{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BOTPBOWWTESKPCG6KRGSR7XZLB","short_pith_number":"pith:BOTPBOWW","schema_version":"1.0","canonical_sha256":"0ba6f0bad69924a788de544d28fef95869a033de51ea4e6f44c52607c7072000","source":{"kind":"arxiv","id":"2101.06459","version":1},"attestation_state":"computed","paper":{"title":"Robustness to Augmentations as a Generalization metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dhruva Kashyap, Natarajan Subramanyam, Sumukh Aithal K","submitted_at":"2021-01-16T15:36:38Z","abstract_excerpt":"Generalization is the ability of a model to predict on unseen domains and is a fundamental task in machine learning. Several generalization bounds, both theoretical and empirical have been proposed but they do not provide tight bounds .In this work, we propose a simple yet effective method to predict the generalization performance of a model by using the concept that models that are robust to augmentations are more generalizable than those which are not. We experiment with several augmentations and composition of augmentations to check the generalization capacity of a model. We also provide a "},"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":"2101.06459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-16T15:36:38Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9ea425c5ec922186c5699126a437ab93c9858ff23952d4591fd72491111be352","abstract_canon_sha256":"f02691365f3d1aedd85d5957ff0bfc7e50fe56f463b47ab4af78a282a05f65ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:18.613034Z","signature_b64":"+Uh7Z6oAxkm1Uo+WGtxGdE02emrfupDoI1no2hLno5revq6GoQwY2uMFFyIENBRDStP9+CKuzYF4e66g4sfSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ba6f0bad69924a788de544d28fef95869a033de51ea4e6f44c52607c7072000","last_reissued_at":"2026-07-05T02:07:18.612579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:18.612579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustness to Augmentations as a Generalization metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dhruva Kashyap, Natarajan Subramanyam, Sumukh Aithal K","submitted_at":"2021-01-16T15:36:38Z","abstract_excerpt":"Generalization is the ability of a model to predict on unseen domains and is a fundamental task in machine learning. Several generalization bounds, both theoretical and empirical have been proposed but they do not provide tight bounds .In this work, we propose a simple yet effective method to predict the generalization performance of a model by using the concept that models that are robust to augmentations are more generalizable than those which are not. We experiment with several augmentations and composition of augmentations to check the generalization capacity of a model. We also provide a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.06459","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/2101.06459/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":"2101.06459","created_at":"2026-07-05T02:07:18.612641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.06459v1","created_at":"2026-07-05T02:07:18.612641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.06459","created_at":"2026-07-05T02:07:18.612641+00:00"},{"alias_kind":"pith_short_12","alias_value":"BOTPBOWWTESK","created_at":"2026-07-05T02:07:18.612641+00:00"},{"alias_kind":"pith_short_16","alias_value":"BOTPBOWWTESKPCG6","created_at":"2026-07-05T02:07:18.612641+00:00"},{"alias_kind":"pith_short_8","alias_value":"BOTPBOWW","created_at":"2026-07-05T02:07:18.612641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.00450","citing_title":"Unsupervised Source-Free Ranking of Biomedical Segmentation Models Under Distribution Shift","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BOTPBOWWTESKPCG6KRGSR7XZLB","json":"https://pith.science/pith/BOTPBOWWTESKPCG6KRGSR7XZLB.json","graph_json":"https://pith.science/api/pith-number/BOTPBOWWTESKPCG6KRGSR7XZLB/graph.json","events_json":"https://pith.science/api/pith-number/BOTPBOWWTESKPCG6KRGSR7XZLB/events.json","paper":"https://pith.science/paper/BOTPBOWW"},"agent_actions":{"view_html":"https://pith.science/pith/BOTPBOWWTESKPCG6KRGSR7XZLB","download_json":"https://pith.science/pith/BOTPBOWWTESKPCG6KRGSR7XZLB.json","view_paper":"https://pith.science/paper/BOTPBOWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.06459&json=true","fetch_graph":"https://pith.science/api/pith-number/BOTPBOWWTESKPCG6KRGSR7XZLB/graph.json","fetch_events":"https://pith.science/api/pith-number/BOTPBOWWTESKPCG6KRGSR7XZLB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BOTPBOWWTESKPCG6KRGSR7XZLB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BOTPBOWWTESKPCG6KRGSR7XZLB/action/storage_attestation","attest_author":"https://pith.science/pith/BOTPBOWWTESKPCG6KRGSR7XZLB/action/author_attestation","sign_citation":"https://pith.science/pith/BOTPBOWWTESKPCG6KRGSR7XZLB/action/citation_signature","submit_replication":"https://pith.science/pith/BOTPBOWWTESKPCG6KRGSR7XZLB/action/replication_record"}},"created_at":"2026-07-05T02:07:18.612641+00:00","updated_at":"2026-07-05T02:07:18.612641+00:00"}