{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4ZRPGA5ZECDAQ3RQFMPZ6OSWM6","short_pith_number":"pith:4ZRPGA5Z","schema_version":"1.0","canonical_sha256":"e662f303b92086086e302b1f9f3a56678d83bdf8f20727ffdf2c6927b7e1fcec","source":{"kind":"arxiv","id":"1910.03561","version":3},"attestation_state":"computed","paper":{"title":"Deep Network Classification by Scattering and Homotopy Dictionary Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"John Zarka, Louis Thiry, St\\'ephane Mallat, Tom\\'as Angles","submitted_at":"2019-10-08T17:47:44Z","abstract_excerpt":"We introduce a sparse scattering deep convolutional neural network, which provides a simple model to analyze properties of deep representation learning for classification. Learning a single dictionary matrix with a classifier yields a higher classification accuracy than AlexNet over the ImageNet 2012 dataset. The network first applies a scattering transform that linearizes variabilities due to geometric transformations such as translations and small deformations. A sparse $\\ell^1$ dictionary coding reduces intra-class variability while preserving class separation through projections over union"},"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":"1910.03561","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-08T17:47:44Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"3dedc17da9d9ecac200553c68fa848488810e4f90b01c3008b903f412e737b63","abstract_canon_sha256":"01628c9dace604090c5970b8352776d8d860309523214cdc8fa201e6cf69bb4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:32.526287Z","signature_b64":"0WNOwr4YibGGW0Krikd6QJXnY+7sblIx/S5g0RXRRSewSdikQ+Nox4rWN9qJV1pxhYd7WKE9IGLTzir2iisOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e662f303b92086086e302b1f9f3a56678d83bdf8f20727ffdf2c6927b7e1fcec","last_reissued_at":"2026-07-05T00:42:32.525797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:32.525797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Network Classification by Scattering and Homotopy Dictionary Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"John Zarka, Louis Thiry, St\\'ephane Mallat, Tom\\'as Angles","submitted_at":"2019-10-08T17:47:44Z","abstract_excerpt":"We introduce a sparse scattering deep convolutional neural network, which provides a simple model to analyze properties of deep representation learning for classification. Learning a single dictionary matrix with a classifier yields a higher classification accuracy than AlexNet over the ImageNet 2012 dataset. The network first applies a scattering transform that linearizes variabilities due to geometric transformations such as translations and small deformations. A sparse $\\ell^1$ dictionary coding reduces intra-class variability while preserving class separation through projections over union"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.03561","kind":"arxiv","version":3},"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/1910.03561/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":"1910.03561","created_at":"2026-07-05T00:42:32.525858+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.03561v3","created_at":"2026-07-05T00:42:32.525858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.03561","created_at":"2026-07-05T00:42:32.525858+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZRPGA5ZECDA","created_at":"2026-07-05T00:42:32.525858+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZRPGA5ZECDAQ3RQ","created_at":"2026-07-05T00:42:32.525858+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZRPGA5Z","created_at":"2026-07-05T00:42:32.525858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZRPGA5ZECDAQ3RQFMPZ6OSWM6","json":"https://pith.science/pith/4ZRPGA5ZECDAQ3RQFMPZ6OSWM6.json","graph_json":"https://pith.science/api/pith-number/4ZRPGA5ZECDAQ3RQFMPZ6OSWM6/graph.json","events_json":"https://pith.science/api/pith-number/4ZRPGA5ZECDAQ3RQFMPZ6OSWM6/events.json","paper":"https://pith.science/paper/4ZRPGA5Z"},"agent_actions":{"view_html":"https://pith.science/pith/4ZRPGA5ZECDAQ3RQFMPZ6OSWM6","download_json":"https://pith.science/pith/4ZRPGA5ZECDAQ3RQFMPZ6OSWM6.json","view_paper":"https://pith.science/paper/4ZRPGA5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.03561&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZRPGA5ZECDAQ3RQFMPZ6OSWM6/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZRPGA5ZECDAQ3RQFMPZ6OSWM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZRPGA5ZECDAQ3RQFMPZ6OSWM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZRPGA5ZECDAQ3RQFMPZ6OSWM6/action/storage_attestation","attest_author":"https://pith.science/pith/4ZRPGA5ZECDAQ3RQFMPZ6OSWM6/action/author_attestation","sign_citation":"https://pith.science/pith/4ZRPGA5ZECDAQ3RQFMPZ6OSWM6/action/citation_signature","submit_replication":"https://pith.science/pith/4ZRPGA5ZECDAQ3RQFMPZ6OSWM6/action/replication_record"}},"created_at":"2026-07-05T00:42:32.525858+00:00","updated_at":"2026-07-05T00:42:32.525858+00:00"}