{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ISKD6SWL7V3XKGNIH4XGLKS3RH","short_pith_number":"pith:ISKD6SWL","canonical_record":{"source":{"id":"1904.08827","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-18T15:08:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7a902795b5e59bfa79565111c686f8ca5c4da45b35e96d30cb593b839431782e","abstract_canon_sha256":"04934a3d0974692ae872a1ef3f59076525ee930d35ece2e11ccbd12cabc4def3"},"schema_version":"1.0"},"canonical_sha256":"44943f4acbfd777519a83f2e65aa5b89ff1ff4811863066a8d703d0df5c6e54e","source":{"kind":"arxiv","id":"1904.08827","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.08827","created_at":"2026-07-05T01:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"1904.08827v3","created_at":"2026-07-05T01:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08827","created_at":"2026-07-05T01:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"ISKD6SWL7V3X","created_at":"2026-07-05T01:43:54Z"},{"alias_kind":"pith_short_16","alias_value":"ISKD6SWL7V3XKGNI","created_at":"2026-07-05T01:43:54Z"},{"alias_kind":"pith_short_8","alias_value":"ISKD6SWL","created_at":"2026-07-05T01:43:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ISKD6SWL7V3XKGNIH4XGLKS3RH","target":"record","payload":{"canonical_record":{"source":{"id":"1904.08827","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-18T15:08:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7a902795b5e59bfa79565111c686f8ca5c4da45b35e96d30cb593b839431782e","abstract_canon_sha256":"04934a3d0974692ae872a1ef3f59076525ee930d35ece2e11ccbd12cabc4def3"},"schema_version":"1.0"},"canonical_sha256":"44943f4acbfd777519a83f2e65aa5b89ff1ff4811863066a8d703d0df5c6e54e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:54.438473Z","signature_b64":"NiawBpRTq3lSkwcdPEWj5Uj1TgBx1eE3kcza2z+lJgDB9NrfjSiOpRJWfZygQETHaGCa1drlNzL4XKYeZx7nBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44943f4acbfd777519a83f2e65aa5b89ff1ff4811863066a8d703d0df5c6e54e","last_reissued_at":"2026-07-05T01:43:54.438079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:54.438079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.08827","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:43:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nXw65S5nk7UTb0pCe8GURH503fcJA23LVEZXBq9VPZpMEFIxdzC/0xaHWv4CqzWijyt8amMRhoNUP/C3wP6xCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:40:38.025216Z"},"content_sha256":"deaabeaa88c78f1632091ebf7d16fd393a9bcb7db7819c2c6ef546eb5e62b26a","schema_version":"1.0","event_id":"sha256:deaabeaa88c78f1632091ebf7d16fd393a9bcb7db7819c2c6ef546eb5e62b26a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ISKD6SWL7V3XKGNIH4XGLKS3RH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Residual Autoencoders for Expectation Maximization-inspired Dictionary Learning","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":"2019-04-18T15:08:10Z","abstract_excerpt":"We introduce a neural-network architecture, termed the constrained recurrent sparse autoencoder (CRsAE), that solves convolutional dictionary learning problems, thus establishing a link between dictionary learning and neural networks. Specifically, we leverage the interpretation of the alternating-minimization algorithm for dictionary learning as an approximate Expectation-Maximization algorithm to develop autoencoders that enable the simultaneous training of the dictionary and regularization parameter (ReLU bias). The forward pass of the encoder approximates the sufficient statistics of the E"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08827","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/1904.08827/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:43:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nYPCI4x7FVPxSS9Q6IzZvfQdjUtHqi/CIedOp7OYUatsusjsOxK2hMi3awqqToPYgJJi3GMjfnzlj5LU3bC9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:40:38.102865Z"},"content_sha256":"f774f05e5da38a7db06c5b2cb56fb09ced6ae41ec2c58ffaacc8f4d0ceea77f2","schema_version":"1.0","event_id":"sha256:f774f05e5da38a7db06c5b2cb56fb09ced6ae41ec2c58ffaacc8f4d0ceea77f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ISKD6SWL7V3XKGNIH4XGLKS3RH/bundle.json","state_url":"https://pith.science/pith/ISKD6SWL7V3XKGNIH4XGLKS3RH