{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4YKODAOJD4S5HGIVVTDZ5SYXSQ","short_pith_number":"pith:4YKODAOJ","canonical_record":{"source":{"id":"2011.13602","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-11-27T08:33:51Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"607426d7db431431a9a9c494d6d68a008c8337b3c16fd47e97c0316d62a69c7b","abstract_canon_sha256":"a49e5933b21dd6d46ceae084e67f8765fda8176eb8d27b138ab4d9ea2fa2aa4e"},"schema_version":"1.0"},"canonical_sha256":"e614e181c91f25d39915acc79ecb179421655248c36d5eb0028fb8800b3016b1","source":{"kind":"arxiv","id":"2011.13602","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.13602","created_at":"2026-07-05T08:13:06Z"},{"alias_kind":"arxiv_version","alias_value":"2011.13602v2","created_at":"2026-07-05T08:13:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13602","created_at":"2026-07-05T08:13:06Z"},{"alias_kind":"pith_short_12","alias_value":"4YKODAOJD4S5","created_at":"2026-07-05T08:13:06Z"},{"alias_kind":"pith_short_16","alias_value":"4YKODAOJD4S5HGIV","created_at":"2026-07-05T08:13:06Z"},{"alias_kind":"pith_short_8","alias_value":"4YKODAOJ","created_at":"2026-07-05T08:13:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4YKODAOJD4S5HGIVVTDZ5SYXSQ","target":"record","payload":{"canonical_record":{"source":{"id":"2011.13602","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-11-27T08:33:51Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"607426d7db431431a9a9c494d6d68a008c8337b3c16fd47e97c0316d62a69c7b","abstract_canon_sha256":"a49e5933b21dd6d46ceae084e67f8765fda8176eb8d27b138ab4d9ea2fa2aa4e"},"schema_version":"1.0"},"canonical_sha256":"e614e181c91f25d39915acc79ecb179421655248c36d5eb0028fb8800b3016b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:06.204215Z","signature_b64":"O59AoF/UnPGu3lhmQEg87Aazcy4MeQ6+uo1BUrz3K/c9GwFLbyKOMPtzYhbZleHYKnaCwyYWzaudFFUWknBMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e614e181c91f25d39915acc79ecb179421655248c36d5eb0028fb8800b3016b1","last_reissued_at":"2026-07-05T08:13:06.203778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:06.203778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.13602","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:13:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IPmBssLtIloRiNbcHPGziSBO0TQR1dJDGoRLWzMhnNKQKs+E+GEyGS3GAl1u1XpRM97jCHeiwrqGU9huRTATAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:31:58.814268Z"},"content_sha256":"8b4475ccc8b6985e07660a1a4f1805860e556d8188596a125320bd2fabe5aa40","schema_version":"1.0","event_id":"sha256:8b4475ccc8b6985e07660a1a4f1805860e556d8188596a125320bd2fabe5aa40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4YKODAOJD4S5HGIVVTDZ5SYXSQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Statistical theory for image classification using deep convolutional neural networks with cross-entropy loss under the hierarchical max-pooling model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Michael Kohler, Sophie Langer","submitted_at":"2020-11-27T08:33:51Z","abstract_excerpt":"Convolutional neural networks (CNNs) trained with cross-entropy loss have proven to be extremely successful in classifying images. In recent years, much work has been done to also improve the theoretical understanding of neural networks. Nevertheless, it seems limited when these networks are trained with cross-entropy loss, mainly because of the unboundedness of the target function. In this paper, we aim to fill this gap by analyzing the rate of the excess risk of a CNN classifier trained by cross-entropy loss. Under suitable assumptions on the smoothness and structure of the a posteriori prob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13602","kind":"arxiv","version":2},"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/2011.13602/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:13:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rd4REl9cjXSaOI6X+JFGRl98YHkH30/me/KBFHz5aVkaeuCzMPKBC1e12xfFcEkAo0B4oOi77GiV+fjtQFBGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:31:58.814647Z"},"content_sha256":"e81034808454f4ba0d6ef904d77a2be0a389ad2b9581cd3e2735f8849c1f2915","schema_version":"1.0","event_id":"sha256:e81034808454f4ba0d6ef904d77a2be0a389ad2b9581cd3e2735f8849c1f2915"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4YKODAOJD4S5HGIVVTDZ5SYXSQ/bundle.json","state_url":"https