{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PXE3NRBCPVCAQAINBNT7ERX2OA","short_pith_number":"pith:PXE3NRBC","schema_version":"1.0","canonical_sha256":"7dc9b6c4227d4408010d0b67f246fa7032482d4144864bade40d680ae98f187a","source":{"kind":"arxiv","id":"1811.09795","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahun Kim, Donghyeon Cho, In So Kweon","submitted_at":"2018-11-24T09:08:08Z","abstract_excerpt":"Self-supervised tasks such as colorization, inpainting and zigsaw puzzle have been utilized for visual representation learning for still images, when the number of labeled images is limited or absent at all. Recently, this worthwhile stream of study extends to video domain where the cost of human labeling is even more expensive. However, the most of existing methods are still based on 2D CNN architectures that can not directly capture spatio-temporal information for video applications. In this paper, we introduce a new self-supervised task called as \\textit{Space-Time Cubic Puzzles} to train 3"},"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":"1811.09795","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-24T09:08:08Z","cross_cats_sorted":[],"title_canon_sha256":"1e0c90f2042806e747d75d7d3de771af72b8a76beea687e3830cc8608ef5ec1a","abstract_canon_sha256":"84d4cd9cb768f66729988fa19ce34c7ad708f0a0495419f9fed808b36a9c61c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:01.202919Z","signature_b64":"7TuXRiJThu2rV+5khggjlWuFtq8CfglT8ueDyHLrPr5ZJHkqQjeakT55bStro81DMtsgCMr9Hg1YBqVJTGHhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dc9b6c4227d4408010d0b67f246fa7032482d4144864bade40d680ae98f187a","last_reissued_at":"2026-05-18T00:00:01.202442Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:01.202442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahun Kim, Donghyeon Cho, In So Kweon","submitted_at":"2018-11-24T09:08:08Z","abstract_excerpt":"Self-supervised tasks such as colorization, inpainting and zigsaw puzzle have been utilized for visual representation learning for still images, when the number of labeled images is limited or absent at all. Recently, this worthwhile stream of study extends to video domain where the cost of human labeling is even more expensive. However, the most of existing methods are still based on 2D CNN architectures that can not directly capture spatio-temporal information for video applications. In this paper, we introduce a new self-supervised task called as \\textit{Space-Time Cubic Puzzles} to train 3"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.09795","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":"1811.09795","created_at":"2026-05-18T00:00:01.202510+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.09795v1","created_at":"2026-05-18T00:00:01.202510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.09795","created_at":"2026-05-18T00:00:01.202510+00:00"},{"alias_kind":"pith_short_12","alias_value":"PXE3NRBCPVCA","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"PXE3NRBCPVCAQAIN","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"PXE3NRBC","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09245","citing_title":"CalibFree: Self-Supervised View Feature Separation for Calibration-Free Multi-Camera Multi-Object Tracking","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PXE3NRBCPVCAQAINBNT7ERX2OA","json":"https://pith.science/pith/PXE3NRBCPVCAQAINBNT7ERX2OA.json","graph_json":"https://pith.science/api/pith-number/PXE3NRBCPVCAQAINBNT7ERX2OA/graph.json","events_json":"https://pith.science/api/pith-number/PXE3NRBCPVCAQAINBNT7ERX2OA/events.json","paper":"https://pith.science/paper/PXE3NRBC"},"agent_actions":{"view_html":"https://pith.science/pith/PXE3NRBCPVCAQAINBNT7ERX2OA","download_json":"https://pith.science/pith/PXE3NRBCPVCAQAINBNT7ERX2OA.json","view_paper":"https://pith.science/paper/PXE3NRBC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.09795&json=true","fetch_graph":"https://pith.science/api/pith-number/PXE3NRBCPVCAQAINBNT7ERX2OA/graph.json","fetch_events":"https://pith.science/api/pith-number/PXE3NRBCPVCAQAINBNT7ERX2OA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PXE3NRBCPVCAQAINBNT7ERX2OA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PXE3NRBCPVCAQAINBNT7ERX2OA/action/storage_attestation","attest_author":"https://pith.science/pith/PXE3NRBCPVCAQAINBNT7ERX2OA/action/author_attestation","sign_citation":"https://pith.science/pith/PXE3NRBCPVCAQAINBNT7ERX2OA/action/citation_signature","submit_replication":"https://pith.science/pith/PXE3NRBCPVCAQAINBNT7ERX2OA/action/replication_record"}},"created_at":"2026-05-18T00:00:01.202510+00:00","updated_at":"2026-05-18T00:00:01.202510+00:00"}