{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TA6LAEHYI7AJNHLDVFXDJV5PRA","short_pith_number":"pith:TA6LAEHY","canonical_record":{"source":{"id":"2106.16057","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-30T13:32:23Z","cross_cats_sorted":[],"title_canon_sha256":"ba886c1fb3fd260629560728b68c172f1da2dc73c809ea0fb32f8ed3ab7f1769","abstract_canon_sha256":"01517b934392feb57399e80589db36fab27340076f2f9fb44b2eb1263455d73c"},"schema_version":"1.0"},"canonical_sha256":"983cb010f847c0969d63a96e34d7af8828c3cd4cd2714df22fe2aa710dc08b1e","source":{"kind":"arxiv","id":"2106.16057","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.16057","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"arxiv_version","alias_value":"2106.16057v1","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.16057","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"pith_short_12","alias_value":"TA6LAEHYI7AJ","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"pith_short_16","alias_value":"TA6LAEHYI7AJNHLD","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"pith_short_8","alias_value":"TA6LAEHY","created_at":"2026-07-05T02:54:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TA6LAEHYI7AJNHLDVFXDJV5PRA","target":"record","payload":{"canonical_record":{"source":{"id":"2106.16057","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-30T13:32:23Z","cross_cats_sorted":[],"title_canon_sha256":"ba886c1fb3fd260629560728b68c172f1da2dc73c809ea0fb32f8ed3ab7f1769","abstract_canon_sha256":"01517b934392feb57399e80589db36fab27340076f2f9fb44b2eb1263455d73c"},"schema_version":"1.0"},"canonical_sha256":"983cb010f847c0969d63a96e34d7af8828c3cd4cd2714df22fe2aa710dc08b1e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:02.986614Z","signature_b64":"zzIO42XD4KEI1iWqfndwYLgFcvLwEhxWSqncx9+qRz8zwzp9yqx1RBQeyfCYXwANHF1EAluAexp/HYOXnbcdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"983cb010f847c0969d63a96e34d7af8828c3cd4cd2714df22fe2aa710dc08b1e","last_reissued_at":"2026-07-05T02:54:02.986183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:02.986183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.16057","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:54:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZfdajrBczZCzob9rbT+Wn/eTE0RyEDwAf0O1S2ZMk+jbyw+uJSFa0tkGIgWx/P1WsnzxYnB+kbwjr1yG9BWFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:29:23.790232Z"},"content_sha256":"bc250fb27a5e99e1425c9bba494964d323079086ce36dba6fcb1d1e1d5f603f9","schema_version":"1.0","event_id":"sha256:bc250fb27a5e99e1425c9bba494964d323079086ce36dba6fcb1d1e1d5f603f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TA6LAEHYI7AJNHLDVFXDJV5PRA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DAEMA: Denoising Autoencoder with Mask Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Damien Fourure, Muhammad Usama Javaid, Nicolas Posocco, Simon Tihon, Thomas Peel","submitted_at":"2021-06-30T13:32:23Z","abstract_excerpt":"Missing data is a recurrent and challenging problem, especially when using machine learning algorithms for real-world applications. For this reason, missing data imputation has become an active research area, in which recent deep learning approaches have achieved state-of-the-art results. We propose DAEMA (Denoising Autoencoder with Mask Attention), an algorithm based on a denoising autoencoder architecture with an attention mechanism. While most imputation algorithms use incomplete inputs as they would use complete data - up to basic preprocessing (e.g. mean imputation) - DAEMA leverages a ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.16057","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/2106.16057/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":"2026-07-05T02:54:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bxgfk1v22mh2Kp77PCYewQttT3lpczejhcvgsVzZWenBapfdjAZiS2kpbnnRTyQ3vl+baRms4coKT6ZqN9L0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:29:23.790768Z"},"content_sha256":"82b59bdbfbc8b3f47dbf7afcd46504914fd04ff665357db1a698c95d20a39588","schema_version":"1.0","event_id":"sha256:82b59bdbfbc8b3f47dbf7afcd46504914fd04ff665357db1a698c95d20a39588"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TA6LAEHYI7AJNHLDVFXDJV5PRA/bundle.json","state_url":"https://pith.science/pith/TA6LAEHYI7AJNHLDVFXDJV5PRA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TA6LAEHYI7AJNHLDVFXDJV5PRA/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":"2026-08-14T09:29:23Z","links":{"resolver":"https://pith.science/pith/TA6LAEHYI7AJNHLDVFXDJV5PRA","bundle":"https://pith.science/pith/TA6LAEHYI7AJNHLDVFXDJV5PRA/bundle.json","state":"https://pith.science/pith/TA6LAEHYI7AJNHLDVFXDJV5PRA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TA6LAEHYI7AJNHLDVFXDJV5PRA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TA6LAEHYI7AJNHLDVFXDJV5PRA","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":"01517b934392feb57399e80589db36fab27340076f2f9fb44b2eb1263455d73c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-30T13:32:23Z","title_canon_sha256":"ba886c1fb3fd260629560728b68c172f1da2dc73c809ea0fb32f8ed3ab7f1769"},"schema_version":"1.0","source":{"id":"2106.16057","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.16057","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"arxiv_version","alias_value":"2106.16057v1","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.16057","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"pith_short_12","alias_value":"TA6LAEHYI7AJ","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"pith_short_16","alias_value":"TA6LAEHYI7AJNHLD","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"pith_short_8","alias_value":"TA6LAEHY","created_at":"2026-07-05T02:54:02Z"}],"graph_snapshots":[{"event_id":"sha256:82b59bdbfbc8b3f47dbf7afcd46504914fd04ff665357db1a698c95d20a39588","target":"graph","created_at":"2026-07-05T02:54:02Z","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/2106.16057/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Missing data is a recurrent and challenging problem, especially when using machine learning algorithms for real-world applications. For this reason, missing data imputation has become an active research area, in which recent deep learning approaches have achieved state-of-the-art results. We propose DAEMA (Denoising Autoencoder with Mask Attention), an algorithm based on a denoising autoencoder architecture with an attention mechanism. While most imputation algorithms use incomplete inputs as they would use complete data - up to basic preprocessing (e.g. mean imputation) - DAEMA leverages a ma","authors_text":"Damien Fourure, Muhammad Usama Javaid, Nicolas Posocco, Simon Tihon, Thomas Peel","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-30T13:32:23Z","title":"DAEMA: Denoising Autoencoder with Mask Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.16057","kind":"arxiv","version":1},"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:bc250fb27a5e99e1425c9bba494964d323079086ce36dba6fcb1d1e1d5f603f9","target":"record","created_at":"2026-07-05T02:54:02Z","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":"01517b934392feb57399e80589db36fab27340076f2f9fb44b2eb1263455d73c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-30T13:32:23Z","title_canon_sha256":"ba886c1fb3fd260629560728b68c172f1da2dc73c809ea0fb32f8ed3ab7f1769"},"schema_version":"1.0","source":{"id":"2106.16057","kind":"arxiv","version":1}},"canonical_sha256":"983cb010f847c0969d63a96e34d7af8828c3cd4cd2714df22fe2aa710dc08b1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"983cb010f847c0969d63a96e34d7af8828c3cd4cd2714df22fe2aa710dc08b1e","first_computed_at":"2026-07-05T02:54:02.986183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:54:02.986183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zzIO42XD4KEI1iWqfndwYLgFcvLwEhxWSqncx9+qRz8zwzp9yqx1RBQeyfCYXwANHF1EAluAexp/HYOXnbcdCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:54:02.986614Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.16057","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc250fb27a5e99e1425c9bba494964d323079086ce36dba6fcb1d1e1d5f603f9","sha256:82b59bdbfbc8b3f47dbf7afcd46504914fd04ff665357db1a698c95d20a39588"],"state_sha256":"90be134d068a32267047dc9a612130833b8919171610b35c65c3bd8841d23f8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z/C7f/KHS2EXWa5z6xY9yNq7uer6akxhMOnr2joNwK28yz4m5kc+8tItiwbjwb5oak+Zsh3GrHv0Iz7YxfmICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T09:29:23.794584Z","bundle_sha256":"800fba485187cf94cc8bbe4df25c786c01b6295606c96b16b368f4e65e76a23b"}}