{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J72FLHWHXKQPYUMH6ZXPJIW3RB","short_pith_number":"pith:J72FLHWH","schema_version":"1.0","canonical_sha256":"4ff4559ec7baa0fc5187f66ef4a2db884238683201ba29aaa24abd5df25189a6","source":{"kind":"arxiv","id":"2412.02896","version":1},"attestation_state":"computed","paper":{"title":"GUESS: Generative Uncertainty Ensemble for Self Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Donald A. Adjeroh, Gianfranco Doretto, Salman Mohamadi","submitted_at":"2024-12-03T22:59:23Z","abstract_excerpt":"Self-supervised learning (SSL) frameworks consist of pretext task, and loss function aiming to learn useful general features from unlabeled data. The basic idea of most SSL baselines revolves around enforcing the invariance to a variety of data augmentations via the loss function. However, one main issue is that, inattentive or deterministic enforcement of the invariance to any kind of data augmentation is generally not only inefficient, but also potentially detrimental to performance on the downstream tasks. In this work, we investigate the issue from the viewpoint of uncertainty in invarianc"},"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":"2412.02896","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-03T22:59:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ed8f8a0fb489adeeee8db9c333d60296ae4ac4f2896444b0d5f5895adf83a05b","abstract_canon_sha256":"dfa4ac28b61aa519a57906a5494f5c068203a0e0baa0a284344a65d3e1669c90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:21.633972Z","signature_b64":"SZtKxcJyz/+lwYhDCh7voBtoNaiuv2T+u4IOd64ziMxt6BfO7EiS+JUxUK0S2XcPgZ3sAW6WQr157IHkG0bFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ff4559ec7baa0fc5187f66ef4a2db884238683201ba29aaa24abd5df25189a6","last_reissued_at":"2026-07-05T09:44:21.633437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:21.633437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GUESS: Generative Uncertainty Ensemble for Self Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Donald A. Adjeroh, Gianfranco Doretto, Salman Mohamadi","submitted_at":"2024-12-03T22:59:23Z","abstract_excerpt":"Self-supervised learning (SSL) frameworks consist of pretext task, and loss function aiming to learn useful general features from unlabeled data. The basic idea of most SSL baselines revolves around enforcing the invariance to a variety of data augmentations via the loss function. However, one main issue is that, inattentive or deterministic enforcement of the invariance to any kind of data augmentation is generally not only inefficient, but also potentially detrimental to performance on the downstream tasks. In this work, we investigate the issue from the viewpoint of uncertainty in invarianc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02896","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/2412.02896/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":"2412.02896","created_at":"2026-07-05T09:44:21.633496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02896v1","created_at":"2026-07-05T09:44:21.633496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02896","created_at":"2026-07-05T09:44:21.633496+00:00"},{"alias_kind":"pith_short_12","alias_value":"J72FLHWHXKQP","created_at":"2026-07-05T09:44:21.633496+00:00"},{"alias_kind":"pith_short_16","alias_value":"J72FLHWHXKQPYUMH","created_at":"2026-07-05T09:44:21.633496+00:00"},{"alias_kind":"pith_short_8","alias_value":"J72FLHWH","created_at":"2026-07-05T09:44:21.633496+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/J72FLHWHXKQPYUMH6ZXPJIW3RB","json":"https://pith.science/pith/J72FLHWHXKQPYUMH6ZXPJIW3RB.json","graph_json":"https://pith.science/api/pith-number/J72FLHWHXKQPYUMH6ZXPJIW3RB/graph.json","events_json":"https://pith.science/api/pith-number/J72FLHWHXKQPYUMH6ZXPJIW3RB/events.json","paper":"https://pith.science/paper/J72FLHWH"},"agent_actions":{"view_html":"https://pith.science/pith/J72FLHWHXKQPYUMH6ZXPJIW3RB","download_json":"https://pith.science/pith/J72FLHWHXKQPYUMH6ZXPJIW3RB.json","view_paper":"https://pith.science/paper/J72FLHWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02896&json=true","fetch_graph":"https://pith.science/api/pith-number/J72FLHWHXKQPYUMH6ZXPJIW3RB/graph.json","fetch_events":"https://pith.science/api/pith-number/J72FLHWHXKQPYUMH6ZXPJIW3RB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J72FLHWHXKQPYUMH6ZXPJIW3RB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J72FLHWHXKQPYUMH6ZXPJIW3RB/action/storage_attestation","attest_author":"https://pith.science/pith/J72FLHWHXKQPYUMH6ZXPJIW3RB/action/author_attestation","sign_citation":"https://pith.science/pith/J72FLHWHXKQPYUMH6ZXPJIW3RB/action/citation_signature","submit_replication":"https://pith.science/pith/J72FLHWHXKQPYUMH6ZXPJIW3RB/action/replication_record"}},"created_at":"2026-07-05T09:44:21.633496+00:00","updated_at":"2026-07-05T09:44:21.633496+00:00"}