{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F3I4RUFOJNNEYQASVPR4PYHYZL","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":"cb855cfcdec064cdf44b222362f9a6e7f5e666ddbb3be330efb080155a62b97b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-13T17:58:00Z","title_canon_sha256":"216e82199f3390a9aad1eb24730d39ff6d40c5a8c6d1d2cd2e38bc7bea8a688a"},"schema_version":"1.0","source":{"id":"2403.08760","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.08760","created_at":"2026-07-05T07:55:43Z"},{"alias_kind":"arxiv_version","alias_value":"2403.08760v1","created_at":"2026-07-05T07:55:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08760","created_at":"2026-07-05T07:55:43Z"},{"alias_kind":"pith_short_12","alias_value":"F3I4RUFOJNNE","created_at":"2026-07-05T07:55:43Z"},{"alias_kind":"pith_short_16","alias_value":"F3I4RUFOJNNEYQAS","created_at":"2026-07-05T07:55:43Z"},{"alias_kind":"pith_short_8","alias_value":"F3I4RUFO","created_at":"2026-07-05T07:55:43Z"}],"graph_snapshots":[{"event_id":"sha256:a1b0a9d88d4f3848946cae6b8a4812da23de7e7951e81d5b8ea76ee7d2346349","target":"graph","created_at":"2026-07-05T07:55:43Z","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/2403.08760/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning robust and scalable visual representations from massive multi-view video data remains a challenge in computer vision and autonomous driving. Existing pre-training methods either rely on expensive supervised learning with 3D annotations, limiting the scalability, or focus on single-frame or monocular inputs, neglecting the temporal information. We propose MIM4D, a novel pre-training paradigm based on dual masked image modeling (MIM). MIM4D leverages both spatial and temporal relations by training on masked multi-view video inputs. It constructs pseudo-3D features using continuous scene","authors_text":"Bencheng Liao, Jialv Zou, Qian Zhang, Wenyu Liu, Xinggang Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-13T17:58:00Z","title":"MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08760","kind":"arxiv","version":1},"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":"sha256:912ad2c6a38575e86fde06b0a2c943dd3d2c41c9342485d3abc4ce0865765048","target":"record","created_at":"2026-07-05T07:55:43Z","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":"cb855cfcdec064cdf44b222362f9a6e7f5e666ddbb3be330efb080155a62b97b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-13T17:58:00Z","title_canon_sha256":"216e82199f3390a9aad1eb24730d39ff6d40c5a8c6d1d2cd2e38bc7bea8a688a"},"schema_version":"1.0","source":{"id":"2403.08760","kind":"arxiv","version":1}},"canonical_sha256":"2ed1c8d0ae4b5a4c4012abe3c7e0f8caf46797863826912d1d5a9a32f6870d01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ed1c8d0ae4b5a4c4012abe3c7e0f8caf46797863826912d1d5a9a32f6870d01","first_computed_at":"2026-07-05T07:55:43.246786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:43.246786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cixVQsJ7cpE3oBkcEFOqVeKhRW1hKC0oXial/F6OHDn33pNW5aQs+dxNI++7SyskVNsQIt7hNYjYhQvd9iGBCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:43.247197Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.08760","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:912ad2c6a38575e86fde06b0a2c943dd3d2c41c9342485d3abc4ce0865765048","sha256:a1b0a9d88d4f3848946cae6b8a4812da23de7e7951e81d5b8ea76ee7d2346349"],"state_sha256":"cd4f1912c1a12cb3c6bb3573cc1b9fb242895e61f7218a920f9793de4d395a5f"}