{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:H7TGQFDLTPQP2JRIPJYUWLBM4B","short_pith_number":"pith:H7TGQFDL","schema_version":"1.0","canonical_sha256":"3fe668146b9be0fd26287a714b2c2ce040290c0d1634188599ddd90cb9fceb9d","source":{"kind":"arxiv","id":"1609.03068","version":3},"attestation_state":"computed","paper":{"title":"Multiplex visibility graphs to investigate recurrent neural networks dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DS"],"primary_cat":"cs.NE","authors_text":"Cesare Alippi, Filippo Maria Bianchi, Lorenzo Livi, Robert Jenssen","submitted_at":"2016-09-10T16:12:27Z","abstract_excerpt":"A recurrent neural network (RNN) is a universal approximator of dynamical systems, whose performance often depends on sensitive hyperparameters. Tuning of such hyperparameters may be difficult and, typically, based on a trial-and-error approach. In this work, we adopt a graph-based framework to interpret and characterize the internal RNN dynamics. Through this insight, we are able to design a principled unsupervised method to derive configurations with maximized performances, in terms of prediction error and memory capacity. In particular, we propose to model time series of neurons activations"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1609.03068","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-09-10T16:12:27Z","cross_cats_sorted":["math.DS"],"title_canon_sha256":"a3fb90532d2464fde4298d155fae77b21206a1092369f045026b88e6a574fc76","abstract_canon_sha256":"f417db78878e7c2a221fa012c429d8776261aa0b10fe47651b2246692436651f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:19.151058Z","signature_b64":"3FesEPUJb04Azaxuz6O/HWLIq6f4LGNjkOOmkVje8GsvK+xYlIKrXe4CVhW5WE/yCuk3pbon8IzdVNYzXtIkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fe668146b9be0fd26287a714b2c2ce040290c0d1634188599ddd90cb9fceb9d","last_reissued_at":"2026-05-18T00:50:19.150391Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:19.150391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiplex visibility graphs to investigate recurrent neural networks dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DS"],"primary_cat":"cs.NE","authors_text":"Cesare Alippi, Filippo Maria Bianchi, Lorenzo Livi, Robert Jenssen","submitted_at":"2016-09-10T16:12:27Z","abstract_excerpt":"A recurrent neural network (RNN) is a universal approximator of dynamical systems, whose performance often depends on sensitive hyperparameters. Tuning of such hyperparameters may be difficult and, typically, based on a trial-and-error approach. In this work, we adopt a graph-based framework to interpret and characterize the internal RNN dynamics. Through this insight, we are able to design a principled unsupervised method to derive configurations with maximized performances, in terms of prediction error and memory capacity. In particular, we propose to model time series of neurons activations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.03068","kind":"arxiv","version":3},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1609.03068","created_at":"2026-05-18T00:50:19.150477+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.03068v3","created_at":"2026-05-18T00:50:19.150477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.03068","created_at":"2026-05-18T00:50:19.150477+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7TGQFDLTPQP","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7TGQFDLTPQP2JRI","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7TGQFDL","created_at":"2026-05-18T12:30:19.053100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7TGQFDLTPQP2JRIPJYUWLBM4B","json":"https://pith.science/pith/H7TGQFDLTPQP2JRIPJYUWLBM4B.json","graph_json":"https://pith.science/api/pith-number/H7TGQFDLTPQP2JRIPJYUWLBM4B/graph.json","events_json":"https://pith.science/api/pith-number/H7TGQFDLTPQP2JRIPJYUWLBM4B/events.json","paper":"https://pith.science/paper/H7TGQFDL"},"agent_actions":{"view_html":"https://pith.science/pith/H7TGQFDLTPQP2JRIPJYUWLBM4B","download_json":"https://pith.science/pith/H7TGQFDLTPQP2JRIPJYUWLBM4B.json","view_paper":"https://pith.science/paper/H7TGQFDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.03068&json=true","fetch_graph":"https://pith.science/api/pith-number/H7TGQFDLTPQP2JRIPJYUWLBM4B/graph.json","fetch_events":"https://pith.science/api/pith-number/H7TGQFDLTPQP2JRIPJYUWLBM4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7TGQFDLTPQP2JRIPJYUWLBM4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7TGQFDLTPQP2JRIPJYUWLBM4B/action/storage_attestation","attest_author":"https://pith.science/pith/H7TGQFDLTPQP2JRIPJYUWLBM4B/action/author_attestation","sign_citation":"https://pith.science/pith/H7TGQFDLTPQP2JRIPJYUWLBM4B/action/citation_signature","submit_replication":"https://pith.science/pith/H7TGQFDLTPQP2JRIPJYUWLBM4B/action/replication_record"}},"created_at":"2026-05-18T00:50:19.150477+00:00","updated_at":"2026-05-18T00:50:19.150477+00:00"}