{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AOA6OSHA5OUDIDEJWCJYZ3REWS","short_pith_number":"pith:AOA6OSHA","schema_version":"1.0","canonical_sha256":"0381e748e0eba8340c89b0938cee24b4b3fab0dc8e6c0370712b435cdb7090b6","source":{"kind":"arxiv","id":"2306.07125","version":1},"attestation_state":"computed","paper":{"title":"On the Dynamics of Learning Time-Aware Behavior with Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Edward Rietman, Hava T. Siegelmann, Peter DelMastro, Rushiv Arora","submitted_at":"2023-06-12T14:01:30Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) have shown great success in modeling time-dependent patterns, but there is limited research on their learned representations of latent temporal features and the emergence of these representations during training. To address this gap, we use timed automata (TA) to introduce a family of supervised learning tasks modeling behavior dependent on hidden temporal variables whose complexity is directly controllable. Building upon past studies from the perspective of dynamical systems, we train RNNs to emulate temporal flipflops, a new collection of TA that emphasizes t"},"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":"2306.07125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T14:01:30Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"b82b33d3f09df756f8822cc81b2a095771911b0053e9465cde80d2ed5075cdda","abstract_canon_sha256":"981ac69bcadb0b68f3f5b2808f65370acc23bd827fca17afa23d8a34a2a7d4b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:48.003014Z","signature_b64":"QwuvZ9WWq2SQlm+DOq/KaKGMRL0B3ndSrMl9q9iH28d2O2gOGheJEMY9/Lj4c2e+ENEYyo/YP+AJ267r1ShsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0381e748e0eba8340c89b0938cee24b4b3fab0dc8e6c0370712b435cdb7090b6","last_reissued_at":"2026-07-05T06:19:48.002546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:48.002546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Dynamics of Learning Time-Aware Behavior with Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Edward Rietman, Hava T. Siegelmann, Peter DelMastro, Rushiv Arora","submitted_at":"2023-06-12T14:01:30Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) have shown great success in modeling time-dependent patterns, but there is limited research on their learned representations of latent temporal features and the emergence of these representations during training. To address this gap, we use timed automata (TA) to introduce a family of supervised learning tasks modeling behavior dependent on hidden temporal variables whose complexity is directly controllable. Building upon past studies from the perspective of dynamical systems, we train RNNs to emulate temporal flipflops, a new collection of TA that emphasizes t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07125","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.07125/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.07125","created_at":"2026-07-05T06:19:48.002602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07125v1","created_at":"2026-07-05T06:19:48.002602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07125","created_at":"2026-07-05T06:19:48.002602+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOA6OSHA5OUD","created_at":"2026-07-05T06:19:48.002602+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOA6OSHA5OUDIDEJ","created_at":"2026-07-05T06:19:48.002602+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOA6OSHA","created_at":"2026-07-05T06:19:48.002602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.02378","citing_title":"A ghost mechanism: An analytical model of abrupt learning in recurrent networks","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AOA6OSHA5OUDIDEJWCJYZ3REWS","json":"https://pith.science/pith/AOA6OSHA5OUDIDEJWCJYZ3REWS.json","graph_json":"https://pith.science/api/pith-number/AOA6OSHA5OUDIDEJWCJYZ3REWS/graph.json","events_json":"https://pith.science/api/pith-number/AOA6OSHA5OUDIDEJWCJYZ3REWS/events.json","paper":"https://pith.science/paper/AOA6OSHA"},"agent_actions":{"view_html":"https://pith.science/pith/AOA6OSHA5OUDIDEJWCJYZ3REWS","download_json":"https://pith.science/pith/AOA6OSHA5OUDIDEJWCJYZ3REWS.json","view_paper":"https://pith.science/paper/AOA6OSHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07125&json=true","fetch_graph":"https://pith.science/api/pith-number/AOA6OSHA5OUDIDEJWCJYZ3REWS/graph.json","fetch_events":"https://pith.science/api/pith-number/AOA6OSHA5OUDIDEJWCJYZ3REWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOA6OSHA5OUDIDEJWCJYZ3REWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOA6OSHA5OUDIDEJWCJYZ3REWS/action/storage_attestation","attest_author":"https://pith.science/pith/AOA6OSHA5OUDIDEJWCJYZ3REWS/action/author_attestation","sign_citation":"https://pith.science/pith/AOA6OSHA5OUDIDEJWCJYZ3REWS/action/citation_signature","submit_replication":"https://pith.science/pith/AOA6OSHA5OUDIDEJWCJYZ3REWS/action/replication_record"}},"created_at":"2026-07-05T06:19:48.002602+00:00","updated_at":"2026-07-05T06:19:48.002602+00:00"}