{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:R7M3AYWUODLLKRRGRCU3DS74I2","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":"176d331472d6e0fc680c3b5c3154e5b04b3b490597c28cf6a2068fb94c6bc1e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-16T07:46:53Z","title_canon_sha256":"7b0d913bf7e80d721d8636981b160b727d7baeb211a7515f5d7220ff02eee8d4"},"schema_version":"1.0","source":{"id":"2212.08320","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08320","created_at":"2026-07-05T05:38:10Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08320v2","created_at":"2026-07-05T05:38:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08320","created_at":"2026-07-05T05:38:10Z"},{"alias_kind":"pith_short_12","alias_value":"R7M3AYWUODLL","created_at":"2026-07-05T05:38:10Z"},{"alias_kind":"pith_short_16","alias_value":"R7M3AYWUODLLKRRG","created_at":"2026-07-05T05:38:10Z"},{"alias_kind":"pith_short_8","alias_value":"R7M3AYWU","created_at":"2026-07-05T05:38:10Z"}],"graph_snapshots":[{"event_id":"sha256:797b0dd715ad1d99c7a29469835f13b48cd754118379f204e19fa8f7e08fcdc5","target":"graph","created_at":"2026-07-05T05:38:10Z","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/2212.08320/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of deep learning heavily relies on large-scale data with comprehensive labels, which is more expensive and time-consuming to fetch in 3D compared to 2D images or natural languages. This promotes the potential of utilizing models pretrained with data more than 3D as teachers for cross-modal knowledge transferring. In this paper, we revisit masked modeling in a unified fashion of knowledge distillation, and we show that foundational Transformers pretrained with 2D images or natural languages can help self-supervised 3D representation learning through training Autoencoders as Cross-Mo","authors_text":"Jianjian Sun, Junbo Zhang, Kaisheng Ma, Linfeng Zhang, Li Yi, Runpei Dong, Zekun Qi, Zheng Ge","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-16T07:46:53Z","title":"Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08320","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":"sha256:10b4cc111fd0891e9ceb093b294235f2cea6e4fb2613f20caa6f1cbc46698255","target":"record","created_at":"2026-07-05T05:38:10Z","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":"176d331472d6e0fc680c3b5c3154e5b04b3b490597c28cf6a2068fb94c6bc1e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-16T07:46:53Z","title_canon_sha256":"7b0d913bf7e80d721d8636981b160b727d7baeb211a7515f5d7220ff02eee8d4"},"schema_version":"1.0","source":{"id":"2212.08320","kind":"arxiv","version":2}},"canonical_sha256":"8fd9b062d470d6b5462688a9b1cbfc46abad8afd0e490438c5a6d949bde59f9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fd9b062d470d6b5462688a9b1cbfc46abad8afd0e490438c5a6d949bde59f9d","first_computed_at":"2026-07-05T05:38:10.492468Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:10.492468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3SGzKtsQzrX3xV1pyIrbwke/MY8+AlAFOmzxDud+/EgfbFziEN8DgEjxh3QzmrVvJXM8dDfrfWzTLrwV6tW3Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:10.492919Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.08320","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10b4cc111fd0891e9ceb093b294235f2cea6e4fb2613f20caa6f1cbc46698255","sha256:797b0dd715ad1d99c7a29469835f13b48cd754118379f204e19fa8f7e08fcdc5"],"state_sha256":"589f8a07d75d9ad04870ef08427b407e8846e106c5af139ebeccc602815eb0d9"}