{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TLXDL6O3HMNW25P5YF4SEF6ZFP","short_pith_number":"pith:TLXDL6O3","schema_version":"1.0","canonical_sha256":"9aee35f9db3b1b6d75fdc1792217d92bff444babafc14bde9412964501f8171b","source":{"kind":"arxiv","id":"2012.04926","version":1},"attestation_state":"computed","paper":{"title":"Improving Gradient Flow with Unrolled Highway Expectation Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Chonghyuk Song, Eunseok Kim, Inwook Shim","submitted_at":"2020-12-09T09:11:45Z","abstract_excerpt":"Integrating model-based machine learning methods into deep neural architectures allows one to leverage both the expressive power of deep neural nets and the ability of model-based methods to incorporate domain-specific knowledge. In particular, many works have employed the expectation maximization (EM) algorithm in the form of an unrolled layer-wise structure that is jointly trained with a backbone neural network. However, it is difficult to discriminatively train the backbone network by backpropagating through the EM iterations as they are prone to the vanishing gradient problem. To address t"},"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":"2012.04926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-09T09:11:45Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"6f5d9fe2132ef2cb4ca98f59207cd7fd53507590db65a74ba5288b2bf6553a12","abstract_canon_sha256":"8a80e27bbe32941b525b4aae1298433c58f1ef7007acd0543df8d53e78833cbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:16.630884Z","signature_b64":"SzDHXgf3DTWduB6tW8580PZhCixctgJ39kzu58QiwRl/xj7gTH82nbmDnXxSJHowQ4C2NbigZK9HAZbABN0rDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9aee35f9db3b1b6d75fdc1792217d92bff444babafc14bde9412964501f8171b","last_reissued_at":"2026-07-05T01:58:16.630545Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:16.630545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Gradient Flow with Unrolled Highway Expectation Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Chonghyuk Song, Eunseok Kim, Inwook Shim","submitted_at":"2020-12-09T09:11:45Z","abstract_excerpt":"Integrating model-based machine learning methods into deep neural architectures allows one to leverage both the expressive power of deep neural nets and the ability of model-based methods to incorporate domain-specific knowledge. In particular, many works have employed the expectation maximization (EM) algorithm in the form of an unrolled layer-wise structure that is jointly trained with a backbone neural network. However, it is difficult to discriminatively train the backbone network by backpropagating through the EM iterations as they are prone to the vanishing gradient problem. To address t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04926","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.04926/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":"2012.04926","created_at":"2026-07-05T01:58:16.630601+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.04926v1","created_at":"2026-07-05T01:58:16.630601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04926","created_at":"2026-07-05T01:58:16.630601+00:00"},{"alias_kind":"pith_short_12","alias_value":"TLXDL6O3HMNW","created_at":"2026-07-05T01:58:16.630601+00:00"},{"alias_kind":"pith_short_16","alias_value":"TLXDL6O3HMNW25P5","created_at":"2026-07-05T01:58:16.630601+00:00"},{"alias_kind":"pith_short_8","alias_value":"TLXDL6O3","created_at":"2026-07-05T01:58:16.630601+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/TLXDL6O3HMNW25P5YF4SEF6ZFP","json":"https://pith.science/pith/TLXDL6O3HMNW25P5YF4SEF6ZFP.json","graph_json":"https://pith.science/api/pith-number/TLXDL6O3HMNW25P5YF4SEF6ZFP/graph.json","events_json":"https://pith.science/api/pith-number/TLXDL6O3HMNW25P5YF4SEF6ZFP/events.json","paper":"https://pith.science/paper/TLXDL6O3"},"agent_actions":{"view_html":"https://pith.science/pith/TLXDL6O3HMNW25P5YF4SEF6ZFP","download_json":"https://pith.science/pith/TLXDL6O3HMNW25P5YF4SEF6ZFP.json","view_paper":"https://pith.science/paper/TLXDL6O3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.04926&json=true","fetch_graph":"https://pith.science/api/pith-number/TLXDL6O3HMNW25P5YF4SEF6ZFP/graph.json","fetch_events":"https://pith.science/api/pith-number/TLXDL6O3HMNW25P5YF4SEF6ZFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TLXDL6O3HMNW25P5YF4SEF6ZFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TLXDL6O3HMNW25P5YF4SEF6ZFP/action/storage_attestation","attest_author":"https://pith.science/pith/TLXDL6O3HMNW25P5YF4SEF6ZFP/action/author_attestation","sign_citation":"https://pith.science/pith/TLXDL6O3HMNW25P5YF4SEF6ZFP/action/citation_signature","submit_replication":"https://pith.science/pith/TLXDL6O3HMNW25P5YF4SEF6ZFP/action/replication_record"}},"created_at":"2026-07-05T01:58:16.630601+00:00","updated_at":"2026-07-05T01:58:16.630601+00:00"}