{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:FSFXCJ7JCWITCW2OKBVVJAFXOH","short_pith_number":"pith:FSFXCJ7J","canonical_record":{"source":{"id":"1802.00748","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-02T16:14:59Z","cross_cats_sorted":["cs.AI","math.DS","stat.ML"],"title_canon_sha256":"6fbc31eb33fb37744e528f2b4b7aacd724db1091449d07f4fe59f54949a28b1a","abstract_canon_sha256":"9e66494f0f4ad80b2d5ea99b9643b8b97990e05d65843e920e78065b15fd7208"},"schema_version":"1.0"},"canonical_sha256":"2c8b7127e91591315b4e506b5480b771f64f107ece5c5dd8b863453d8c58cf11","source":{"kind":"arxiv","id":"1802.00748","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.00748","created_at":"2026-05-18T00:24:32Z"},{"alias_kind":"arxiv_version","alias_value":"1802.00748v1","created_at":"2026-05-18T00:24:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.00748","created_at":"2026-05-18T00:24:32Z"},{"alias_kind":"pith_short_12","alias_value":"FSFXCJ7JCWIT","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FSFXCJ7JCWITCW2O","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FSFXCJ7J","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:FSFXCJ7JCWITCW2OKBVVJAFXOH","target":"record","payload":{"canonical_record":{"source":{"id":"1802.00748","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-02T16:14:59Z","cross_cats_sorted":["cs.AI","math.DS","stat.ML"],"title_canon_sha256":"6fbc31eb33fb37744e528f2b4b7aacd724db1091449d07f4fe59f54949a28b1a","abstract_canon_sha256":"9e66494f0f4ad80b2d5ea99b9643b8b97990e05d65843e920e78065b15fd7208"},"schema_version":"1.0"},"canonical_sha256":"2c8b7127e91591315b4e506b5480b771f64f107ece5c5dd8b863453d8c58cf11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:32.439072Z","signature_b64":"NZegJtG1Xysy508wa8Se7FAk4wnd3XQikplJ+4lu1j+5LUBZxvFZtOv/pk3SJufixB3+jUHGXW/14hCavIF/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c8b7127e91591315b4e506b5480b771f64f107ece5c5dd8b863453d8c58cf11","last_reissued_at":"2026-05-18T00:24:32.438655Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:32.438655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.00748","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":"2026-05-18T00:24:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8gXcuRpYY5mackliWGj6gwQAKVvYt/IKW6+IKQyGF54zZJKgRw82U5rS+W+NMerMJrljPmgTXlA9vorKdPNTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T17:31:36.983718Z"},"content_sha256":"206c5b03063eaedc9aac9f1227c2480faefa63ae57fbe27b9baebdbc6b1aaa77","schema_version":"1.0","event_id":"sha256:206c5b03063eaedc9aac9f1227c2480faefa63ae57fbe27b9baebdbc6b1aaa77"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:FSFXCJ7JCWITCW2OKBVVJAFXOH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Short-term Memory of Deep RNN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Claudio Gallicchio","submitted_at":"2018-02-02T16:14:59Z","abstract_excerpt":"The extension of deep learning towards temporal data processing is gaining an increasing research interest. In this paper we investigate the properties of state dynamics developed in successive levels of deep recurrent neural networks (RNNs) in terms of short-term memory abilities. Our results reveal interesting insights that shed light on the nature of layering as a factor of RNN design. Noticeably, higher layers in a hierarchically organized RNN architecture results to be inherently biased towards longer memory spans even prior to training of the recurrent connections. Moreover, in the conte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.00748","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":"2026-05-18T00:24:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9x+2IsVHQTlgATkVigXe2XAiM0JRiBy7saobXKbd1Zjg1nvQHahAT92/f0TFasRZsmyoIqqmGwXF88hA4StCCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T17:31:36.984111Z"},"content_sha256":"670fcfabf7c3fefb081314b7a19a840bcea1c5b1f980e779745e0f3e52d8bc79","schema_version":"1.0","event_id":"sha256:670fcfabf7c3fefb081314b7a19a840bcea1c5b1f980e779745e0f3e52d8bc79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FSFXCJ7JCWITCW2OKBVVJAFXOH/bundle.json","state_url":"https://pith.science/pith/FSFXCJ7JCWITCW2OKBVVJAFXOH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FSFXCJ7JCWITCW2OKBVVJAFXOH/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":"2026-05-27T17:31:36Z","links":{"resolver":"https://pith.science/pith/FSFXCJ7JCWITCW2OKBVVJAFXOH","bundle":"https://pith.science/pith/FSFXCJ7JCWITCW2OKBVVJAFXOH/bundle.json","state":"https://pith.science/pith/FSFXCJ7JCWITCW2OKBVVJAFXOH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FSFXCJ7JCWITCW2OKBVVJAFXOH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FSFXCJ7JCWITCW2OKBVVJAFXOH","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":"9e66494f0f4ad80b2d5ea99b9643b8b97990e05d65843e920e78065b15fd7208","cross_cats_sorted":["cs.AI","math.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-02T16:14:59Z","title_canon_sha256":"6fbc31eb33fb37744e528f2b4b7aacd724db1091449d07f4fe59f54949a28b1a"},"schema_version":"1.0","source":{"id":"1802.00748","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.00748","created_at":"2026-05-18T00:24:32Z"},{"alias_kind":"arxiv_version","alias_value":"1802.00748v1","created_at":"2026-05-18T00:24:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.00748","created_at":"2026-05-18T00:24:32Z"},{"alias_kind":"pith_short_12","alias_value":"FSFXCJ7JCWIT","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FSFXCJ7JCWITCW2O","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FSFXCJ7J","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:670fcfabf7c3fefb081314b7a19a840bcea1c5b1f980e779745e0f3e52d8bc79","target":"graph","created_at":"2026-05-18T00:24:32Z","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":"The extension of deep learning towards temporal data processing is gaining an increasing research interest. In this paper we investigate the properties of state dynamics developed in successive levels of deep recurrent neural networks (RNNs) in terms of short-term memory abilities. Our results reveal interesting insights that shed light on the nature of layering as a factor of RNN design. Noticeably, higher layers in a hierarchically organized RNN architecture results to be inherently biased towards longer memory spans even prior to training of the recurrent connections. Moreover, in the conte","authors_text":"Claudio Gallicchio","cross_cats":["cs.AI","math.DS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-02T16:14:59Z","title":"Short-term Memory of Deep RNN"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.00748","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":"sha256:206c5b03063eaedc9aac9f1227c2480faefa63ae57fbe27b9baebdbc6b1aaa77","target":"record","created_at":"2026-05-18T00:24:32Z","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":"9e66494f0f4ad80b2d5ea99b9643b8b97990e05d65843e920e78065b15fd7208","cross_cats_sorted":["cs.AI","math.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-02T16:14:59Z","title_canon_sha256":"6fbc31eb33fb37744e528f2b4b7aacd724db1091449d07f4fe59f54949a28b1a"},"schema_version":"1.0","source":{"id":"1802.00748","kind":"arxiv","version":1}},"canonical_sha256":"2c8b7127e91591315b4e506b5480b771f64f107ece5c5dd8b863453d8c58cf11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c8b7127e91591315b4e506b5480b771f64f107ece5c5dd8b863453d8c58cf11","first_computed_at":"2026-05-18T00:24:32.438655Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:32.438655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NZegJtG1Xysy508wa8Se7FAk4wnd3XQikplJ+4lu1j+5LUBZxvFZtOv/pk3SJufixB3+jUHGXW/14hCavIF/AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:32.439072Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.00748","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:206c5b03063eaedc9aac9f1227c2480faefa63ae57fbe27b9baebdbc6b1aaa77","sha256:670fcfabf7c3fefb081314b7a19a840bcea1c5b1f980e779745e0f3e52d8bc79"],"state_sha256":"c7d724fa561643f7f821e5c0d7edf98fdea30fe41acfe6b1f211fe48215c2f29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OaZClmWGwAK+frXTJBH9jCKkREYciEhyi8oNQI5jNxsFpO/mGD1ud/6Y8U5j/t0G+d543LsLnvs8TzaWny+gAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T17:31:36.986760Z","bundle_sha256":"48495d726e6571c551ef1ccafb6aad166902246d2a30e26ae19ec2c1abd1ec1f"}}