{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2CNCMRMEPMWO2THLSNCYD4Q3K7","short_pith_number":"pith:2CNCMRME","schema_version":"1.0","canonical_sha256":"d09a2645847b2ced4ceb934581f21b57e51d8c653709e0ae39f1075df07f7d78","source":{"kind":"arxiv","id":"2607.13192","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdullah-Al-Zubaer Imran, Matthew A. Massey, Nishat Nayla, Nusrat Munia, Tyler Ward","submitted_at":"2026-07-14T18:45:04Z","abstract_excerpt":"Self-supervision is a powerful technique for learning visual representations from unlabeled data. Existing techniques primarily adopt a two-stage approach for self-supervised learning (SSL): a pretraining stage on unlabeled data followed by a finetuning stage on labeled data. While this pipeline has demonstrated extreme effectiveness, the interaction between self-supervised and supervised learning objectives remains insufficiently understood. In this work, we systematically investigate whether jointly optimizing the self-supervised and supervised objectives during training provides a better al"},"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":"2607.13192","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-14T18:45:04Z","cross_cats_sorted":[],"title_canon_sha256":"d6d5573347e5f75c67a2be80f3d4b670e6edb39033b96a1ae48c6c46d041a955","abstract_canon_sha256":"dd033caf03eef8fae76394e53b7c4be24c596290fc3f42ec5b9d3dbcb81cebed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T00:22:02.199506Z","signature_b64":"EyYEfmy5i66BkkGigpHS1UjqVPEyCTuL2h2RlMRcCzxEgkOmLJPrIDSNakOptHgFdk5lgSAYO1CNFLhYE25NAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d09a2645847b2ced4ceb934581f21b57e51d8c653709e0ae39f1075df07f7d78","last_reissued_at":"2026-07-16T00:22:02.198643Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T00:22:02.198643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdullah-Al-Zubaer Imran, Matthew A. Massey, Nishat Nayla, Nusrat Munia, Tyler Ward","submitted_at":"2026-07-14T18:45:04Z","abstract_excerpt":"Self-supervision is a powerful technique for learning visual representations from unlabeled data. Existing techniques primarily adopt a two-stage approach for self-supervised learning (SSL): a pretraining stage on unlabeled data followed by a finetuning stage on labeled data. While this pipeline has demonstrated extreme effectiveness, the interaction between self-supervised and supervised learning objectives remains insufficiently understood. In this work, we systematically investigate whether jointly optimizing the self-supervised and supervised objectives during training provides a better al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13192","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.13192/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":"2607.13192","created_at":"2026-07-16T00:22:02.199094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13192v1","created_at":"2026-07-16T00:22:02.199094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13192","created_at":"2026-07-16T00:22:02.199094+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CNCMRMEPMWO","created_at":"2026-07-16T00:22:02.199094+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CNCMRMEPMWO2THL","created_at":"2026-07-16T00:22:02.199094+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CNCMRME","created_at":"2026-07-16T00:22:02.199094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CNCMRMEPMWO2THLSNCYD4Q3K7","json":"https://pith.science/pith/2CNCMRMEPMWO2THLSNCYD4Q3K7.json","graph_json":"https://pith.science/api/pith-number/2CNCMRMEPMWO2THLSNCYD4Q3K7/graph.json","events_json":"https://pith.science/api/pith-number/2CNCMRMEPMWO2THLSNCYD4Q3K7/events.json","paper":"https://pith.science/paper/2CNCMRME"},"agent_actions":{"view_html":"https://pith.science/pith/2CNCMRMEPMWO2THLSNCYD4Q3K7","download_json":"https://pith.science/pith/2CNCMRMEPMWO2THLSNCYD4Q3K7.json","view_paper":"https://pith.science/paper/2CNCMRME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13192&json=true","fetch_graph":"https://pith.science/api/pith-number/2CNCMRMEPMWO2THLSNCYD4Q3K7/graph.json","fetch_events":"https://pith.science/api/pith-number/2CNCMRMEPMWO2THLSNCYD4Q3K7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CNCMRMEPMWO2THLSNCYD4Q3K7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CNCMRMEPMWO2THLSNCYD4Q3K7/action/storage_attestation","attest_author":"https://pith.science/pith/2CNCMRMEPMWO2THLSNCYD4Q3K7/action/author_attestation","sign_citation":"https://pith.science/pith/2CNCMRMEPMWO2THLSNCYD4Q3K7/action/citation_signature","submit_replication":"https://pith.science/pith/2CNCMRMEPMWO2THLSNCYD4Q3K7/action/replication_record"}},"created_at":"2026-07-16T00:22:02.199094+00:00","updated_at":"2026-07-16T00:22:02.199094+00:00"}