{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RHBBRZYOG5VWUWM7ZD3UWQ6BTN","short_pith_number":"pith:RHBBRZYO","canonical_record":{"source":{"id":"1809.08717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-24T01:37:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a8e791c592752c4634ccaac5da922a9e60a65cc2c75ce5ac89753803a67fddf9","abstract_canon_sha256":"7958aa767ccf4229250ceb76f0deb948f9d3404be3ea7560922243518470937d"},"schema_version":"1.0"},"canonical_sha256":"89c218e70e376b6a599fc8f74b43c19b51fd999357251fe619d6d730738d70ad","source":{"kind":"arxiv","id":"1809.08717","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.08717","created_at":"2026-05-18T00:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"1809.08717v1","created_at":"2026-05-18T00:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.08717","created_at":"2026-05-18T00:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"RHBBRZYOG5VW","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RHBBRZYOG5VWUWM7","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RHBBRZYO","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RHBBRZYOG5VWUWM7ZD3UWQ6BTN","target":"record","payload":{"canonical_record":{"source":{"id":"1809.08717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-24T01:37:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a8e791c592752c4634ccaac5da922a9e60a65cc2c75ce5ac89753803a67fddf9","abstract_canon_sha256":"7958aa767ccf4229250ceb76f0deb948f9d3404be3ea7560922243518470937d"},"schema_version":"1.0"},"canonical_sha256":"89c218e70e376b6a599fc8f74b43c19b51fd999357251fe619d6d730738d70ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:03.761163Z","signature_b64":"7r43fXgVnENYV2OdGe8aDbrjvJOXONxy1wgfk8TB2Zifz1oNRoWOw4H1M81qsBc0nGKn4OV6wmF+zaOkCt6JDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89c218e70e376b6a599fc8f74b43c19b51fd999357251fe619d6d730738d70ad","last_reissued_at":"2026-05-18T00:05:03.760756Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:03.760756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.08717","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":"2026-05-18T00:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qwKSpJet3i9YaD1FmK0QCITPqRvDaNY9ZSmu7U4z7y/6Zw1ADt5rrVNPyXOiMN0uvJsfUJ0JsHcYvvCRWytfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T20:21:39.125696Z"},"content_sha256":"5bd5906cd7bea2f9e1a0341143358b35273d150bfe9dfb04d3dd269ea83a543e","schema_version":"1.0","event_id":"sha256:5bd5906cd7bea2f9e1a0341143358b35273d150bfe9dfb04d3dd269ea83a543e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RHBBRZYOG5VWUWM7ZD3UWQ6BTN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified recurrent neural network for many feature types","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Stec, Diego Klabjan, Jean Utke","submitted_at":"2018-09-24T01:37:26Z","abstract_excerpt":"There are time series that are amenable to recurrent neural network (RNN) solutions when treated as sequences, but some series, e.g. asynchronous time series, provide a richer variation of feature types than current RNN cells take into account. In order to address such situations, we introduce a unified RNN that handles five different feature types, each in a different manner. Our RNN framework separates sequential features into two groups dependent on their frequency, which we call sparse and dense features, and which affect cell updates differently. Further, we also incorporate time features"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.08717","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":"2026-05-18T00:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aMgRHn/PtIkwPw0ZyZuZ5hZDxuBvKmJHr4LHCsY2MFMZwa6C2GJb1PK1pGtC3mqC/2FfywVoAynGkDI6bpbnBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T20:21:39.126358Z"},"content_sha256":"54d53b54a9eeb88ff2dcb382e0dc536e65184cb118206b50d47c569511d5b3bd","schema_version":"1.0","event_id":"sha256:54d53b54a9eeb88ff2dcb382e0dc536e65184cb118206b50d47c569511d5b3bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RHBBRZYOG5VWUWM7ZD3UWQ6BTN/bundle.json","state_url":"https://pith.science/pith/RHBBRZYOG5VWUWM7ZD3UWQ6BTN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RHBBRZYOG5VWUWM7ZD3UWQ6BTN/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":"2026-05-29T20:21:39Z","links":{"resolver":"https://pith.science/pith/RHBBRZYOG5VWUWM7ZD3UWQ6BTN","bundle":"https://pith.science/pith/RHBBRZYOG5VWUWM7ZD3UWQ6BTN/bundle.json","state":"https://pith.science/pith/RHBBRZYOG5VWUWM7ZD3UWQ6BTN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RHBBRZYOG5VWUWM7ZD3UWQ6BTN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RHBBRZYOG5VWUWM7ZD3UWQ6BTN","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":"7958aa767ccf4229250ceb76f0deb948f9d3404be3ea7560922243518470937d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-24T01:37:26Z","title_canon_sha256":"a8e791c592752c4634ccaac5da922a9e60a65cc2c75ce5ac89753803a67fddf9"},"schema_version":"1.0","source":{"id":"1809.08717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.08717","created_at":"2026-05-18T00:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"1809.08717v1","created_at":"2026-05-18T00:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.08717","created_at":"2026-05-18T00:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"RHBBRZYOG5VW","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RHBBRZYOG5VWUWM7","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RHBBRZYO","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:54d53b54a9eeb88ff2dcb382e0dc536e65184cb118206b50d47c569511d5b3bd","target":"graph","created_at":"2026-05-18T00:05:03Z","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":"There are time series that are amenable to recurrent neural network (RNN) solutions when treated as sequences, but some series, e.g. asynchronous time series, provide a richer variation of feature types than current RNN cells take into account. In order to address such situations, we introduce a unified RNN that handles five different feature types, each in a different manner. Our RNN framework separates sequential features into two groups dependent on their frequency, which we call sparse and dense features, and which affect cell updates differently. Further, we also incorporate time features","authors_text":"Alexander Stec, Diego Klabjan, Jean Utke","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-24T01:37:26Z","title":"Unified recurrent neural network for many feature types"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.08717","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":"sha256:5bd5906cd7bea2f9e1a0341143358b35273d150bfe9dfb04d3dd269ea83a543e","target":"record","created_at":"2026-05-18T00:05:03Z","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":"7958aa767ccf4229250ceb76f0deb948f9d3404be3ea7560922243518470937d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-24T01:37:26Z","title_canon_sha256":"a8e791c592752c4634ccaac5da922a9e60a65cc2c75ce5ac89753803a67fddf9"},"schema_version":"1.0","source":{"id":"1809.08717","kind":"arxiv","version":1}},"canonical_sha256":"89c218e70e376b6a599fc8f74b43c19b51fd999357251fe619d6d730738d70ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89c218e70e376b6a599fc8f74b43c19b51fd999357251fe619d6d730738d70ad","first_computed_at":"2026-05-18T00:05:03.760756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:03.760756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7r43fXgVnENYV2OdGe8aDbrjvJOXONxy1wgfk8TB2Zifz1oNRoWOw4H1M81qsBc0nGKn4OV6wmF+zaOkCt6JDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:03.761163Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.08717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bd5906cd7bea2f9e1a0341143358b35273d150bfe9dfb04d3dd269ea83a543e","sha256:54d53b54a9eeb88ff2dcb382e0dc536e65184cb118206b50d47c569511d5b3bd"],"state_sha256":"4a76ad88bd7066a06088d3a84d22a914ae497ca3857c94c254a9bf26cf0c0cce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/yMz65kQwTlDc5adN9p7LQetnby9SjlTvwNvmi4Rq4IbTZu030XN62VFKur7gexWkploW6imLJiVujmVCA6FDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T20:21:39.130833Z","bundle_sha256":"e1a82a382278bca37cc62acabc1edc048052060b8a6ff5d9a69ef698da532396"}}