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ISKD6SWL7V3XKGNIH4XGLKS3RH/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":"2026-08-17T21:40:38Z","links":{"resolver":"https://pith.science/pith/ISKD6SWL7V3XKGNIH4XGLKS3RH","bundle":"https://pith.science/pith/ISKD6SWL7V3XKGNIH4XGLKS3RH/bundle.json","state":"https://pith.science/pith/ISKD6SWL7V3XKGNIH4XGLKS3RH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ISKD6SWL7V3XKGNIH4XGLKS3RH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ISKD6SWL7V3XKGNIH4XGLKS3RH","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":"04934a3d0974692ae872a1ef3f59076525ee930d35ece2e11ccbd12cabc4def3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-18T15:08:10Z","title_canon_sha256":"7a902795b5e59bfa79565111c686f8ca5c4da45b35e96d30cb593b839431782e"},"schema_version":"1.0","source":{"id":"1904.08827","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.08827","created_at":"2026-07-05T01:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"1904.08827v3","created_at":"2026-07-05T01:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08827","created_at":"2026-07-05T01:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"ISKD6SWL7V3X","created_at":"2026-07-05T01:43:54Z"},{"alias_kind":"pith_short_16","alias_value":"ISKD6SWL7V3XKGNI","created_at":"2026-07-05T01:43:54Z"},{"alias_kind":"pith_short_8","alias_value":"ISKD6SWL","created_at":"2026-07-05T01:43:54Z"}],"graph_snapshots":[{"event_id":"sha256:f774f05e5da38a7db06c5b2cb56fb09ced6ae41ec2c58ffaacc8f4d0ceea77f2","target":"graph","created_at":"2026-07-05T01:43:54Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1904.08827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a neural-network architecture, termed the constrained recurrent sparse autoencoder (CRsAE), that solves convolutional dictionary learning problems, thus establishing a link between dictionary learning and neural networks. Specifically, we leverage the interpretation of the alternating-minimization algorithm for dictionary learning as an approximate Expectation-Maximization algorithm to develop autoencoders that enable the simultaneous training of the dictionary and regularization parameter (ReLU bias). The forward pass of the encoder approximates the sufficient statistics of the E","authors_text":"Bahareh Tolooshams, Demba Ba, Sourav Dey","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-18T15:08:10Z","title":"Deep Residual Autoencoders for Expectation Maximization-inspired Dictionary Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08827","kind":"arxiv","version":3},"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:deaabeaa88c78f1632091ebf7d16fd393a9bcb7db7819c2c6ef546eb5e62b26a","target":"record","created_at":"2026-07-05T01:43:54Z","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":"04934a3d0974692ae872a1ef3f59076525ee930d35ece2e11ccbd12cabc4def3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-18T15:08:10Z","title_canon_sha256":"7a902795b5e59bfa79565111c686f8ca5c4da45b35e96d30cb593b839431782e"},"schema_version":"1.0","source":{"id":"1904.08827","kind":"arxiv","version":3}},"canonical_sha256":"44943f4acbfd777519a83f2e65aa5b89ff1ff4811863066a8d703d0df5c6e54e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44943f4acbfd777519a83f2e65aa5b89ff1ff4811863066a8d703d0df5c6e54e","first_computed_at":"2026-07-05T01:43:54.438079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:43:54.438079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NiawBpRTq3lSkwcdPEWj5Uj1TgBx1eE3kcza2z+lJgDB9NrfjSiOpRJWfZygQETHaGCa1drlNzL4XKYeZx7nBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:43:54.438473Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.08827","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:deaabeaa88c78f1632091ebf7d16fd393a9bcb7db7819c2c6ef546eb5e62b26a","sha256:f774f05e5da38a7db06c5b2cb56fb09ced6ae41ec2c58ffaacc8f4d0ceea77f2"],"state_sha256":"336b95e227f9658d166151a9fc5deca859498aede676654be3c2add2ee9034ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"asTWUkYiHTI3tRcYcV7RZX1v3pDyysOXT1sgU8r00Ri1RBuKA/fiagZome2dSjXuKEu1Z3Vi0ECVjVzhuCgsDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T21:40:38.343095Z","bundle_sha256":"93df5e16a94bc30c675c7d2ebc65664ac8e03ef0e436e4b09cb4d6a63473a223"}}