{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5TUTNO2Z7LCBZIBH5KNE4NXEHC","short_pith_number":"pith:5TUTNO2Z","canonical_record":{"source":{"id":"1905.00135","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-30T23:35:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3feb0b20be10e283f6824a3e261ecfde267d686b2fc0578e6076bd58b5d34bbd","abstract_canon_sha256":"5de81e90ebff83f652efb616416e8a1da5868483c8ca8404820876bfa5c828fe"},"schema_version":"1.0"},"canonical_sha256":"ece936bb59fac41ca027ea9a4e36e438a9d35d1889d2eb190034540ea68e98bd","source":{"kind":"arxiv","id":"1905.00135","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.00135","created_at":"2026-05-17T23:41:36Z"},{"alias_kind":"arxiv_version","alias_value":"1905.00135v1","created_at":"2026-05-17T23:41:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00135","created_at":"2026-05-17T23:41:36Z"},{"alias_kind":"pith_short_12","alias_value":"5TUTNO2Z7LCB","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5TUTNO2Z7LCBZIBH","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5TUTNO2Z","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5TUTNO2Z7LCBZIBH5KNE4NXEHC","target":"record","payload":{"canonical_record":{"source":{"id":"1905.00135","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-30T23:35:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3feb0b20be10e283f6824a3e261ecfde267d686b2fc0578e6076bd58b5d34bbd","abstract_canon_sha256":"5de81e90ebff83f652efb616416e8a1da5868483c8ca8404820876bfa5c828fe"},"schema_version":"1.0"},"canonical_sha256":"ece936bb59fac41ca027ea9a4e36e438a9d35d1889d2eb190034540ea68e98bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:36.325064Z","signature_b64":"tvQy9kgF5XwKwHbCHPOHE0Ak+sFwhPWvgkZ1vpHgYuSoqX5VxHsV+cyL5e03M0RjBJWKFFVlw6S8RcvR46k9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ece936bb59fac41ca027ea9a4e36e438a9d35d1889d2eb190034540ea68e98bd","last_reissued_at":"2026-05-17T23:41:36.324568Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:36.324568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.00135","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":"2026-05-17T23:41:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W6kGwsflp77f4/vDV6ouY5gD8ivQLiURqZ2egEa+a2U7uUWK6Oy/rDURHGVEjuU20dh2bEvMkx3lj+Z4Uf7/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T11:01:46.684463Z"},"content_sha256":"d199d4f0c988001794e63eac54558c16d50168d6d08f19efce0fd83433c1aea4","schema_version":"1.0","event_id":"sha256:d199d4f0c988001794e63eac54558c16d50168d6d08f19efce0fd83433c1aea4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5TUTNO2Z7LCBZIBH5KNE4NXEHC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Harmonic Networks with Limited Training Samples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Matej Ulicny, Rozenn Dahyot, Vladimir A. Krylov","submitted_at":"2019-04-30T23:35:30Z","abstract_excerpt":"Convolutional neural networks (CNNs) are very popular nowadays for image processing. CNNs allow one to learn optimal filters in a (mostly) supervised machine learning context. However this typically requires abundant labelled training data to estimate the filter parameters. Alternative strategies have been deployed for reducing the number of parameters and / or filters to be learned and thus decrease overfitting. In the context of reverting to preset filters, we propose here a computationally efficient harmonic block that uses Discrete Cosine Transform (DCT) filters in CNNs. In this work we ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00135","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":"2026-05-17T23:41:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"COqhwXBmjP/5AJG2bsqvwXTl9S4HdLMesDgVcFVIBH9gxzBORoVE0SsGVEkAJfF2DKnZKQZIDzNMwcDwFtDZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T11:01:46.684803Z"},"content_sha256":"b178ead9524a98090d40fb5d53ca411a74e0fb43684205afd4818bd524d13811","schema_version":"1.0","event_id":"sha256:b178ead9524a98090d40fb5d53ca411a74e0fb43684205afd4818bd524d13811"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5TUTNO2Z7LCBZIBH5KNE4NXEHC/bundle.json","state_url":"https://pith.science