{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MTVI5KFTP2KW2QRDEGCNEWM3R5","short_pith_number":"pith:MTVI5KFT","schema_version":"1.0","canonical_sha256":"64ea8ea8b37e956d42232184d2599b8f72af97f065147fb3c99e6523d86cb752","source":{"kind":"arxiv","id":"2209.01275","version":1},"attestation_state":"computed","paper":{"title":"Feature diversity in self-supervised learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arjun Vaithilingam Sudhakar, Pranshu Malviya","submitted_at":"2022-09-02T21:34:11Z","abstract_excerpt":"Many studies on scaling laws consider basic factors such as model size, model shape, dataset size, and compute power. These factors are easily tunable and represent the fundamental elements of any machine learning setup. But researchers have also employed more complex factors to estimate the test error and generalization performance with high predictability. These factors are generally specific to the domain or application. For example, feature diversity was primarily used for promoting syn-to-real transfer by Chen et al. (2021). With numerous scaling factors defined in previous works, it woul"},"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":"2209.01275","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-02T21:34:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a9cfeac5a6dc9afab13c5a3b0f28b87d59fc49d9cd299fc9683cd666fbe51b87","abstract_canon_sha256":"4de8ee1f07547979f30aaf78829af69b764b9e04280d375a81b16a147b484f13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:26.951036Z","signature_b64":"iWsiT2FC3AgnVh9mYjxMeT2Pfsjei7jCjI+WLyvqF35O30GV8rdnjw6ijVreVqh5aPSExDCopIgJOTtI/BabBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64ea8ea8b37e956d42232184d2599b8f72af97f065147fb3c99e6523d86cb752","last_reissued_at":"2026-07-05T04:54:26.950574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:26.950574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature diversity in self-supervised learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arjun Vaithilingam Sudhakar, Pranshu Malviya","submitted_at":"2022-09-02T21:34:11Z","abstract_excerpt":"Many studies on scaling laws consider basic factors such as model size, model shape, dataset size, and compute power. These factors are easily tunable and represent the fundamental elements of any machine learning setup. But researchers have also employed more complex factors to estimate the test error and generalization performance with high predictability. These factors are generally specific to the domain or application. For example, feature diversity was primarily used for promoting syn-to-real transfer by Chen et al. (2021). With numerous scaling factors defined in previous works, it woul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.01275","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/2209.01275/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":"2209.01275","created_at":"2026-07-05T04:54:26.950630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.01275v1","created_at":"2026-07-05T04:54:26.950630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.01275","created_at":"2026-07-05T04:54:26.950630+00:00"},{"alias_kind":"pith_short_12","alias_value":"MTVI5KFTP2KW","created_at":"2026-07-05T04:54:26.950630+00:00"},{"alias_kind":"pith_short_16","alias_value":"MTVI5KFTP2KW2QRD","created_at":"2026-07-05T04:54:26.950630+00:00"},{"alias_kind":"pith_short_8","alias_value":"MTVI5KFT","created_at":"2026-07-05T04:54:26.950630+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09331","citing_title":"Multi-Agent Language Models: Advancing Cooperation, Coordination, and Adaptation","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MTVI5KFTP2KW2QRDEGCNEWM3R5","json":"https://pith.science/pith/MTVI5KFTP2KW2QRDEGCNEWM3R5.json","graph_json":"https://pith.science/api/pith-number/MTVI5KFTP2KW2QRDEGCNEWM3R5/graph.json","events_json":"https://pith.science/api/pith-number/MTVI5KFTP2KW2QRDEGCNEWM3R5/events.json","paper":"https://pith.science/paper/MTVI5KFT"},"agent_actions":{"view_html":"https://pith.science/pith/MTVI5KFTP2KW2QRDEGCNEWM3R5","download_json":"https://pith.science/pith/MTVI5KFTP2KW2QRDEGCNEWM3R5.json","view_paper":"https://pith.science/paper/MTVI5KFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.01275&json=true","fetch_graph":"https://pith.science/api/pith-number/MTVI5KFTP2KW2QRDEGCNEWM3R5/graph.json","fetch_events":"https://pith.science/api/pith-number/MTVI5KFTP2KW2QRDEGCNEWM3R5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MTVI5KFTP2KW2QRDEGCNEWM3R5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MTVI5KFTP2KW2QRDEGCNEWM3R5/action/storage_attestation","attest_author":"https://pith.science/pith/MTVI5KFTP2KW2QRDEGCNEWM3R5/action/author_attestation","sign_citation":"https://pith.science/pith/MTVI5KFTP2KW2QRDEGCNEWM3R5/action/citation_signature","submit_replication":"https://pith.science/pith/MTVI5KFTP2KW2QRDEGCNEWM3R5/action/replication_record"}},"created_at":"2026-07-05T04:54:26.950630+00:00","updated_at":"2026-07-05T04:54:26.950630+00:00"}