72bae0b5148fedf824457f","first_computed_at":"2026-07-05T08:08:41.024196Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:41.024196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nM5+KzDZ0ez9dcc9Pto+P85LmJiuovvDqj6sGUYeddcD5ttG7CBN+yseuHn0FJsj6TPgGRJslMh34xQMra8kDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:41.024680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16846","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75d9d322e8276cdeb28c48dd6fc2e3906918f534738f2777dbacc1a2a9d54040","sha256:479a700593a175fd2d48bb658a9ca79b02f676cb6fcd845f13c541c7c0e41b8c"],"state_sha256":"683ad0be68936adac304555a67288f4af97e15b8a9ba81173de6b40662e3124a"}