{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:O2DG4BGDRPOMUZX3EV7BE4YHKZ","short_pith_number":"pith:O2DG4BGD","schema_version":"1.0","canonical_sha256":"76866e04c38bdcca66fb257e127307566204cc13523619d544de85690b8237af","source":{"kind":"arxiv","id":"1503.03438","version":3},"attestation_state":"computed","paper":{"title":"A mathematical motivation for complex-valued convolutional networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Szlam, Joan Bruna, Mark Tygert, Serkan Piantino, Soumith Chintala, Yann LeCun","submitted_at":"2015-03-11T18:24:13Z","abstract_excerpt":"A complex-valued convolutional network (convnet) implements the repeated application of the following composition of three operations, recursively applying the composition to an input vector of nonnegative real numbers: (1) convolution with complex-valued vectors followed by (2) taking the absolute value of every entry of the resulting vectors followed by (3) local averaging. For processing real-valued random vectors, complex-valued convnets can be viewed as \"data-driven multiscale windowed power spectra,\" \"data-driven multiscale windowed absolute spectra,\" \"data-driven multiwavelet absolute v"},"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":"1503.03438","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-11T18:24:13Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"4b87ff162c86b27bd7b97cd3fe5163040d6271c7e51d0cf5d1779038d08df7f9","abstract_canon_sha256":"ab1a040612de674ac49dcbbce709b0c116710d983cc89c40bb9e19f7578b7ad3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:53.077981Z","signature_b64":"Eq6A7nrM3S0co7pn8JLKUNgXl8Mp1LX1orCeVKnNHnjtGWPyXPH7hm0JDcpG6+z7ZxpZAtubDL8lJJEaU3/7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76866e04c38bdcca66fb257e127307566204cc13523619d544de85690b8237af","last_reissued_at":"2026-05-18T01:15:53.077517Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:53.077517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A mathematical motivation for complex-valued convolutional networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Szlam, Joan Bruna, Mark Tygert, Serkan Piantino, Soumith Chintala, Yann LeCun","submitted_at":"2015-03-11T18:24:13Z","abstract_excerpt":"A complex-valued convolutional network (convnet) implements the repeated application of the following composition of three operations, recursively applying the composition to an input vector of nonnegative real numbers: (1) convolution with complex-valued vectors followed by (2) taking the absolute value of every entry of the resulting vectors followed by (3) local averaging. For processing real-valued random vectors, complex-valued convnets can be viewed as \"data-driven multiscale windowed power spectra,\" \"data-driven multiscale windowed absolute spectra,\" \"data-driven multiwavelet absolute v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.03438","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":""},"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":"1503.03438","created_at":"2026-05-18T01:15:53.077602+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.03438v3","created_at":"2026-05-18T01:15:53.077602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.03438","created_at":"2026-05-18T01:15:53.077602+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2DG4BGDRPOM","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2DG4BGDRPOMUZX3","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2DG4BGD","created_at":"2026-05-18T12:29:34.919912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.05377","citing_title":"Resonant Machine Learning Based on Complex Growth Transform Dynamical Systems","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2DG4BGDRPOMUZX3EV7BE4YHKZ","json":"https://pith.science/pith/O2DG4BGDRPOMUZX3EV7BE4YHKZ.json","graph_json":"https://pith.science/api/pith-number/O2DG4BGDRPOMUZX3EV7BE4YHKZ/graph.json","events_json":"https://pith.science/api/pith-number/O2DG4BGDRPOMUZX3EV7BE4YHKZ/events.json","paper":"https://pith.science/paper/O2DG4BGD"},"agent_actions":{"view_html":"https://pith.science/pith/O2DG4BGDRPOMUZX3EV7BE4YHKZ","download_json":"https://pith.science/pith/O2DG4BGDRPOMUZX3EV7BE4YHKZ.json","view_paper":"https://pith.science/paper/O2DG4BGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.03438&json=true","fetch_graph":"https://pith.science/api/pith-number/O2DG4BGDRPOMUZX3EV7BE4YHKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/O2DG4BGDRPOMUZX3EV7BE4YHKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2DG4BGDRPOMUZX3EV7BE4YHKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2DG4BGDRPOMUZX3EV7BE4YHKZ/action/storage_attestation","attest_author":"https://pith.science/pith/O2DG4BGDRPOMUZX3EV7BE4YHKZ/action/author_attestation","sign_citation":"https://pith.science/pith/O2DG4BGDRPOMUZX3EV7BE4YHKZ/action/citation_signature","submit_replication":"https://pith.science/pith/O2DG4BGDRPOMUZX3EV7BE4YHKZ/action/replication_record"}},"created_at":"2026-05-18T01:15:53.077602+00:00","updated_at":"2026-05-18T01:15:53.077602+00:00"}