/pith/5TUTNO2Z7LCBZIBH5KNE4NXEHC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5TUTNO2Z7LCBZIBH5KNE4NXEHC/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":"2026-06-26T11:01:46Z","links":{"resolver":"https://pith.science/pith/5TUTNO2Z7LCBZIBH5KNE4NXEHC","bundle":"https://pith.science/pith/5TUTNO2Z7LCBZIBH5KNE4NXEHC/bundle.json","state":"https://pith.science/pith/5TUTNO2Z7LCBZIBH5KNE4NXEHC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5TUTNO2Z7LCBZIBH5KNE4NXEHC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5TUTNO2Z7LCBZIBH5KNE4NXEHC","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":"5de81e90ebff83f652efb616416e8a1da5868483c8ca8404820876bfa5c828fe","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-30T23:35:30Z","title_canon_sha256":"3feb0b20be10e283f6824a3e261ecfde267d686b2fc0578e6076bd58b5d34bbd"},"schema_version":"1.0","source":{"id":"1905.00135","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.00135","created_at":"2026-05-17T23:41:36Z"},{"alias_kind":"arxiv_version","alias_value":"1905.00135v1","created_at":"2026-05-17T23:41:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00135","created_at":"2026-05-17T23:41:36Z"},{"alias_kind":"pith_short_12","alias_value":"5TUTNO2Z7LCB","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5TUTNO2Z7LCBZIBH","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5TUTNO2Z","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:b178ead9524a98090d40fb5d53ca411a74e0fb43684205afd4818bd524d13811","target":"graph","created_at":"2026-05-17T23:41:36Z","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":"Convolutional neural networks (CNNs) are very popular nowadays for image processing. CNNs allow one to learn optimal filters in a (mostly) supervised machine learning context. However this typically requires abundant labelled training data to estimate the filter parameters. Alternative strategies have been deployed for reducing the number of parameters and / or filters to be learned and thus decrease overfitting. In the context of reverting to preset filters, we propose here a computationally efficient harmonic block that uses Discrete Cosine Transform (DCT) filters in CNNs. In this work we ex","authors_text":"Matej Ulicny, Rozenn Dahyot, Vladimir A. Krylov","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-30T23:35:30Z","title":"Harmonic Networks with Limited Training Samples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00135","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:d199d4f0c988001794e63eac54558c16d50168d6d08f19efce0fd83433c1aea4","target":"record","created_at":"2026-05-17T23:41:36Z","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":"5de81e90ebff83f652efb616416e8a1da5868483c8ca8404820876bfa5c828fe","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-30T23:35:30Z","title_canon_sha256":"3feb0b20be10e283f6824a3e261ecfde267d686b2fc0578e6076bd58b5d34bbd"},"schema_version":"1.0","source":{"id":"1905.00135","kind":"arxiv","version":1}},"canonical_sha256":"ece936bb59fac41ca027ea9a4e36e438a9d35d1889d2eb190034540ea68e98bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ece936bb59fac41ca027ea9a4e36e438a9d35d1889d2eb190034540ea68e98bd","first_computed_at":"2026-05-17T23:41:36.324568Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:36.324568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tvQy9kgF5XwKwHbCHPOHE0Ak+sFwhPWvgkZ1vpHgYuSoqX5VxHsV+cyL5e03M0RjBJWKFFVlw6S8RcvR46k9DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:36.325064Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.00135","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d199d4f0c988001794e63eac54558c16d50168d6d08f19efce0fd83433c1aea4","sha256:b178ead9524a98090d40fb5d53ca411a74e0fb43684205afd4818bd524d13811"],"state_sha256":"25ad8e1749a32930fb627742d383b049090bee15e560d4f8eaa4275a26942bc3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BqXgE2clcCwFtrN3lT9AOJyCMnRdzxiGEjeH+gxppr7X/ezbssa1+wgBHnCWBRcR7bTZmYFZx9sEWiFMWFBkAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T11:01:46.686725Z","bundle_sha256":"ebedd95d10414dc1142fb317a118882c6cae8b89b2e14560f49244de6bdf53e1"}}