{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q2O3S37G2FIV4Q7VZK5MBN3A2J","short_pith_number":"pith:Q2O3S37G","schema_version":"1.0","canonical_sha256":"869db96fe6d1515e43f5cabac0b760d270dfe6b82083baa4d450d3dfe35383ef","source":{"kind":"arxiv","id":"2401.03201","version":2},"attestation_state":"computed","paper":{"title":"3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Ruifei Ma, Ruilong Ren, Xiangde Liu, Xiaoyan Wang, Yifan Xu, Zeju Li","submitted_at":"2024-01-06T12:20:18Z","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"},"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":"2401.03201","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-06T12:20:18Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"d352b11750a78e1db8b1d362002f8af61994b6d99fe371ae2fdbe3844ca698c8","abstract_canon_sha256":"9bd8b9d64800d0e18e2357d65d136e974261a5b02cc2867e741225eaaa1c225b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:00.027748Z","signature_b64":"R6SwNgK5x0+EGPyZIRd/5y1yJWe3MVzwJrHiJfzB3jkUx4sEpb23XF8JNKbXNEh7llvgfoggDafP3NAtgjMQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"869db96fe6d1515e43f5cabac0b760d270dfe6b82083baa4d450d3dfe35383ef","last_reissued_at":"2026-07-05T07:34:00.027290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:00.027290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Ruifei Ma, Ruilong Ren, Xiangde Liu, Xiaoyan Wang, Yifan Xu, Zeju Li","submitted_at":"2024-01-06T12:20:18Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03201","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/2401.03201/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":"2401.03201","created_at":"2026-07-05T07:34:00.027360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03201v2","created_at":"2026-07-05T07:34:00.027360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03201","created_at":"2026-07-05T07:34:00.027360+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2O3S37G2FIV","created_at":"2026-07-05T07:34:00.027360+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2O3S37G2FIV4Q7V","created_at":"2026-07-05T07:34:00.027360+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2O3S37G","created_at":"2026-07-05T07:34:00.027360+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/Q2O3S37G2FIV4Q7VZK5MBN3A2J","json":"https://pith.science/pith/Q2O3S37G2FIV4Q7VZK5MBN3A2J.json","graph_json":"https://pith.science/api/pith-number/Q2O3S37G2FIV4Q7VZK5MBN3A2J/graph.json","events_json":"https://pith.science/api/pith-number/Q2O3S37G2FIV4Q7VZK5MBN3A2J/events.json","paper":"https://pith.science/paper/Q2O3S37G"},"agent_actions":{"view_html":"https://pith.science/pith/Q2O3S37G2FIV4Q7VZK5MBN3A2J","download_json":"https://pith.science/pith/Q2O3S37G2FIV4Q7VZK5MBN3A2J.json","view_paper":"https://pith.science/paper/Q2O3S37G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03201&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2O3S37G2FIV4Q7VZK5MBN3A2J/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2O3S37G2FIV4Q7VZK5MBN3A2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2O3S37G2FIV4Q7VZK5MBN3A2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2O3S37G2FIV4Q7VZK5MBN3A2J/action/storage_attestation","attest_author":"https://pith.science/pith/Q2O3S37G2FIV4Q7VZK5MBN3A2J/action/author_attestation","sign_citation":"https://pith.science/pith/Q2O3S37G2FIV4Q7VZK5MBN3A2J/action/citation_signature","submit_replication":"https://pith.science/pith/Q2O3S37G2FIV4Q7VZK5MBN3A2J/action/replication_record"}},"created_at":"2026-07-05T07:34:00.027360+00:00","updated_at":"2026-07-05T07:34:00.027360+00:00"}