{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SPRVURBRRCUAFAWZQMVDQYMU6O","short_pith_number":"pith:SPRVURBR","canonical_record":{"source":{"id":"1901.10082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-29T03:12:42Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"023931b0495a44e991a53e45b521a6df024427face28cc472c2e35e6e4e39a4e","abstract_canon_sha256":"c793bea46f025e000823dbf1eedf4eaff2627072c33217a4a128e839d91a23f1"},"schema_version":"1.0"},"canonical_sha256":"93e35a443188a80282d9832a386194f3b09eaee7b8d44c6fa6756a1360371400","source":{"kind":"arxiv","id":"1901.10082","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.10082","created_at":"2026-05-17T23:42:24Z"},{"alias_kind":"arxiv_version","alias_value":"1901.10082v1","created_at":"2026-05-17T23:42:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10082","created_at":"2026-05-17T23:42:24Z"},{"alias_kind":"pith_short_12","alias_value":"SPRVURBRRCUA","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SPRVURBRRCUAFAWZ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SPRVURBR","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SPRVURBRRCUAFAWZQMVDQYMU6O","target":"record","payload":{"canonical_record":{"source":{"id":"1901.10082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-29T03:12:42Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"023931b0495a44e991a53e45b521a6df024427face28cc472c2e35e6e4e39a4e","abstract_canon_sha256":"c793bea46f025e000823dbf1eedf4eaff2627072c33217a4a128e839d91a23f1"},"schema_version":"1.0"},"canonical_sha256":"93e35a443188a80282d9832a386194f3b09eaee7b8d44c6fa6756a1360371400","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:24.361216Z","signature_b64":"zi74gqwUxNGaEv/VinBs0gu/6lWgHp8f667SE6y/UczvEJG8x3IIIxtJxunwhM2QT8HQOhfGSwaNK0Khi1RwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93e35a443188a80282d9832a386194f3b09eaee7b8d44c6fa6756a1360371400","last_reissued_at":"2026-05-17T23:42:24.360615Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:24.360615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.10082","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yop3Hh96YX+uvdZfUoHbIs8LUBTzKyawYtDNPfX1U6sMHqhYBhUEvZoB/q9p96xqjmDsaskdI6IlWhbqcsvaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:06:41.679483Z"},"content_sha256":"9fc5449f6c6ce67561320c50616114798fdb6aedf24e9dea12b345e7f616e66a","schema_version":"1.0","event_id":"sha256:9fc5449f6c6ce67561320c50616114798fdb6aedf24e9dea12b345e7f616e66a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SPRVURBRRCUAFAWZQMVDQYMU6O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational Characterizations of Local Entropy and Heat Regularization in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Daniel Sanz-Alonso, Nicolas Garcia Trillos, Zach Kaplan","submitted_at":"2019-01-29T03:12:42Z","abstract_excerpt":"The aim of this paper is to provide new theoretical and computational understanding on two loss regularizations employed in deep learning, known as local entropy and heat regularization. For both regularized losses we introduce variational characterizations that naturally suggest a two-step scheme for their optimization, based on the iterative shift of a probability density and the calculation of a best Gaussian approximation in Kullback-Leibler divergence. Under this unified light, the optimization schemes for local entropy and heat regularized loss differ only over which argument of the Kull"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10082","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":""},"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":"2026-05-17T23:42:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g7O8B58xtNSnBvfE9TreeEQebgBFxM8VWR/NmhpD9RQvUa0wtqk2P6bAwfBRQiLg41qtLW5pf+v89YPnyIBQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:06:41.679996Z"},"content_sha256":"172e824294360c53b36e80e8594a2fb84e126ea1b32fec71b3421e5a4c8e0f83","schema_version":"1.0","event_id":"sha256:172e824294360c53b36e80e8594a2fb84e126ea1b32fec71b3421e5a4c8e0f83"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SPRVURBRRCUAFAWZQMVDQYMU6O/bundle.json","state_url":"https://pith.science/pith/SPRVURBRRCUAFAWZQMVDQYMU6O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