{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:R7M3AYWUODLLKRRGRCU3DS74I2","short_pith_number":"pith:R7M3AYWU","canonical_record":{"source":{"id":"2212.08320","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-16T07:46:53Z","cross_cats_sorted":[],"title_canon_sha256":"7b0d913bf7e80d721d8636981b160b727d7baeb211a7515f5d7220ff02eee8d4","abstract_canon_sha256":"176d331472d6e0fc680c3b5c3154e5b04b3b490597c28cf6a2068fb94c6bc1e1"},"schema_version":"1.0"},"canonical_sha256":"8fd9b062d470d6b5462688a9b1cbfc46abad8afd0e490438c5a6d949bde59f9d","source":{"kind":"arxiv","id":"2212.08320","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:R7M3AYWUODLLKRRGRCU3DS74I2","target":"record","payload":{"canonical_record":{"source":{"id":"2212.08320","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-16T07:46:53Z","cross_cats_sorted":[],"title_canon_sha256":"7b0d913bf7e80d721d8636981b160b727d7baeb211a7515f5d7220ff02eee8d4","abstract_canon_sha256":"176d331472d6e0fc680c3b5c3154e5b04b3b490597c28cf6a2068fb94c6bc1e1"},"schema_version":"1.0"},"canonical_sha256":"8fd9b062d470d6b5462688a9b1cbfc46abad8afd0e490438c5a6d949bde59f9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:10.492919Z","signature_b64":"3SGzKtsQzrX3xV1pyIrbwke/MY8+AlAFOmzxDud+/EgfbFziEN8DgEjxh3QzmrVvJXM8dDfrfWzTLrwV6tW3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fd9b062d470d6b5462688a9b1cbfc46abad8afd0e490438c5a6d949bde59f9d","last_reissued_at":"2026-07-05T05:38:10.492468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:10.492468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.08320","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:38:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MrCmSI/STlXUBHZxceqFVERtgWSrI6X5eDzUvN1Ghy0HSFBGFuHW1x/qfPWWjTyzEd5711mwnxQd05m/2FiBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T09:28:14.912668Z"},"content_sha256":"10b4cc111fd0891e9ceb093b294235f2cea6e4fb2613f20caa6f1cbc46698255","schema_version":"1.0","event_id":"sha256:10b4cc111fd0891e9ceb093b294235f2cea6e4fb2613f20caa6f1cbc46698255"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:R7M3AYWUODLLKRRGRCU3DS74I2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianjian Sun, Junbo Zhang, Kaisheng Ma, Linfeng Zhang, Li Yi, Runpei Dong, Zekun Qi, Zheng Ge","submitted_at":"2022-12-16T07:46:53Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08320","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/2212.08320/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:38:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FS6Ek0WdsHD4kMh4FL/u+5syTO+RadZyiNPTVtpwl+ixzE2pHrwGSazuOFBuMhZcGQPm3aNx7Nvp+kau4Yk/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T09:28:14.913040Z"},"content_sha256":"797b0dd715ad1d99c7a29469835f13b48cd754118379f204e19fa8f7e08fcdc5","schema_version":"1.0","event_id":"sha256:797b0dd715ad1d99c7a29469835f13b48cd754118379f204e19fa8f7e08fcdc5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R7M3AYWUODLLKRRGRCU3DS74I2/bundle.json","state_url":"https://pith.science/pith/R7M3AYWUODLLKRRGRCU3DS74I2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R7M3AYWUODLLKRRGRCU3DS74I2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-22T09:28:14Z","links":{"resolver":"https://pith.science/pith/R7M3AYWUODLLKRRGRCU3DS74I2","bundle":"https://pith.science/pith/R7M3AYWUODLLKRRGRCU3DS74I2/bundle.json","state":"https://pith.science/pith/R7M3AYWUODLLKRRGRCU3DS74I2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R7M3AYWUODLLKRRGRCU3DS74I2/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XVmY22C6xAnIPnIZY67eDR9Ani+m7dTewQTaubLeUjvdigQKDBL0J3DSf4zIBsrLJp/aXCaVorGfpJAy8d6UAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T09:28:14.915559Z","bundle_sha256":"b9ea6fd6c2a52b341c44463891072b7d704b7a1bdcb2b60a8653f6b2f2a1630b"}}