{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:37VCRSVNQTVAMSCTVK2MKHV7JA","short_pith_number":"pith:37VCRSVN","schema_version":"1.0","canonical_sha256":"dfea28caad84ea064853aab4c51ebf48287a61731fa4b8fd019e3a4334a49d95","source":{"kind":"arxiv","id":"1803.07728","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Representation Learning by Predicting Image Rotations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Nikos Komodakis, Praveer Singh, Spyros Gidaris","submitted_at":"2018-03-21T03:21:14Z","abstract_excerpt":"Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of computer vision thanks to their unparalleled capacity to learn high level semantic image features. However, in order to successfully learn those features, they usually require massive amounts of manually labeled data, which is both expensive and impractical to scale. Therefore, unsupervised semantic feature learning, i.e., learning without requiring manual annotation effort, is of crucial importance in order to successfully harvest the vast amount of visual data that are available today. In our wor"},"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":"1803.07728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-21T03:21:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ced7583a722b16ad57440dc6b8e8cacaf56960d98dc4dddb016dc131437d5ed8","abstract_canon_sha256":"46e2442a9d4ea4eddb887ebc17d1bc8b2457c7f00725427493b0effc6014e64c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:29.150037Z","signature_b64":"6iuUgs6fiasVc67l53ceW9TGdLvtY1LVsNT2CkiPElf047tu1w8/e8xfeT9N80avGBAzxTC924CDK585BOT2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfea28caad84ea064853aab4c51ebf48287a61731fa4b8fd019e3a4334a49d95","last_reissued_at":"2026-05-18T00:20:29.149471Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:29.149471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Representation Learning by Predicting Image Rotations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Nikos Komodakis, Praveer Singh, Spyros Gidaris","submitted_at":"2018-03-21T03:21:14Z","abstract_excerpt":"Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of computer vision thanks to their unparalleled capacity to learn high level semantic image features. However, in order to successfully learn those features, they usually require massive amounts of manually labeled data, which is both expensive and impractical to scale. Therefore, unsupervised semantic feature learning, i.e., learning without requiring manual annotation effort, is of crucial importance in order to successfully harvest the vast amount of visual data that are available today. In our wor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07728","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1803.07728","created_at":"2026-05-18T00:20:29.149551+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.07728v1","created_at":"2026-05-18T00:20:29.149551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07728","created_at":"2026-05-18T00:20:29.149551+00:00"},{"alias_kind":"pith_short_12","alias_value":"37VCRSVNQTVA","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"37VCRSVNQTVAMSCT","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"37VCRSVN","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":13,"sample":[{"citing_arxiv_id":"1907.11704","citing_title":"Accurate and Robust Pulmonary Nodule Detection by 3D Feature Pyramid Network with Self-supervised Feature Learning","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11879","citing_title":"Multi-task Self-Supervised Learning for Human Activity Detection","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2211.16327","citing_title":"On the Power of Foundation Models","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2505.15263","citing_title":"gen2seg: Generative Models Enable Generalizable Instance Segmentation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17837","citing_title":"Temporal Aware Pruning for Efficient Diffusion-based Video Generation","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01369","citing_title":"MU-SHOT-Fi: Self-Supervised Multi-User Wi-Fi Sensing with Source-free Unsupervised Domain Adaptation","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21058","citing_title":"A Dialogue between Causal and Traditional Representation Learning: Toward Mutual Benefits in a Unified Formulation","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16456","citing_title":"Multi-hop Relational Contrastive Learning: Extending Spatial Contrastive Pre-training Beyond Pairwise Relations","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17837","citing_title":"Temporal Aware Pruning for Efficient Diffusion-based Video Generation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2509.10554","citing_title":"MAE-SAM2: Mask Autoencoder-Enhanced SAM2 for Clinical Retinal Vascular Leakage Segmentation","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2509.24382","citing_title":"REMAP: Regularized Matching and Partial Alignment of Video Embeddings","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2411.15633","citing_title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","ref_index":205,"is_internal_anchor":true},{"citing_arxiv_id":"2110.04627","citing_title":"Vector-quantized Image Modeling with Improved VQGAN","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2002.05709","citing_title":"A Simple Framework for Contrastive Learning of Visual Representations","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11870","citing_title":"Information theoretic underpinning of self-supervised learning by clustering","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08819","citing_title":"From pre-training to downstream performance: Does domain-specific pre-training make sense?","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01369","citing_title":"MU-SHOT-Fi: Self-Supervised Multi-User Wi-Fi Sensing with Source-free Unsupervised Domain Adaptation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05651","citing_title":"Probing Intrinsic Medical Task Relationships: A Contrastive Learning Perspective","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20392","citing_title":"Self-supervised pretraining for an iterative image size agnostic vision transformer","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37VCRSVNQTVAMSCTVK2MKHV7JA","json":"https://pith.science/pith/37VCRSVNQTVAMSCTVK2MKHV7JA.json","graph_json":"https://pith.science/api/pith-number/37VCRSVNQTVAMSCTVK2MKHV7JA/graph.json","events_json":"https://pith.science/api/pith-number/37VCRSVNQTVAMSCTVK2MKHV7JA/events.json","paper":"https://pith.science/paper/37VCRSVN"},"agent_actions":{"view_html":"https://pith.science/pith/37VCRSVNQTVAMSCTVK2MKHV7JA","download_json":"https://pith.science/pith/37VCRSVNQTVAMSCTVK2MKHV7JA.json","view_paper":"https://pith.science/paper/37VCRSVN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.07728&json=true","fetch_graph":"https://pith.science/api/pith-number/37VCRSVNQTVAMSCTVK2MKHV7JA/graph.json","fetch_events":"https://pith.science/api/pith-number/37VCRSVNQTVAMSCTVK2MKHV7JA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37VCRSVNQTVAMSCTVK2MKHV7JA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37VCRSVNQTVAMSCTVK2MKHV7JA/action/storage_attestation","attest_author":"https://pith.science/pith/37VCRSVNQTVAMSCTVK2MKHV7JA/action/author_attestation","sign_citation":"https://pith.science/pith/37VCRSVNQTVAMSCTVK2MKHV7JA/action/citation_signature","submit_replication":"https://pith.science/pith/37VCRSVNQTVAMSCTVK2MKHV7JA/action/replication_record"}},"created_at":"2026-05-18T00:20:29.149551+00:00","updated_at":"2026-05-18T00:20:29.149551+00:00"}