SPRVURBRRCUAFAWZQMVDQYMU6O/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":"2026-05-30T18:06:41Z","links":{"resolver":"https://pith.science/pith/SPRVURBRRCUAFAWZQMVDQYMU6O","bundle":"https://pith.science/pith/SPRVURBRRCUAFAWZQMVDQYMU6O/bundle.json","state":"https://pith.science/pith/SPRVURBRRCUAFAWZQMVDQYMU6O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SPRVURBRRCUAFAWZQMVDQYMU6O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SPRVURBRRCUAFAWZQMVDQYMU6O","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":"c793bea46f025e000823dbf1eedf4eaff2627072c33217a4a128e839d91a23f1","cross_cats_sorted":["cs.LG","stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-29T03:12:42Z","title_canon_sha256":"023931b0495a44e991a53e45b521a6df024427face28cc472c2e35e6e4e39a4e"},"schema_version":"1.0","source":{"id":"1901.10082","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.10082","created_at":"2026-05-17T23:42:24Z"},{"alias_kind":"arxiv_version","alias_value":"1901.10082v1","created_at":"2026-05-17T23:42:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10082","created_at":"2026-05-17T23:42:24Z"},{"alias_kind":"pith_short_12","alias_value":"SPRVURBRRCUA","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SPRVURBRRCUAFAWZ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SPRVURBR","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:172e824294360c53b36e80e8594a2fb84e126ea1b32fec71b3421e5a4c8e0f83","target":"graph","created_at":"2026-05-17T23:42:24Z","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":"The aim of this paper is to provide new theoretical and computational understanding on two loss regularizations employed in deep learning, known as local entropy and heat regularization. For both regularized losses we introduce variational characterizations that naturally suggest a two-step scheme for their optimization, based on the iterative shift of a probability density and the calculation of a best Gaussian approximation in Kullback-Leibler divergence. Under this unified light, the optimization schemes for local entropy and heat regularized loss differ only over which argument of the Kull","authors_text":"Daniel Sanz-Alonso, Nicolas Garcia Trillos, Zach Kaplan","cross_cats":["cs.LG","stat.CO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-29T03:12:42Z","title":"Variational Characterizations of Local Entropy and Heat Regularization in Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10082","kind":"arxiv","version":1},"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":"sha256:9fc5449f6c6ce67561320c50616114798fdb6aedf24e9dea12b345e7f616e66a","target":"record","created_at":"2026-05-17T23:42:24Z","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":"c793bea46f025e000823dbf1eedf4eaff2627072c33217a4a128e839d91a23f1","cross_cats_sorted":["cs.LG","stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-29T03:12:42Z","title_canon_sha256":"023931b0495a44e991a53e45b521a6df024427face28cc472c2e35e6e4e39a4e"},"schema_version":"1.0","source":{"id":"1901.10082","kind":"arxiv","version":1}},"canonical_sha256":"93e35a443188a80282d9832a386194f3b09eaee7b8d44c6fa6756a1360371400","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93e35a443188a80282d9832a386194f3b09eaee7b8d44c6fa6756a1360371400","first_computed_at":"2026-05-17T23:42:24.360615Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:24.360615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zi74gqwUxNGaEv/VinBs0gu/6lWgHp8f667SE6y/UczvEJG8x3IIIxtJxunwhM2QT8HQOhfGSwaNK0Khi1RwAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:24.361216Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.10082","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fc5449f6c6ce67561320c50616114798fdb6aedf24e9dea12b345e7f616e66a","sha256:172e824294360c53b36e80e8594a2fb84e126ea1b32fec71b3421e5a4c8e0f83"],"state_sha256":"fbb26cda7f7bc1aab272f52a75f14eb05a5ddaa827295a738d11f802c0f233f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XZ9ya0hYGnG1Jdn4EfQ+KtAxM2DLz4u8wJX5idA1RF+NVQHeeXn05rYgLwu+mqS1pbPi0IYMCrK7acLloDGwDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T18:06:41.683009Z","bundle_sha256":"0477a55af3a5b51f3fcf14203c8b5bce301823dc54a3d58a445b39b0eef06d2b"}}