{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YN4MNYTZSXMCAE634NCXM2FPVA","short_pith_number":"pith:YN4MNYTZ","schema_version":"1.0","canonical_sha256":"c378c6e27995d82013dbe3457668afa81eb9c7649fff4c8afd4dd0b5be7f744e","source":{"kind":"arxiv","id":"2308.10421","version":3},"attestation_state":"computed","paper":{"title":"UniM$^2$AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Mei Feng, Guanglei Yang, Jian Zou, Tao Luo, Tianyu Huang, Wangmeng Zuo, Zhenhua Guo","submitted_at":"2023-08-21T02:13:40Z","abstract_excerpt":"Masked Autoencoders (MAE) play a pivotal role in learning potent representations, delivering outstanding results across various 3D perception tasks essential for autonomous driving. In real-world driving scenarios, it's commonplace to deploy multiple sensors for comprehensive environment perception. Despite integrating multi-modal features from these sensors can produce rich and powerful features, there is a noticeable challenge in MAE methods addressing this integration due to the substantial disparity between the different modalities. This research delves into multi-modal Masked Autoencoders"},"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":"2308.10421","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T02:13:40Z","cross_cats_sorted":[],"title_canon_sha256":"b1c28085e5be1c02ee0a300e6b156edf9563aea2de055c583d85a67e93b78b55","abstract_canon_sha256":"55707dce4be2fb5b4305ae456fc7bd3d26277e0e156e17d751be95d562c46d5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:20.050926Z","signature_b64":"DhsuXdCLUU8oW4m0/dI/StgyEbyds73b2wKlIiiV7Z6S4EC2MvDgbg7oDpE+qqe1wSIYFuamtZrMOs41GuSAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c378c6e27995d82013dbe3457668afa81eb9c7649fff4c8afd4dd0b5be7f744e","last_reissued_at":"2026-07-05T08:58:20.050456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:20.050456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniM$^2$AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Mei Feng, Guanglei Yang, Jian Zou, Tao Luo, Tianyu Huang, Wangmeng Zuo, Zhenhua Guo","submitted_at":"2023-08-21T02:13:40Z","abstract_excerpt":"Masked Autoencoders (MAE) play a pivotal role in learning potent representations, delivering outstanding results across various 3D perception tasks essential for autonomous driving. In real-world driving scenarios, it's commonplace to deploy multiple sensors for comprehensive environment perception. Despite integrating multi-modal features from these sensors can produce rich and powerful features, there is a noticeable challenge in MAE methods addressing this integration due to the substantial disparity between the different modalities. This research delves into multi-modal Masked Autoencoders"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10421","kind":"arxiv","version":3},"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/2308.10421/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":"2308.10421","created_at":"2026-07-05T08:58:20.050513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10421v3","created_at":"2026-07-05T08:58:20.050513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10421","created_at":"2026-07-05T08:58:20.050513+00:00"},{"alias_kind":"pith_short_12","alias_value":"YN4MNYTZSXMC","created_at":"2026-07-05T08:58:20.050513+00:00"},{"alias_kind":"pith_short_16","alias_value":"YN4MNYTZSXMCAE63","created_at":"2026-07-05T08:58:20.050513+00:00"},{"alias_kind":"pith_short_8","alias_value":"YN4MNYTZ","created_at":"2026-07-05T08:58:20.050513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01595","citing_title":"Epipolar Attention Field Transformers for Bird's Eye View Semantic Segmentation","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YN4MNYTZSXMCAE634NCXM2FPVA","json":"https://pith.science/pith/YN4MNYTZSXMCAE634NCXM2FPVA.json","graph_json":"https://pith.science/api/pith-number/YN4MNYTZSXMCAE634NCXM2FPVA/graph.json","events_json":"https://pith.science/api/pith-number/YN4MNYTZSXMCAE634NCXM2FPVA/events.json","paper":"https://pith.science/paper/YN4MNYTZ"},"agent_actions":{"view_html":"https://pith.science/pith/YN4MNYTZSXMCAE634NCXM2FPVA","download_json":"https://pith.science/pith/YN4MNYTZSXMCAE634NCXM2FPVA.json","view_paper":"https://pith.science/paper/YN4MNYTZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10421&json=true","fetch_graph":"https://pith.science/api/pith-number/YN4MNYTZSXMCAE634NCXM2FPVA/graph.json","fetch_events":"https://pith.science/api/pith-number/YN4MNYTZSXMCAE634NCXM2FPVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YN4MNYTZSXMCAE634NCXM2FPVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YN4MNYTZSXMCAE634NCXM2FPVA/action/storage_attestation","attest_author":"https://pith.science/pith/YN4MNYTZSXMCAE634NCXM2FPVA/action/author_attestation","sign_citation":"https://pith.science/pith/YN4MNYTZSXMCAE634NCXM2FPVA/action/citation_signature","submit_replication":"https://pith.science/pith/YN4MNYTZSXMCAE634NCXM2FPVA/action/replication_record"}},"created_at":"2026-07-05T08:58:20.050513+00:00","updated_at":"2026-07-05T08:58:20.050513+00:00"}