{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WF4EWT4O6ZFEJELAKUHY6EM6MU","short_pith_number":"pith:WF4EWT4O","schema_version":"1.0","canonical_sha256":"b1784b4f8ef64a449160550f8f119e650d9126600800ad035ae4fba99e15568e","source":{"kind":"arxiv","id":"2301.12892","version":2},"attestation_state":"computed","paper":{"title":"Quantifying and maximizing the information flux in recurrent neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"q-bio.NC","authors_text":"Achim Schilling, Claus Metzner, Dennis Voelkl, Marius E. Yamakou, Patrick Krauss","submitted_at":"2023-01-30T13:52:39Z","abstract_excerpt":"Free-running Recurrent Neural Networks (RNNs), especially probabilistic models, generate an ongoing information flux that can be quantified with the mutual information $I\\left[\\vec{x}(t),\\vec{x}(t\\!+\\!1)\\right]$ between subsequent system states $\\vec{x}$. Although, former studies have shown that $I$ depends on the statistics of the network's connection weights, it is unclear (1) how to maximize $I$ systematically and (2) how to quantify the flux in large systems where computing the mutual information becomes intractable. Here, we address these questions using Boltzmann machines as model system"},"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":"2301.12892","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.NC","submitted_at":"2023-01-30T13:52:39Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"3e4cdfb82cd0ddb4e64f7b67434b0f6ec85f198b1bbbf5e5841da5afc02586f0","abstract_canon_sha256":"8a28a7f9a5031e48204aa2700a048c190dca04952e14f0fb4c1a44dc39f845e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:38.940113Z","signature_b64":"MdE5eCovHcAvCAjnzh3jUO57/fIiM2pZ3r+8ckxg/Pq3C6piq5+eCEQ8CNSxCeKNYjdreMj8xcFFBTuSUdeqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1784b4f8ef64a449160550f8f119e650d9126600800ad035ae4fba99e15568e","last_reissued_at":"2026-07-05T07:01:38.939621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:38.939621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying and maximizing the information flux in recurrent neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"q-bio.NC","authors_text":"Achim Schilling, Claus Metzner, Dennis Voelkl, Marius E. Yamakou, Patrick Krauss","submitted_at":"2023-01-30T13:52:39Z","abstract_excerpt":"Free-running Recurrent Neural Networks (RNNs), especially probabilistic models, generate an ongoing information flux that can be quantified with the mutual information $I\\left[\\vec{x}(t),\\vec{x}(t\\!+\\!1)\\right]$ between subsequent system states $\\vec{x}$. Although, former studies have shown that $I$ depends on the statistics of the network's connection weights, it is unclear (1) how to maximize $I$ systematically and (2) how to quantify the flux in large systems where computing the mutual information becomes intractable. Here, we address these questions using Boltzmann machines as model system"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12892","kind":"arxiv","version":2},"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/2301.12892/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":"2301.12892","created_at":"2026-07-05T07:01:38.939681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12892v2","created_at":"2026-07-05T07:01:38.939681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12892","created_at":"2026-07-05T07:01:38.939681+00:00"},{"alias_kind":"pith_short_12","alias_value":"WF4EWT4O6ZFE","created_at":"2026-07-05T07:01:38.939681+00:00"},{"alias_kind":"pith_short_16","alias_value":"WF4EWT4O6ZFEJELA","created_at":"2026-07-05T07:01:38.939681+00:00"},{"alias_kind":"pith_short_8","alias_value":"WF4EWT4O","created_at":"2026-07-05T07:01:38.939681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.10072","citing_title":"Author-Specific Linguistic Patterns Unveiled: A Deep Learning Study on Word Class Distributions","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WF4EWT4O6ZFEJELAKUHY6EM6MU","json":"https://pith.science/pith/WF4EWT4O6ZFEJELAKUHY6EM6MU.json","graph_json":"https://pith.science/api/pith-number/WF4EWT4O6ZFEJELAKUHY6EM6MU/graph.json","events_json":"https://pith.science/api/pith-number/WF4EWT4O6ZFEJELAKUHY6EM6MU/events.json","paper":"https://pith.science/paper/WF4EWT4O"},"agent_actions":{"view_html":"https://pith.science/pith/WF4EWT4O6ZFEJELAKUHY6EM6MU","download_json":"https://pith.science/pith/WF4EWT4O6ZFEJELAKUHY6EM6MU.json","view_paper":"https://pith.science/paper/WF4EWT4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12892&json=true","fetch_graph":"https://pith.science/api/pith-number/WF4EWT4O6ZFEJELAKUHY6EM6MU/graph.json","fetch_events":"https://pith.science/api/pith-number/WF4EWT4O6ZFEJELAKUHY6EM6MU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WF4EWT4O6ZFEJELAKUHY6EM6MU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WF4EWT4O6ZFEJELAKUHY6EM6MU/action/storage_attestation","attest_author":"https://pith.science/pith/WF4EWT4O6ZFEJELAKUHY6EM6MU/action/author_attestation","sign_citation":"https://pith.science/pith/WF4EWT4O6ZFEJELAKUHY6EM6MU/action/citation_signature","submit_replication":"https://pith.science/pith/WF4EWT4O6ZFEJELAKUHY6EM6MU/action/replication_record"}},"created_at":"2026-07-05T07:01:38.939681+00:00","updated_at":"2026-07-05T07:01:38.939681+00:00"}