://pith.science/pith/4YKODAOJD4S5HGIVVTDZ5SYXSQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4YKODAOJD4S5HGIVVTDZ5SYXSQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T05:31:58Z","links":{"resolver":"https://pith.science/pith/4YKODAOJD4S5HGIVVTDZ5SYXSQ","bundle":"https://pith.science/pith/4YKODAOJD4S5HGIVVTDZ5SYXSQ/bundle.json","state":"https://pith.science/pith/4YKODAOJD4S5HGIVVTDZ5SYXSQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4YKODAOJD4S5HGIVVTDZ5SYXSQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4YKODAOJD4S5HGIVVTDZ5SYXSQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a49e5933b21dd6d46ceae084e67f8765fda8176eb8d27b138ab4d9ea2fa2aa4e","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-11-27T08:33:51Z","title_canon_sha256":"607426d7db431431a9a9c494d6d68a008c8337b3c16fd47e97c0316d62a69c7b"},"schema_version":"1.0","source":{"id":"2011.13602","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.13602","created_at":"2026-07-05T08:13:06Z"},{"alias_kind":"arxiv_version","alias_value":"2011.13602v2","created_at":"2026-07-05T08:13:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13602","created_at":"2026-07-05T08:13:06Z"},{"alias_kind":"pith_short_12","alias_value":"4YKODAOJD4S5","created_at":"2026-07-05T08:13:06Z"},{"alias_kind":"pith_short_16","alias_value":"4YKODAOJD4S5HGIV","created_at":"2026-07-05T08:13:06Z"},{"alias_kind":"pith_short_8","alias_value":"4YKODAOJ","created_at":"2026-07-05T08:13:06Z"}],"graph_snapshots":[{"event_id":"sha256:e81034808454f4ba0d6ef904d77a2be0a389ad2b9581cd3e2735f8849c1f2915","target":"graph","created_at":"2026-07-05T08:13:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2011.13602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Convolutional neural networks (CNNs) trained with cross-entropy loss have proven to be extremely successful in classifying images. In recent years, much work has been done to also improve the theoretical understanding of neural networks. Nevertheless, it seems limited when these networks are trained with cross-entropy loss, mainly because of the unboundedness of the target function. In this paper, we aim to fill this gap by analyzing the rate of the excess risk of a CNN classifier trained by cross-entropy loss. Under suitable assumptions on the smoothness and structure of the a posteriori prob","authors_text":"Michael Kohler, Sophie Langer","cross_cats":["stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-11-27T08:33:51Z","title":"Statistical theory for image classification using deep convolutional neural networks with cross-entropy loss under the hierarchical max-pooling model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13602","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8b4475ccc8b6985e07660a1a4f1805860e556d8188596a125320bd2fabe5aa40","target":"record","created_at":"2026-07-05T08:13:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a49e5933b21dd6d46ceae084e67f8765fda8176eb8d27b138ab4d9ea2fa2aa4e","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-11-27T08:33:51Z","title_canon_sha256":"607426d7db431431a9a9c494d6d68a008c8337b3c16fd47e97c0316d62a69c7b"},"schema_version":"1.0","source":{"id":"2011.13602","kind":"arxiv","version":2}},"canonical_sha256":"e614e181c91f25d39915acc79ecb179421655248c36d5eb0028fb8800b3016b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e614e181c91f25d39915acc79ecb179421655248c36d5eb0028fb8800b3016b1","first_computed_at":"2026-07-05T08:13:06.203778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:13:06.203778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O59AoF/UnPGu3lhmQEg87Aazcy4MeQ6+uo1BUrz3K/c9GwFLbyKOMPtzYhbZleHYKnaCwyYWzaudFFUWknBMDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:13:06.204215Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.13602","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b4475ccc8b6985e07660a1a4f1805860e556d8188596a125320bd2fabe5aa40","sha256:e81034808454f4ba0d6ef904d77a2be0a389ad2b9581cd3e2735f8849c1f2915"],"state_sha256":"da7019fa7fcae955788a05fd671476165aab13802139e593127ba0889c132e19"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uFsWQVSfkgfV4bamoW4NPzX8Hx+gF9SvAuPpw36o9HK54bTUWKSGRecdiqdHSW++WHDb4JpSggmkqeK8ATQVCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:31:58.818453Z","bundle_sha256":"4fee90972cc604682c17d2c37be716caf92abd50d9ff6d0b1b7eb06e25210169"}}