{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:A7BCCCKXUCPSLVFKTINCPXKJIN","short_pith_number":"pith:A7BCCCKX","schema_version":"1.0","canonical_sha256":"07c2210957a09f25d4aa9a1a27dd49437b49e7c490a8e684cf6756e7f3bd4ac5","source":{"kind":"arxiv","id":"1807.04734","version":1},"attestation_state":"computed","paper":{"title":"Scalable Convolutional Dictionary Learning with Constrained Recurrent Sparse Auto-encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bahareh Tolooshams, Demba Ba, Sourav Dey","submitted_at":"2018-07-12T17:18:37Z","abstract_excerpt":"Given a convolutional dictionary underlying a set of observed signals, can a carefully designed auto-encoder recover the dictionary in the presence of noise? We introduce an auto-encoder architecture, termed constrained recurrent sparse auto-encoder (CRsAE), that answers this question in the affirmative. Given an input signal and an approximate dictionary, the encoder finds a sparse approximation using FISTA. The decoder reconstructs the signal by applying the dictionary to the output of the encoder. The encoder and decoder in CRsAE parallel the sparse-coding and dictionary update steps in opt"},"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":"1807.04734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-12T17:18:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"468fd117a4b30aa3a4c50d6c8194923da67d3a1882edca1731d49e6c06705979","abstract_canon_sha256":"ad08673f64f01db6fc802de49a0194c065585a6c5b06208c991cd00229950fe0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:52.662277Z","signature_b64":"ZejnTebjd4dBWGX6zOE0wt92fjluuSpGokU6SPWpIfrFvsItZPsDTYxzowRh7QJJ3CMcgcR9RLxFCkjXRbEoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07c2210957a09f25d4aa9a1a27dd49437b49e7c490a8e684cf6756e7f3bd4ac5","last_reissued_at":"2026-05-18T00:10:52.661567Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:52.661567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Convolutional Dictionary Learning with Constrained Recurrent Sparse Auto-encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bahareh Tolooshams, Demba Ba, Sourav Dey","submitted_at":"2018-07-12T17:18:37Z","abstract_excerpt":"Given a convolutional dictionary underlying a set of observed signals, can a carefully designed auto-encoder recover the dictionary in the presence of noise? We introduce an auto-encoder architecture, termed constrained recurrent sparse auto-encoder (CRsAE), that answers this question in the affirmative. Given an input signal and an approximate dictionary, the encoder finds a sparse approximation using FISTA. The decoder reconstructs the signal by applying the dictionary to the output of the encoder. The encoder and decoder in CRsAE parallel the sparse-coding and dictionary update steps in opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.04734","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1807.04734","created_at":"2026-05-18T00:10:52.661690+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.04734v1","created_at":"2026-05-18T00:10:52.661690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.04734","created_at":"2026-05-18T00:10:52.661690+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7BCCCKXUCPS","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7BCCCKXUCPSLVFK","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7BCCCKX","created_at":"2026-05-18T12:32:13.499390+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/A7BCCCKXUCPSLVFKTINCPXKJIN","json":"https://pith.science/pith/A7BCCCKXUCPSLVFKTINCPXKJIN.json","graph_json":"https://pith.science/api/pith-number/A7BCCCKXUCPSLVFKTINCPXKJIN/graph.json","events_json":"https://pith.science/api/pith-number/A7BCCCKXUCPSLVFKTINCPXKJIN/events.json","paper":"https://pith.science/paper/A7BCCCKX"},"agent_actions":{"view_html":"https://pith.science/pith/A7BCCCKXUCPSLVFKTINCPXKJIN","download_json":"https://pith.science/pith/A7BCCCKXUCPSLVFKTINCPXKJIN.json","view_paper":"https://pith.science/paper/A7BCCCKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.04734&json=true","fetch_graph":"https://pith.science/api/pith-number/A7BCCCKXUCPSLVFKTINCPXKJIN/graph.json","fetch_events":"https://pith.science/api/pith-number/A7BCCCKXUCPSLVFKTINCPXKJIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7BCCCKXUCPSLVFKTINCPXKJIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7BCCCKXUCPSLVFKTINCPXKJIN/action/storage_attestation","attest_author":"https://pith.science/pith/A7BCCCKXUCPSLVFKTINCPXKJIN/action/author_attestation","sign_citation":"https://pith.science/pith/A7BCCCKXUCPSLVFKTINCPXKJIN/action/citation_signature","submit_replication":"https://pith.science/pith/A7BCCCKXUCPSLVFKTINCPXKJIN/action/replication_record"}},"created_at":"2026-05-18T00:10:52.661690+00:00","updated_at":"2026-05-18T00:10:52.661690+00:00"}