{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q2O3S37G2FIV4Q7VZK5MBN3A2J","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":"9bd8b9d64800d0e18e2357d65d136e974261a5b02cc2867e741225eaaa1c225b","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-06T12:20:18Z","title_canon_sha256":"d352b11750a78e1db8b1d362002f8af61994b6d99fe371ae2fdbe3844ca698c8"},"schema_version":"1.0","source":{"id":"2401.03201","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.03201","created_at":"2026-07-05T07:34:00Z"},{"alias_kind":"arxiv_version","alias_value":"2401.03201v2","created_at":"2026-07-05T07:34:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03201","created_at":"2026-07-05T07:34:00Z"},{"alias_kind":"pith_short_12","alias_value":"Q2O3S37G2FIV","created_at":"2026-07-05T07:34:00Z"},{"alias_kind":"pith_short_16","alias_value":"Q2O3S37G2FIV4Q7V","created_at":"2026-07-05T07:34:00Z"},{"alias_kind":"pith_short_8","alias_value":"Q2O3S37G","created_at":"2026-07-05T07:34:00Z"}],"graph_snapshots":[{"event_id":"sha256:ea85fe7d53b2296be65ceaca9cf61eef4e3d8a8ede0f851c97e8460044dc8421","target":"graph","created_at":"2026-07-05T07:34:00Z","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/2401.03201/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The remarkable potential of multi-modal large language models (MLLMs) in comprehending both vision and language information has been widely acknowledged. However, the scarcity of 3D scenes-language pairs in comparison to their 2D counterparts, coupled with the inadequacy of existing approaches in understanding of 3D scenes by LLMs, poses a significant challenge. In response, we collect and construct an extensive dataset comprising 75K instruction-response pairs tailored for 3D scenes. This dataset addresses tasks related to 3D VQA, 3D grounding, and 3D conversation. To further enhance the inte","authors_text":"Chao Zhang, Ruifei Ma, Ruilong Ren, Xiangde Liu, Xiaoyan Wang, Yifan Xu, Zeju Li","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-06T12:20:18Z","title":"3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03201","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:a739c141a83176f3694107e4ef3bfc64d92bbb764cf994ac87829b0f965dfdec","target":"record","created_at":"2026-07-05T07:34:00Z","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":"9bd8b9d64800d0e18e2357d65d136e974261a5b02cc2867e741225eaaa1c225b","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-06T12:20:18Z","title_canon_sha256":"d352b11750a78e1db8b1d362002f8af61994b6d99fe371ae2fdbe3844ca698c8"},"schema_version":"1.0","source":{"id":"2401.03201","kind":"arxiv","version":2}},"canonical_sha256":"869db96fe6d1515e43f5cabac0b760d270dfe6b82083baa4d450d3dfe35383ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"869db96fe6d1515e43f5cabac0b760d270dfe6b82083baa4d450d3dfe35383ef","first_computed_at":"2026-07-05T07:34:00.027290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:34:00.027290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R6SwNgK5x0+EGPyZIRd/5y1yJWe3MVzwJrHiJfzB3jkUx4sEpb23XF8JNKbXNEh7llvgfoggDafP3NAtgjMQDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:34:00.027748Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.03201","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a739c141a83176f3694107e4ef3bfc64d92bbb764cf994ac87829b0f965dfdec","sha256:ea85fe7d53b2296be65ceaca9cf61eef4e3d8a8ede0f851c97e8460044dc8421"],"state_sha256":"d933e04bf9fdc0615dbb6cf9bed27f84954246ea90b116bd09187e74a6cd79a0"}