{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XUBHD3LAEQO7FQZIKHX2W432MZ","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":"8cd024eff753c34774928526aae105f214f5b821cfb02f53b3485f4145a64578","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-13T07:09:45Z","title_canon_sha256":"324594b786128c4188d7accb76c145e83e10822b0d3f6c473fe6e52a5df0f582"},"schema_version":"1.0","source":{"id":"2302.06148","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.06148","created_at":"2026-07-05T05:41:02Z"},{"alias_kind":"arxiv_version","alias_value":"2302.06148v1","created_at":"2026-07-05T05:41:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06148","created_at":"2026-07-05T05:41:02Z"},{"alias_kind":"pith_short_12","alias_value":"XUBHD3LAEQO7","created_at":"2026-07-05T05:41:02Z"},{"alias_kind":"pith_short_16","alias_value":"XUBHD3LAEQO7FQZI","created_at":"2026-07-05T05:41:02Z"},{"alias_kind":"pith_short_8","alias_value":"XUBHD3LA","created_at":"2026-07-05T05:41:02Z"}],"graph_snapshots":[{"event_id":"sha256:44a7c7225a1b3a8791699902538c8c4f947e6b65572b63321c022cefe65313d7","target":"graph","created_at":"2026-07-05T05:41:02Z","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/2302.06148/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current RGB-D scene recognition approaches often train two standalone backbones for RGB and depth modalities with the same Places or ImageNet pre-training. However, the pre-trained depth network is still biased by RGB-based models which may result in a suboptimal solution. In this paper, we present a single-model self-supervised hybrid pre-training framework for RGB and depth modalities, termed as CoMAE. Our CoMAE presents a curriculum learning strategy to unify the two popular self-supervised representation learning algorithms: contrastive learning and masked image modeling. Specifically, we ","authors_text":"Gangshan Wu, Jiange Yang, Limin Wang, Sheng Guo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-13T07:09:45Z","title":"CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06148","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:d6eabafacb15d37c077f3715fa80e6da8df58d0e9993aed4ac0b59af1f5dcbfe","target":"record","created_at":"2026-07-05T05:41:02Z","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":"8cd024eff753c34774928526aae105f214f5b821cfb02f53b3485f4145a64578","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-13T07:09:45Z","title_canon_sha256":"324594b786128c4188d7accb76c145e83e10822b0d3f6c473fe6e52a5df0f582"},"schema_version":"1.0","source":{"id":"2302.06148","kind":"arxiv","version":1}},"canonical_sha256":"bd0271ed60241df2c32851efab737a6661b3c83610d88ee95afef1f447eb8ed8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd0271ed60241df2c32851efab737a6661b3c83610d88ee95afef1f447eb8ed8","first_computed_at":"2026-07-05T05:41:02.487092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:41:02.487092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Brqg/xSFhv+jKl2sop3SD9SunRvLKJ9B1kzAP4KKxKEVqwGliWTh4V4H6wOe0Z2Q6iMfHb4moeSFfRtMrKJxBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:41:02.487493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.06148","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6eabafacb15d37c077f3715fa80e6da8df58d0e9993aed4ac0b59af1f5dcbfe","sha256:44a7c7225a1b3a8791699902538c8c4f947e6b65572b63321c022cefe65313d7"],"state_sha256":"c326a57f4dadf4e4534ea826e64c54e7661c506cc518e7b1f8099fd99d7320e5"}