{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:HFH2MFNXOHMYLQYGLLMRT37DLG","short_pith_number":"pith:HFH2MFNX","canonical_record":{"source":{"id":"1605.09458","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-31T00:58:47Z","cross_cats_sorted":[],"title_canon_sha256":"fbd2971af01581c326a4b9c76febdebb5563cd22a50bf510e929b7a0e7f70cae","abstract_canon_sha256":"50cee74d70a13ae39c59caee6800f46144e48328bbdaca0090945ba6d3a4dd07"},"schema_version":"1.0"},"canonical_sha256":"394fa615b771d985c3065ad919efe359b7bab6bdbfb9c70b8b0c2a25fe6ee3b9","source":{"kind":"arxiv","id":"1605.09458","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.09458","created_at":"2026-05-18T01:13:17Z"},{"alias_kind":"arxiv_version","alias_value":"1605.09458v1","created_at":"2026-05-18T01:13:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.09458","created_at":"2026-05-18T01:13:17Z"},{"alias_kind":"pith_short_12","alias_value":"HFH2MFNXOHMY","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"HFH2MFNXOHMYLQYG","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"HFH2MFNX","created_at":"2026-05-18T12:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:HFH2MFNXOHMYLQYGLLMRT37DLG","target":"record","payload":{"canonical_record":{"source":{"id":"1605.09458","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-31T00:58:47Z","cross_cats_sorted":[],"title_canon_sha256":"fbd2971af01581c326a4b9c76febdebb5563cd22a50bf510e929b7a0e7f70cae","abstract_canon_sha256":"50cee74d70a13ae39c59caee6800f46144e48328bbdaca0090945ba6d3a4dd07"},"schema_version":"1.0"},"canonical_sha256":"394fa615b771d985c3065ad919efe359b7bab6bdbfb9c70b8b0c2a25fe6ee3b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:17.251486Z","signature_b64":"pdb+ybO0om0LBfHPDY90TnHc34sDNOTxALpCZwogYh4NIcLAVPfVsQoYCWaj5Yba5jwz+rsJvf6MMO1yJU6sAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"394fa615b771d985c3065ad919efe359b7bab6bdbfb9c70b8b0c2a25fe6ee3b9","last_reissued_at":"2026-05-18T01:13:17.250897Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:17.250897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.09458","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":"2026-05-18T01:13:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ej1D7Dc7LvDrsYQvE17KIWZjvyLDF8DeyuGVZj/pcEqRYV3MMLjptq8ZVZuPVJR5O/rIaLaQ61972k5TnxZRBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:16:53.261910Z"},"content_sha256":"f9e642b669e3bc485c52f9b64fba1cbb928c90d25ca81c74930034cd18e94bb5","schema_version":"1.0","event_id":"sha256:f9e642b669e3bc485c52f9b64fba1cbb928c90d25ca81c74930034cd18e94bb5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:HFH2MFNXOHMYLQYGLLMRT37DLG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Auto-encoders Effectively via Eliminating Task-irrelevant Input Variables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dehua Li, Hong Wu, Hui Shen, Zhaoxiang Zang","submitted_at":"2016-05-31T00:58:47Z","abstract_excerpt":"Auto-encoders are often used as building blocks of deep network classifier to learn feature extractors, but task-irrelevant information in the input data may lead to bad extractors and result in poor generalization performance of the network. In this paper,via dropping the task-irrelevant input variables the performance of auto-encoders can be obviously improved .Specifically, an importance-based variable selection method is proposed to aim at finding the task-irrelevant input variables and dropping them.It firstly estimates importance of each variable,and then drops the variables with importa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.09458","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:13:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/iapjRUw5Pfbk1CBEk6eBE9GieS224e+sK1jSyhOBifjq2B2gb66qgUJDUK2agOHFRYoY1egBuDj4I8l9GopDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:16:53.262252Z"},"content_sha256":"eab754bf9a64223b8c5ecac1ef1725bead0fc1956b9c3aee17d1735740f2c4ec","schema_version":"1.0","event_id":"sha256:eab754bf9a64223b8c5ecac1ef1725bead0fc1956b9c3aee17d1735740f2c4ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HFH2MFNXOHMYLQYGLLMRT37DLG/bundle.json","state_url":"https://pith.science/pith/HFH2MFNXOHMYLQYGLLMRT37