{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HGSHQELZQAQU7XZSWM4RU2BBWM","short_pith_number":"pith:HGSHQELZ","schema_version":"1.0","canonical_sha256":"39a478117980214fdf32b3391a6821b30326accf25ac3f89d43f79093dc22bb7","source":{"kind":"arxiv","id":"2306.06010","version":2},"attestation_state":"computed","paper":{"title":"A Large-Scale Analysis on Self-Supervised Video Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akash Kumar, Ashlesha Kumar, Vibhav Vineet, Yogesh Singh Rawat","submitted_at":"2023-06-09T16:27:14Z","abstract_excerpt":"Self-supervised learning is an effective way for label-free model pre-training, especially in the video domain where labeling is expensive. Existing self-supervised works in the video domain use varying experimental setups to demonstrate their effectiveness and comparison across approaches becomes challenging with no standard benchmark. In this work, we first provide a benchmark that enables a comparison of existing approaches on the same ground. Next, we study five different aspects of self-supervised learning important for videos; 1) dataset size, 2) complexity, 3) data distribution, 4) data"},"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":"2306.06010","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-09T16:27:14Z","cross_cats_sorted":[],"title_canon_sha256":"7c62a8edd172e658675517e693f3b473925ef6bfc1b1815be0857a7cfd11de14","abstract_canon_sha256":"e450c97053291a059d5797270d670486c49043422880da0903abd6f8f6dddda2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:54.437151Z","signature_b64":"9it5tT76/clRyhRrtmmaSPz+/x5ez3cCvqCUlN2pjWHG7nV7xB98mRW6IYlxfPsfRNlwKEDsb0dnYeMDqV/eBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39a478117980214fdf32b3391a6821b30326accf25ac3f89d43f79093dc22bb7","last_reissued_at":"2026-07-05T07:14:54.436588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:54.436588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Large-Scale Analysis on Self-Supervised Video Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akash Kumar, Ashlesha Kumar, Vibhav Vineet, Yogesh Singh Rawat","submitted_at":"2023-06-09T16:27:14Z","abstract_excerpt":"Self-supervised learning is an effective way for label-free model pre-training, especially in the video domain where labeling is expensive. Existing self-supervised works in the video domain use varying experimental setups to demonstrate their effectiveness and comparison across approaches becomes challenging with no standard benchmark. In this work, we first provide a benchmark that enables a comparison of existing approaches on the same ground. Next, we study five different aspects of self-supervised learning important for videos; 1) dataset size, 2) complexity, 3) data distribution, 4) data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06010","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/2306.06010/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.06010","created_at":"2026-07-05T07:14:54.436646+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06010v2","created_at":"2026-07-05T07:14:54.436646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06010","created_at":"2026-07-05T07:14:54.436646+00:00"},{"alias_kind":"pith_short_12","alias_value":"HGSHQELZQAQU","created_at":"2026-07-05T07:14:54.436646+00:00"},{"alias_kind":"pith_short_16","alias_value":"HGSHQELZQAQU7XZS","created_at":"2026-07-05T07:14:54.436646+00:00"},{"alias_kind":"pith_short_8","alias_value":"HGSHQELZ","created_at":"2026-07-05T07:14:54.436646+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.07072","citing_title":"Stable Mean Teacher for Semi-supervised Video Action Detection","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HGSHQELZQAQU7XZSWM4RU2BBWM","json":"https://pith.science/pith/HGSHQELZQAQU7XZSWM4RU2BBWM.json","graph_json":"https://pith.science/api/pith-number/HGSHQELZQAQU7XZSWM4RU2BBWM/graph.json","events_json":"https://pith.science/api/pith-number/HGSHQELZQAQU7XZSWM4RU2BBWM/events.json","paper":"https://pith.science/paper/HGSHQELZ"},"agent_actions":{"view_html":"https://pith.science/pith/HGSHQELZQAQU7XZSWM4RU2BBWM","download_json":"https://pith.science/pith/HGSHQELZQAQU7XZSWM4RU2BBWM.json","view_paper":"https://pith.science/paper/HGSHQELZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06010&json=true","fetch_graph":"https://pith.science/api/pith-number/HGSHQELZQAQU7XZSWM4RU2BBWM/graph.json","fetch_events":"https://pith.science/api/pith-number/HGSHQELZQAQU7XZSWM4RU2BBWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HGSHQELZQAQU7XZSWM4RU2BBWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HGSHQELZQAQU7XZSWM4RU2BBWM/action/storage_attestation","attest_author":"https://pith.science/pith/HGSHQELZQAQU7XZSWM4RU2BBWM/action/author_attestation","sign_citation":"https://pith.science/pith/HGSHQELZQAQU7XZSWM4RU2BBWM/action/citation_signature","submit_replication":"https://pith.science/pith/HGSHQELZQAQU7XZSWM4RU2BBWM/action/replication_record"}},"created_at":"2026-07-05T07:14:54.436646+00:00","updated_at":"2026-07-05T07:14:54.436646+00:00"}