{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2NTLJS6C3YKJR3UV4HDNP5AN4I","short_pith_number":"pith:2NTLJS6C","schema_version":"1.0","canonical_sha256":"d366b4cbc2de1498ee95e1c6d7f40de20448c8f76b1c2d69d68b60e991664c9e","source":{"kind":"arxiv","id":"2302.11380","version":1},"attestation_state":"computed","paper":{"title":"Stress and Adaptation: Applying Anna Karenina Principle in Deep Learning for Image Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hanna Antson, Jaesik Choi, Kallol Roy, Nesma Mahmoud, Osamu Shimmi","submitted_at":"2023-02-22T13:53:20Z","abstract_excerpt":"Image classification with deep neural networks has reached state-of-art with high accuracy. This success is attributed to good internal representation features that bypasses the difficulties of the non-convex optimization problems. We have little understanding of these internal representations, let alone quantifying them. Recent research efforts have focused on alternative theories and explanations of the generalizability of these deep networks. We propose the alternative perturbation of deep models during their training induces changes that lead to transitions to different families. The resul"},"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":"2302.11380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-22T13:53:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e9788d749f977a82a58cdce25c29364eaa6517afdb3fe1432e12f1af6e4ad5f1","abstract_canon_sha256":"6514d6cb1c1acfb7719cb512d3fc4984d5daf60d9a524fbf4d956a6d3f6cbce8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:42.934618Z","signature_b64":"zFCKKimTieU41JzEQzUOUndCNEACbGzSHwDn+EFoPLrhqncHdQr8q5+LmMa/SDiXXXA4PBtjsobHktt0K/ZcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d366b4cbc2de1498ee95e1c6d7f40de20448c8f76b1c2d69d68b60e991664c9e","last_reissued_at":"2026-07-05T05:44:42.934200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:42.934200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stress and Adaptation: Applying Anna Karenina Principle in Deep Learning for Image Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hanna Antson, Jaesik Choi, Kallol Roy, Nesma Mahmoud, Osamu Shimmi","submitted_at":"2023-02-22T13:53:20Z","abstract_excerpt":"Image classification with deep neural networks has reached state-of-art with high accuracy. This success is attributed to good internal representation features that bypasses the difficulties of the non-convex optimization problems. We have little understanding of these internal representations, let alone quantifying them. Recent research efforts have focused on alternative theories and explanations of the generalizability of these deep networks. We propose the alternative perturbation of deep models during their training induces changes that lead to transitions to different families. The resul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11380","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/2302.11380/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":"2302.11380","created_at":"2026-07-05T05:44:42.934247+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.11380v1","created_at":"2026-07-05T05:44:42.934247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11380","created_at":"2026-07-05T05:44:42.934247+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NTLJS6C3YKJ","created_at":"2026-07-05T05:44:42.934247+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NTLJS6C3YKJR3UV","created_at":"2026-07-05T05:44:42.934247+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NTLJS6C","created_at":"2026-07-05T05:44:42.934247+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20980","citing_title":"Robusto-2: Benchmarking Humans & VLMs for Autonomous Driving in Lima & New York City","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2NTLJS6C3YKJR3UV4HDNP5AN4I","json":"https://pith.science/pith/2NTLJS6C3YKJR3UV4HDNP5AN4I.json","graph_json":"https://pith.science/api/pith-number/2NTLJS6C3YKJR3UV4HDNP5AN4I/graph.json","events_json":"https://pith.science/api/pith-number/2NTLJS6C3YKJR3UV4HDNP5AN4I/events.json","paper":"https://pith.science/paper/2NTLJS6C"},"agent_actions":{"view_html":"https://pith.science/pith/2NTLJS6C3YKJR3UV4HDNP5AN4I","download_json":"https://pith.science/pith/2NTLJS6C3YKJR3UV4HDNP5AN4I.json","view_paper":"https://pith.science/paper/2NTLJS6C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.11380&json=true","fetch_graph":"https://pith.science/api/pith-number/2NTLJS6C3YKJR3UV4HDNP5AN4I/graph.json","fetch_events":"https://pith.science/api/pith-number/2NTLJS6C3YKJR3UV4HDNP5AN4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NTLJS6C3YKJR3UV4HDNP5AN4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NTLJS6C3YKJR3UV4HDNP5AN4I/action/storage_attestation","attest_author":"https://pith.science/pith/2NTLJS6C3YKJR3UV4HDNP5AN4I/action/author_attestation","sign_citation":"https://pith.science/pith/2NTLJS6C3YKJR3UV4HDNP5AN4I/action/citation_signature","submit_replication":"https://pith.science/pith/2NTLJS6C3YKJR3UV4HDNP5AN4I/action/replication_record"}},"created_at":"2026-07-05T05:44:42.934247+00:00","updated_at":"2026-07-05T05:44:42.934247+00:00"}