{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X3WBVDHPCTM5JGX4O3PJ6HODDO","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":"237b30d39cc28259f4cbd0bcc7fe8ad5edb498ebc1f632c0c671936e615e9bd0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T01:18:48Z","title_canon_sha256":"4a0efff5197fd08e05de67322c5678b547b675d6a10f07782ebcb5179589759a"},"schema_version":"1.0","source":{"id":"2403.11401","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11401","created_at":"2026-07-05T07:59:36Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11401v2","created_at":"2026-07-05T07:59:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11401","created_at":"2026-07-05T07:59:36Z"},{"alias_kind":"pith_short_12","alias_value":"X3WBVDHPCTM5","created_at":"2026-07-05T07:59:36Z"},{"alias_kind":"pith_short_16","alias_value":"X3WBVDHPCTM5JGX4","created_at":"2026-07-05T07:59:36Z"},{"alias_kind":"pith_short_8","alias_value":"X3WBVDHP","created_at":"2026-07-05T07:59:36Z"}],"graph_snapshots":[{"event_id":"sha256:a53b59eaf717342ab395947526171fc3872439d29933aefc0f139e78cdfb67ff","target":"graph","created_at":"2026-07-05T07:59:36Z","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/2403.11401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces Scene-LLM, a 3D-visual-language model that enhances embodied agents' abilities in interactive 3D indoor environments by integrating the reasoning strengths of Large Language Models (LLMs). Scene-LLM adopts a hybrid 3D visual feature representation, that incorporates dense spatial information and supports scene state updates. The model employs a projection layer to efficiently project these features in the pre-trained textual embedding space, enabling effective interpretation of 3D visual information. Unique to our approach is the integration of both scene-level and ego-ce","authors_text":"Jingyu Liu, Rao Fu, Wenhan Xiong, Xilun Chen, Yixin Nie","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T01:18:48Z","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11401","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":"sha256:6db0fe874b0ef115a567a71a3b6a3995bb4120ddc2d9827cd62a9f628db8fafe","target":"record","created_at":"2026-07-05T07:59:36Z","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":"237b30d39cc28259f4cbd0bcc7fe8ad5edb498ebc1f632c0c671936e615e9bd0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T01:18:48Z","title_canon_sha256":"4a0efff5197fd08e05de67322c5678b547b675d6a10f07782ebcb5179589759a"},"schema_version":"1.0","source":{"id":"2403.11401","kind":"arxiv","version":2}},"canonical_sha256":"beec1a8cef14d9d49afc76de9f1dc31b82951a783fc1c137e28de8ca8a349510","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"beec1a8cef14d9d49afc76de9f1dc31b82951a783fc1c137e28de8ca8a349510","first_computed_at":"2026-07-05T07:59:36.315952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:36.315952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DVhDFrIC83W3kLci/A0BsOyTD0T4DvpKo15gYaopJIg06Q5EltDnJhTO5jais/e6yKX+xuWennjvexRWTlx0Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:36.316575Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11401","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6db0fe874b0ef115a567a71a3b6a3995bb4120ddc2d9827cd62a9f628db8fafe","sha256:a53b59eaf717342ab395947526171fc3872439d29933aefc0f139e78cdfb67ff"],"state_sha256":"f1e11bf1883d56ade05c0b6ebf37b09e3e2e2d49fa10170010d009077986cf2e"}