{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:VEEBZ3QJFJ4EF4UYGXUEEEG23R","short_pith_number":"pith:VEEBZ3QJ","canonical_record":{"source":{"id":"1709.01867","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-06T15:53:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"089fa24159edd49c7f55e0852f9eea86a13624027bfc83e485112ff978d073ba","abstract_canon_sha256":"2493d8a31366bde95d1cce274e747911cbe79c5636cf0718601098d9deba6570"},"schema_version":"1.0"},"canonical_sha256":"a9081cee092a7842f29835e84210dadc4d3848335e4e01b088ea9a8751893f0f","source":{"kind":"arxiv","id":"1709.01867","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.01867","created_at":"2026-05-18T00:27:27Z"},{"alias_kind":"arxiv_version","alias_value":"1709.01867v4","created_at":"2026-05-18T00:27:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.01867","created_at":"2026-05-18T00:27:27Z"},{"alias_kind":"pith_short_12","alias_value":"VEEBZ3QJFJ4E","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VEEBZ3QJFJ4EF4UY","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VEEBZ3QJ","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:VEEBZ3QJFJ4EF4UYGXUEEEG23R","target":"record","payload":{"canonical_record":{"source":{"id":"1709.01867","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-06T15:53:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"089fa24159edd49c7f55e0852f9eea86a13624027bfc83e485112ff978d073ba","abstract_canon_sha256":"2493d8a31366bde95d1cce274e747911cbe79c5636cf0718601098d9deba6570"},"schema_version":"1.0"},"canonical_sha256":"a9081cee092a7842f29835e84210dadc4d3848335e4e01b088ea9a8751893f0f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:27.802997Z","signature_b64":"Jnha5cWS2TduqMKwN9eeOdUx7fvB4ES6bglhMVrKIBz1u0qhzmVgiD6m1q0MKrWkFBi9+zkoTozTqwkV5wb2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9081cee092a7842f29835e84210dadc4d3848335e4e01b088ea9a8751893f0f","last_reissued_at":"2026-05-18T00:27:27.802295Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:27.802295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.01867","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:27:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oe9AQeksAYNn9tfnLwaehnEomeFssoWsSLEjftz4rmM9QtrfAsOE5jIQ+xaM7nCo+6vau9ZuPxrysq80aOVGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T13:16:36.337857Z"},"content_sha256":"8e4efacef1fefac8894f7a56d570e39e95a5a58840c1e380202ba7385428286f","schema_version":"1.0","event_id":"sha256:8e4efacef1fefac8894f7a56d570e39e95a5a58840c1e380202ba7385428286f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:VEEBZ3QJFJ4EF4UYGXUEEEG23R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Networks Regularization Through Class-wise Invariant Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cl\\'ement Chatelain, Romain H\\'erault, S\\'ebastien Adam, Soufiane Belharbi","submitted_at":"2017-09-06T15:53:16Z","abstract_excerpt":"Training deep neural networks is known to require a large number of training samples. However, in many applications only few training samples are available. In this work, we tackle the issue of training neural networks for classification task when few training samples are available. We attempt to solve this issue by proposing a new regularization term that constrains the hidden layers of a network to learn class-wise invariant representations. In our regularization framework, learning invariant representations is generalized to the class membership where samples with the same class should have"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.01867","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:27:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lGozrUwnZhQ7VDIeZo5i/9Wz9mZKeQKNVZJtOVsnX7kMpiRBYptkX1VIbwCHUnZqHPKJtiIc6qqEuJe/ZpMHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T13:16:36.338188Z"},"content_sha256":"a59293a8327f4f72f89fe8ac892314a7874248a1a53ab2fdaab6756538c42b23","schema_version":"1.0","event_id":"sha256:a59293a8327f4f72f89fe8ac892314a7874248a1a53ab2fdaab6756538c42b23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VEEBZ3QJFJ4EF4UYGXUEEEG23R/bundle.json","state_url":"https://pith.science/pith/VEEBZ3QJFJ4EF4UYGXUEEEG23R