{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OWZ6K73CWPCQNXNVWVTOEMLSBY","short_pith_number":"pith:OWZ6K73C","schema_version":"1.0","canonical_sha256":"75b3e57f62b3c506ddb5b566e231720e11896190dba3a51e870172435c2ae3b7","source":{"kind":"arxiv","id":"1902.09701","version":2},"attestation_state":"computed","paper":{"title":"Learning Implicitly Recurrent CNNs Through Parameter Sharing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Michael Maire, Pedro Savarese","submitted_at":"2019-02-26T02:02:09Z","abstract_excerpt":"We introduce a parameter sharing scheme, in which different layers of a convolutional neural network (CNN) are defined by a learned linear combination of parameter tensors from a global bank of templates. Restricting the number of templates yields a flexible hybridization of traditional CNNs and recurrent networks. Compared to traditional CNNs, we demonstrate substantial parameter savings on standard image classification tasks, while maintaining accuracy.\n  Our simple parameter sharing scheme, though defined via soft weights, in practice often yields trained networks with near strict recurrent"},"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":"1902.09701","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-26T02:02:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"530e328aae219b944615cdddc3611af455ec7a026988d1196322659d19d4091b","abstract_canon_sha256":"074ff8e6f683e43ca2e3b36f152c7a374472302db751e0284995a2e60b9f307b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:19.026511Z","signature_b64":"UPGd7iLa/yONXLXMaLSgUPeSKiIdPOEhyS6Hyk47GSQPUSZOzkr8FIemUzjpyIDxMwnnGusEpR3TN7NjmSfXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75b3e57f62b3c506ddb5b566e231720e11896190dba3a51e870172435c2ae3b7","last_reissued_at":"2026-05-17T23:51:19.025960Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:19.025960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Implicitly Recurrent CNNs Through Parameter Sharing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Michael Maire, Pedro Savarese","submitted_at":"2019-02-26T02:02:09Z","abstract_excerpt":"We introduce a parameter sharing scheme, in which different layers of a convolutional neural network (CNN) are defined by a learned linear combination of parameter tensors from a global bank of templates. Restricting the number of templates yields a flexible hybridization of traditional CNNs and recurrent networks. Compared to traditional CNNs, we demonstrate substantial parameter savings on standard image classification tasks, while maintaining accuracy.\n  Our simple parameter sharing scheme, though defined via soft weights, in practice often yields trained networks with near strict recurrent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09701","kind":"arxiv","version":2},"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":"1902.09701","created_at":"2026-05-17T23:51:19.026046+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.09701v2","created_at":"2026-05-17T23:51:19.026046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09701","created_at":"2026-05-17T23:51:19.026046+00:00"},{"alias_kind":"pith_short_12","alias_value":"OWZ6K73CWPCQ","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"OWZ6K73CWPCQNXNV","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"OWZ6K73C","created_at":"2026-05-18T12:33:24.271573+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/OWZ6K73CWPCQNXNVWVTOEMLSBY","json":"https://pith.science/pith/OWZ6K73CWPCQNXNVWVTOEMLSBY.json","graph_json":"https://pith.science/api/pith-number/OWZ6K73CWPCQNXNVWVTOEMLSBY/graph.json","events_json":"https://pith.science/api/pith-number/OWZ6K73CWPCQNXNVWVTOEMLSBY/events.json","paper":"https://pith.science/paper/OWZ6K73C"},"agent_actions":{"view_html":"https://pith.science/pith/OWZ6K73CWPCQNXNVWVTOEMLSBY","download_json":"https://pith.science/pith/OWZ6K73CWPCQNXNVWVTOEMLSBY.json","view_paper":"https://pith.science/paper/OWZ6K73C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.09701&json=true","fetch_graph":"https://pith.science/api/pith-number/OWZ6K73CWPCQNXNVWVTOEMLSBY/graph.json","fetch_events":"https://pith.science/api/pith-number/OWZ6K73CWPCQNXNVWVTOEMLSBY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OWZ6K73CWPCQNXNVWVTOEMLSBY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OWZ6K73CWPCQNXNVWVTOEMLSBY/action/storage_attestation","attest_author":"https://pith.science/pith/OWZ6K73CWPCQNXNVWVTOEMLSBY/action/author_attestation","sign_citation":"https://pith.science/pith/OWZ6K73CWPCQNXNVWVTOEMLSBY/action/citation_signature","submit_replication":"https://pith.science/pith/OWZ6K73CWPCQNXNVWVTOEMLSBY/action/replication_record"}},"created_at":"2026-05-17T23:51:19.026046+00:00","updated_at":"2026-05-17T23:51:19.026046+00:00"}