{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DQ3EXBHKL3MMVXLQIXOY34O2OB","short_pith_number":"pith:DQ3EXBHK","canonical_record":{"source":{"id":"2105.14092","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2021-05-28T20:24:00Z","cross_cats_sorted":[],"title_canon_sha256":"d2eef5eb0f6314539254f22edbe75f473eb47ca2ae2776df6cd8d5c54fda5d1b","abstract_canon_sha256":"6612a1bf3e4b87b704e6e8f3701e5724a469afb103d32842ad31fc3b762790ea"},"schema_version":"1.0"},"canonical_sha256":"1c364b84ea5ed8cadd7045dd8df1da70498c9d7373935af4d8fc9ebd7c0fba0c","source":{"kind":"arxiv","id":"2105.14092","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.14092","created_at":"2026-07-05T06:01:33Z"},{"alias_kind":"arxiv_version","alias_value":"2105.14092v6","created_at":"2026-07-05T06:01:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14092","created_at":"2026-07-05T06:01:33Z"},{"alias_kind":"pith_short_12","alias_value":"DQ3EXBHKL3MM","created_at":"2026-07-05T06:01:33Z"},{"alias_kind":"pith_short_16","alias_value":"DQ3EXBHKL3MMVXLQ","created_at":"2026-07-05T06:01:33Z"},{"alias_kind":"pith_short_8","alias_value":"DQ3EXBHK","created_at":"2026-07-05T06:01:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DQ3EXBHKL3MMVXLQIXOY34O2OB","target":"record","payload":{"canonical_record":{"source":{"id":"2105.14092","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2021-05-28T20:24:00Z","cross_cats_sorted":[],"title_canon_sha256":"d2eef5eb0f6314539254f22edbe75f473eb47ca2ae2776df6cd8d5c54fda5d1b","abstract_canon_sha256":"6612a1bf3e4b87b704e6e8f3701e5724a469afb103d32842ad31fc3b762790ea"},"schema_version":"1.0"},"canonical_sha256":"1c364b84ea5ed8cadd7045dd8df1da70498c9d7373935af4d8fc9ebd7c0fba0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:33.233589Z","signature_b64":"LVmC310Ut9wsSKlfH8UrOX8Lrpjib2uuzkOorT6GHnumCFWYmuinPb7zqrfmT2fEIoQSjlEUogJ1ehPG0WJVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c364b84ea5ed8cadd7045dd8df1da70498c9d7373935af4d8fc9ebd7c0fba0c","last_reissued_at":"2026-07-05T06:01:33.233012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:33.233012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.14092","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:01:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cFhOKA1i+C5bpMK5ZwDV53istWDT+1+jwYN5ReJyebujBD7EjvBDBjq84NxgwWTyANT7rOb8fnr5FdnPbcQJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T22:32:20.813306Z"},"content_sha256":"c5588ac80fdfc49c54e4e793cf472f46dc402727f8d302f0725ef6e74fdbfae3","schema_version":"1.0","event_id":"sha256:c5588ac80fdfc49c54e4e793cf472f46dc402727f8d302f0725ef6e74fdbfae3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DQ3EXBHKL3MMVXLQIXOY34O2OB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Least Redundant Gated Recurrent Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"{\\L}ukasz Lepak, {\\L}ukasz Neumann, Pawe{\\l} Wawrzy\\'nski","submitted_at":"2021-05-28T20:24:00Z","abstract_excerpt":"Recurrent neural networks are important tools for sequential data processing. However, they are notorious for problems regarding their training. Challenges include capturing complex relations between consecutive states and stability and efficiency of training. In this paper, we introduce a recurrent neural architecture called Deep Memory Update (DMU). It is based on updating the previous memory state with a deep transformation of the lagged state and the network input. The architecture is able to learn to transform its internal state using any nonlinear function. Its training is stable and fas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14092","kind":"arxiv","version":6},"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/2105.14092/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":"2026-07-05T06:01:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/QrHbqOuAGfw6fdQffIs4QqV7F72ALIxcx3JalmeS/GsMdcUjVwDEkYp0dDOgSAw65MdDL/7Ng0RQCCZAazmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T22:32:20.813681Z"},"content_sha256":"5dcddaa54193bc37abe933ec90722a916e0898e8d8ddcec216d9f1862fb517b4","schema_version":"1.0","event_id":"sha256:5dcddaa54193bc37abe933ec90722a916e0898e8d8ddcec216d9f1862fb517b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DQ3EXBHKL3MMVXLQIXOY34O2OB/bundle.json","state_url":"https://pith.science/pith/DQ3EXBHKL3MMVXLQIXOY34O2OB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DQ3EXBHKL3MMVXLQIXOY34O2OB/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":"2026-07-09T22:32:20Z","links":{"resolver":"https://pith.science/pith/DQ3EXBHKL3MMVXLQIXOY34O2OB","bundle":"https://pith.science/pith/DQ3EXBHKL3MMVXLQIXOY34O2OB/bundle.json","state":"https://pith.science/pith/DQ3EXBHKL3MMVXLQIXOY34O2OB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DQ3EXBHKL3MMVXLQIXOY34O2OB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DQ3EXBHKL3MMVXLQIXOY34O2OB","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":"6612a1bf3e4b87b704e6e8f3701e5724a469afb103d32842ad31fc3b762790ea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2021-05-28T20:24:00Z","title_canon_sha256":"d2eef5eb0f6314539254f22edbe75f473eb47ca2ae2776df6cd8d5c54fda5d1b"},"schema_version":"1.0","source":{"id":"2105.14092","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.14092","created_at":"2026-07-05T06:01:33Z"},{"alias_kind":"arxiv_version","alias_value":"2105.14092v6","created_at":"2026-07-05T06:01:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14092","created_at":"2026-07-05T06:01:33Z"},{"alias_kind":"pith_short_12","alias_value":"DQ3EXBHKL3MM","created_at":"2026-07-05T06:01:33Z"},{"alias_kind":"pith_short_16","alias_value":"DQ3EXBHKL3MMVXLQ","created_at":"2026-07-05T06:01:33Z"},{"alias_kind":"pith_short_8","alias_value":"DQ3EXBHK","created_at":"2026-07-05T06:01:33Z"}],"graph_snapshots":[{"event_id":"sha256:5dcddaa54193bc37abe933ec90722a916e0898e8d8ddcec216d9f1862fb517b4","target":"graph","created_at":"2026-07-05T06:01:33Z","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/2105.14092/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recurrent neural networks are important tools for sequential data processing. However, they are notorious for problems regarding their training. Challenges include capturing complex relations between consecutive states and stability and efficiency of training. In this paper, we introduce a recurrent neural architecture called Deep Memory Update (DMU). It is based on updating the previous memory state with a deep transformation of the lagged state and the network input. The architecture is able to learn to transform its internal state using any nonlinear function. Its training is stable and fas","authors_text":"{\\L}ukasz Lepak, {\\L}ukasz Neumann, Pawe{\\l} Wawrzy\\'nski","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2021-05-28T20:24:00Z","title":"Least Redundant Gated Recurrent Neural Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14092","kind":"arxiv","version":6},"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:c5588ac80fdfc49c54e4e793cf472f46dc402727f8d302f0725ef6e74fdbfae3","target":"record","created_at":"2026-07-05T06:01:33Z","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":"6612a1bf3e4b87b704e6e8f3701e5724a469afb103d32842ad31fc3b762790ea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2021-05-28T20:24:00Z","title_canon_sha256":"d2eef5eb0f6314539254f22edbe75f473eb47ca2ae2776df6cd8d5c54fda5d1b"},"schema_version":"1.0","source":{"id":"2105.14092","kind":"arxiv","version":6}},"canonical_sha256":"1c364b84ea5ed8cadd7045dd8df1da70498c9d7373935af4d8fc9ebd7c0fba0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c364b84ea5ed8cadd7045dd8df1da70498c9d7373935af4d8fc9ebd7c0fba0c","first_computed_at":"2026-07-05T06:01:33.233012Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:01:33.233012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LVmC310Ut9wsSKlfH8UrOX8Lrpjib2uuzkOorT6GHnumCFWYmuinPb7zqrfmT2fEIoQSjlEUogJ1ehPG0WJVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:01:33.233589Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.14092","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5588ac80fdfc49c54e4e793cf472f46dc402727f8d302f0725ef6e74fdbfae3","sha256:5dcddaa54193bc37abe933ec90722a916e0898e8d8ddcec216d9f1862fb517b4"],"state_sha256":"f9e7e44eb3bc311826949c0408d5130fcbff8101e1ca979a55fe123d5886413b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mlg+ynm4wEE77RY8vmdjmbK0h3M/VpzcIpTjjQVwbCxOzdoJYhIPkRRhlffUub5qL46j4QRqMthE+fBLR4B9CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T22:32:20.815759Z","bundle_sha256":"55214e57ba9165d0a6f069fc0921e042f119deef8aa7909f2dc94b31bdced1cc"}}