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VEEBZ3QJFJ4EF4UYGXUEEEG23R/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":"2026-06-29T13:16:36Z","links":{"resolver":"https://pith.science/pith/VEEBZ3QJFJ4EF4UYGXUEEEG23R","bundle":"https://pith.science/pith/VEEBZ3QJFJ4EF4UYGXUEEEG23R/bundle.json","state":"https://pith.science/pith/VEEBZ3QJFJ4EF4UYGXUEEEG23R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VEEBZ3QJFJ4EF4UYGXUEEEG23R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:VEEBZ3QJFJ4EF4UYGXUEEEG23R","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":"2493d8a31366bde95d1cce274e747911cbe79c5636cf0718601098d9deba6570","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-06T15:53:16Z","title_canon_sha256":"089fa24159edd49c7f55e0852f9eea86a13624027bfc83e485112ff978d073ba"},"schema_version":"1.0","source":{"id":"1709.01867","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.01867","created_at":"2026-05-18T00:27:27Z"},{"alias_kind":"arxiv_version","alias_value":"1709.01867v4","created_at":"2026-05-18T00:27:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.01867","created_at":"2026-05-18T00:27:27Z"},{"alias_kind":"pith_short_12","alias_value":"VEEBZ3QJFJ4E","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VEEBZ3QJFJ4EF4UY","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VEEBZ3QJ","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:a59293a8327f4f72f89fe8ac892314a7874248a1a53ab2fdaab6756538c42b23","target":"graph","created_at":"2026-05-18T00:27:27Z","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"},"paper":{"abstract_excerpt":"Training deep neural networks is known to require a large number of training samples. However, in many applications only few training samples are available. In this work, we tackle the issue of training neural networks for classification task when few training samples are available. We attempt to solve this issue by proposing a new regularization term that constrains the hidden layers of a network to learn class-wise invariant representations. In our regularization framework, learning invariant representations is generalized to the class membership where samples with the same class should have","authors_text":"Cl\\'ement Chatelain, Romain H\\'erault, S\\'ebastien Adam, Soufiane Belharbi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-06T15:53:16Z","title":"Neural Networks Regularization Through Class-wise Invariant Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.01867","kind":"arxiv","version":4},"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":"sha256:8e4efacef1fefac8894f7a56d570e39e95a5a58840c1e380202ba7385428286f","target":"record","created_at":"2026-05-18T00:27:27Z","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":"2493d8a31366bde95d1cce274e747911cbe79c5636cf0718601098d9deba6570","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-06T15:53:16Z","title_canon_sha256":"089fa24159edd49c7f55e0852f9eea86a13624027bfc83e485112ff978d073ba"},"schema_version":"1.0","source":{"id":"1709.01867","kind":"arxiv","version":4}},"canonical_sha256":"a9081cee092a7842f29835e84210dadc4d3848335e4e01b088ea9a8751893f0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9081cee092a7842f29835e84210dadc4d3848335e4e01b088ea9a8751893f0f","first_computed_at":"2026-05-18T00:27:27.802295Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:27.802295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jnha5cWS2TduqMKwN9eeOdUx7fvB4ES6bglhMVrKIBz1u0qhzmVgiD6m1q0MKrWkFBi9+zkoTozTqwkV5wb2Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:27.802997Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.01867","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e4efacef1fefac8894f7a56d570e39e95a5a58840c1e380202ba7385428286f","sha256:a59293a8327f4f72f89fe8ac892314a7874248a1a53ab2fdaab6756538c42b23"],"state_sha256":"fb878373e6650c9dcfd5bf0b7834a8d049a4b288ead99c83ff82175fefd012d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"onuypS7QtF/xNSqrLyUmST4KgbOIL068/pYmT5QgPEtK2KMyN4gifrFXgZ07VWX4JqiF4ReOj9Rk+v8qfWCUDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T13:16:36.340048Z","bundle_sha256":"6d02b5e819f7e9dbd7031eb91e360d3b6328a9e03eebe06d357ad33ed2268881"}}