DLG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HFH2MFNXOHMYLQYGLLMRT37DLG/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":"2026-05-31T01:16:53Z","links":{"resolver":"https://pith.science/pith/HFH2MFNXOHMYLQYGLLMRT37DLG","bundle":"https://pith.science/pith/HFH2MFNXOHMYLQYGLLMRT37DLG/bundle.json","state":"https://pith.science/pith/HFH2MFNXOHMYLQYGLLMRT37DLG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HFH2MFNXOHMYLQYGLLMRT37DLG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:HFH2MFNXOHMYLQYGLLMRT37DLG","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":"50cee74d70a13ae39c59caee6800f46144e48328bbdaca0090945ba6d3a4dd07","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-31T00:58:47Z","title_canon_sha256":"fbd2971af01581c326a4b9c76febdebb5563cd22a50bf510e929b7a0e7f70cae"},"schema_version":"1.0","source":{"id":"1605.09458","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.09458","created_at":"2026-05-18T01:13:17Z"},{"alias_kind":"arxiv_version","alias_value":"1605.09458v1","created_at":"2026-05-18T01:13:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.09458","created_at":"2026-05-18T01:13:17Z"},{"alias_kind":"pith_short_12","alias_value":"HFH2MFNXOHMY","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"HFH2MFNXOHMYLQYG","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"HFH2MFNX","created_at":"2026-05-18T12:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:eab754bf9a64223b8c5ecac1ef1725bead0fc1956b9c3aee17d1735740f2c4ec","target":"graph","created_at":"2026-05-18T01:13:17Z","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"},"paper":{"abstract_excerpt":"Auto-encoders are often used as building blocks of deep network classifier to learn feature extractors, but task-irrelevant information in the input data may lead to bad extractors and result in poor generalization performance of the network. In this paper,via dropping the task-irrelevant input variables the performance of auto-encoders can be obviously improved .Specifically, an importance-based variable selection method is proposed to aim at finding the task-irrelevant input variables and dropping them.It firstly estimates importance of each variable,and then drops the variables with importa","authors_text":"Dehua Li, Hong Wu, Hui Shen, Zhaoxiang Zang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-31T00:58:47Z","title":"Training Auto-encoders Effectively via Eliminating Task-irrelevant Input Variables"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.09458","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:f9e642b669e3bc485c52f9b64fba1cbb928c90d25ca81c74930034cd18e94bb5","target":"record","created_at":"2026-05-18T01:13:17Z","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":"50cee74d70a13ae39c59caee6800f46144e48328bbdaca0090945ba6d3a4dd07","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-31T00:58:47Z","title_canon_sha256":"fbd2971af01581c326a4b9c76febdebb5563cd22a50bf510e929b7a0e7f70cae"},"schema_version":"1.0","source":{"id":"1605.09458","kind":"arxiv","version":1}},"canonical_sha256":"394fa615b771d985c3065ad919efe359b7bab6bdbfb9c70b8b0c2a25fe6ee3b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"394fa615b771d985c3065ad919efe359b7bab6bdbfb9c70b8b0c2a25fe6ee3b9","first_computed_at":"2026-05-18T01:13:17.250897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:13:17.250897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pdb+ybO0om0LBfHPDY90TnHc34sDNOTxALpCZwogYh4NIcLAVPfVsQoYCWaj5Yba5jwz+rsJvf6MMO1yJU6sAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:13:17.251486Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.09458","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9e642b669e3bc485c52f9b64fba1cbb928c90d25ca81c74930034cd18e94bb5","sha256:eab754bf9a64223b8c5ecac1ef1725bead0fc1956b9c3aee17d1735740f2c4ec"],"state_sha256":"ca91e1bfe03dc781b0af83975aec1e6e0ac4cf6f4f065469365eaecbd6a0650f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vYVhwjYIGBexwCIhOmLdhnmfPvkt26Uclq8+0v38J0e4x3dVymm/5HkiIzJ3bj2B0GhWfJ3lh5d0oVyoPlO3Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T01:16:53.264365Z","bundle_sha256":"2f696ffc4c430a4e095dc1f57570c32b23b2f9d17c9aec3b3d6a55ebdcc23303"}}