{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7NBLU45VLCDVFQ36N4YX5IB77Y","short_pith_number":"pith:7NBLU45V","schema_version":"1.0","canonical_sha256":"fb42ba73b5588752c37e6f317ea03ffe07809fe74a502e452abca99ae3cba325","source":{"kind":"arxiv","id":"2412.01430","version":1},"attestation_state":"computed","paper":{"title":"MVImgNet2.0: A Larger-scale Dataset of Multi-view Images","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Haolin Liu, Hongjie Liao, Lingteng Qiu, Luyue Shi, Shuguang Cui, Weihao Yuan, Xiaodong Gu, Xiaoguang Han, Yushuang Wu, Zilong Dong","submitted_at":"2024-12-02T12:10:04Z","abstract_excerpt":"MVImgNet is a large-scale dataset that contains multi-view images of ~220k real-world objects in 238 classes. As a counterpart of ImageNet, it introduces 3D visual signals via multi-view shooting, making a soft bridge between 2D and 3D vision. This paper constructs the MVImgNet2.0 dataset that expands MVImgNet into a total of ~520k objects and 515 categories, which derives a 3D dataset with a larger scale that is more comparable to ones in the 2D domain. In addition to the expanded dataset scale and category range, MVImgNet2.0 is of a higher quality than MVImgNet owing to four new features: (i"},"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":"2412.01430","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T12:10:04Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"c26399fe0dcdadf3fedcdb2622bbae876fbfbea566cac3212132a1b8f61f4dcd","abstract_canon_sha256":"ebadc588453f024a2ff7ebd3479bf89dbbcf3ed05678c59a7e4b8e456499bd4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:12.951290Z","signature_b64":"NxEGA7WIosEjO8UtNNHFR9l0ZAhkgUiWg+Prw2lCXBDXXqZBxY6tFuJaSgJRKYNoEgvocwC0gDXDknjvEBM5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb42ba73b5588752c37e6f317ea03ffe07809fe74a502e452abca99ae3cba325","last_reissued_at":"2026-07-05T09:43:12.950793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:12.950793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVImgNet2.0: A Larger-scale Dataset of Multi-view Images","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Haolin Liu, Hongjie Liao, Lingteng Qiu, Luyue Shi, Shuguang Cui, Weihao Yuan, Xiaodong Gu, Xiaoguang Han, Yushuang Wu, Zilong Dong","submitted_at":"2024-12-02T12:10:04Z","abstract_excerpt":"MVImgNet is a large-scale dataset that contains multi-view images of ~220k real-world objects in 238 classes. As a counterpart of ImageNet, it introduces 3D visual signals via multi-view shooting, making a soft bridge between 2D and 3D vision. This paper constructs the MVImgNet2.0 dataset that expands MVImgNet into a total of ~520k objects and 515 categories, which derives a 3D dataset with a larger scale that is more comparable to ones in the 2D domain. In addition to the expanded dataset scale and category range, MVImgNet2.0 is of a higher quality than MVImgNet owing to four new features: (i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01430","kind":"arxiv","version":1},"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/2412.01430/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":"2412.01430","created_at":"2026-07-05T09:43:12.950854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01430v1","created_at":"2026-07-05T09:43:12.950854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01430","created_at":"2026-07-05T09:43:12.950854+00:00"},{"alias_kind":"pith_short_12","alias_value":"7NBLU45VLCDV","created_at":"2026-07-05T09:43:12.950854+00:00"},{"alias_kind":"pith_short_16","alias_value":"7NBLU45VLCDVFQ36","created_at":"2026-07-05T09:43:12.950854+00:00"},{"alias_kind":"pith_short_8","alias_value":"7NBLU45V","created_at":"2026-07-05T09:43:12.950854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11188","citing_title":"ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31585","citing_title":"DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14683","citing_title":"Emerging Properties in Unified Multimodal Pretraining","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7NBLU45VLCDVFQ36N4YX5IB77Y","json":"https://pith.science/pith/7NBLU45VLCDVFQ36N4YX5IB77Y.json","graph_json":"https://pith.science/api/pith-number/7NBLU45VLCDVFQ36N4YX5IB77Y/graph.json","events_json":"https://pith.science/api/pith-number/7NBLU45VLCDVFQ36N4YX5IB77Y/events.json","paper":"https://pith.science/paper/7NBLU45V"},"agent_actions":{"view_html":"https://pith.science/pith/7NBLU45VLCDVFQ36N4YX5IB77Y","download_json":"https://pith.science/pith/7NBLU45VLCDVFQ36N4YX5IB77Y.json","view_paper":"https://pith.science/paper/7NBLU45V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01430&json=true","fetch_graph":"https://pith.science/api/pith-number/7NBLU45VLCDVFQ36N4YX5IB77Y/graph.json","fetch_events":"https://pith.science/api/pith-number/7NBLU45VLCDVFQ36N4YX5IB77Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7NBLU45VLCDVFQ36N4YX5IB77Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7NBLU45VLCDVFQ36N4YX5IB77Y/action/storage_attestation","attest_author":"https://pith.science/pith/7NBLU45VLCDVFQ36N4YX5IB77Y/action/author_attestation","sign_citation":"https://pith.science/pith/7NBLU45VLCDVFQ36N4YX5IB77Y/action/citation_signature","submit_replication":"https://pith.science/pith/7NBLU45VLCDVFQ36N4YX5IB77Y/action/replication_record"}},"created_at":"2026-07-05T09:43:12.950854+00:00","updated_at":"2026-07-05T09:43:12.950854+00:00"}