{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:V6XONEXSXSB4VTP4CF3GHEXJ55","short_pith_number":"pith:V6XONEXS","schema_version":"1.0","canonical_sha256":"afaee692f2bc83cacdfc11766392e9ef460e880c8b9d8f8feb4675289152ad53","source":{"kind":"arxiv","id":"2108.01210","version":1},"attestation_state":"computed","paper":{"title":"Representation learning for neural population activity with Neural Data Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.NC","authors_text":"Chethan Pandarinath, Joel Ye","submitted_at":"2021-08-02T23:36:39Z","abstract_excerpt":"Neural population activity is theorized to reflect an underlying dynamical structure. This structure can be accurately captured using state space models with explicit dynamics, such as those based on recurrent neural networks (RNNs). However, using recurrence to explicitly model dynamics necessitates sequential processing of data, slowing real-time applications such as brain-computer interfaces. Here we introduce the Neural Data Transformer (NDT), a non-recurrent alternative. We test the NDT's ability to capture autonomous dynamical systems by applying it to synthetic datasets with known dynam"},"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":"2108.01210","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"q-bio.NC","submitted_at":"2021-08-02T23:36:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fe773099791fb9686790701c6b52d3329e63e51643490b1aef5ca550c2fb6d8a","abstract_canon_sha256":"1ec075d7b4ba4ee2a12b94353cdd1d2b3a1579812ef83959709ee20cb1c86832"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:01.263376Z","signature_b64":"D0s63PkhxfgaFOzrt6cPHlUbXVJ7m+bKTIoSbYMSvk0P290o2W1dSuPWq6wj8QteDhWYTxGFRAjUqwSpoX6OBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afaee692f2bc83cacdfc11766392e9ef460e880c8b9d8f8feb4675289152ad53","last_reissued_at":"2026-07-05T06:33:01.262878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:01.262878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representation learning for neural population activity with Neural Data Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.NC","authors_text":"Chethan Pandarinath, Joel Ye","submitted_at":"2021-08-02T23:36:39Z","abstract_excerpt":"Neural population activity is theorized to reflect an underlying dynamical structure. This structure can be accurately captured using state space models with explicit dynamics, such as those based on recurrent neural networks (RNNs). However, using recurrence to explicitly model dynamics necessitates sequential processing of data, slowing real-time applications such as brain-computer interfaces. Here we introduce the Neural Data Transformer (NDT), a non-recurrent alternative. We test the NDT's ability to capture autonomous dynamical systems by applying it to synthetic datasets with known dynam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01210","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/2108.01210/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":"2108.01210","created_at":"2026-07-05T06:33:01.262937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.01210v1","created_at":"2026-07-05T06:33:01.262937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01210","created_at":"2026-07-05T06:33:01.262937+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6XONEXSXSB4","created_at":"2026-07-05T06:33:01.262937+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6XONEXSXSB4VTP4","created_at":"2026-07-05T06:33:01.262937+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6XONEXS","created_at":"2026-07-05T06:33:01.262937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12992","citing_title":"SpikeProphecy: A Large-Scale Benchmark for Autoregressive Neural Population Forecasting","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12999","citing_title":"Implicit Behavioral Decoding from Next-Step Spike Forecasts at Population Scale","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04958","citing_title":"CalM: A Self-Supervised Foundation Model for Population Dynamics in Calcium Imaging Data","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18827","citing_title":"OmniMouse: Scaling properties of multi-modal, multi-task Brain Models on 150B Neural Tokens","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V6XONEXSXSB4VTP4CF3GHEXJ55","json":"https://pith.science/pith/V6XONEXSXSB4VTP4CF3GHEXJ55.json","graph_json":"https://pith.science/api/pith-number/V6XONEXSXSB4VTP4CF3GHEXJ55/graph.json","events_json":"https://pith.science/api/pith-number/V6XONEXSXSB4VTP4CF3GHEXJ55/events.json","paper":"https://pith.science/paper/V6XONEXS"},"agent_actions":{"view_html":"https://pith.science/pith/V6XONEXSXSB4VTP4CF3GHEXJ55","download_json":"https://pith.science/pith/V6XONEXSXSB4VTP4CF3GHEXJ55.json","view_paper":"https://pith.science/paper/V6XONEXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.01210&json=true","fetch_graph":"https://pith.science/api/pith-number/V6XONEXSXSB4VTP4CF3GHEXJ55/graph.json","fetch_events":"https://pith.science/api/pith-number/V6XONEXSXSB4VTP4CF3GHEXJ55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6XONEXSXSB4VTP4CF3GHEXJ55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6XONEXSXSB4VTP4CF3GHEXJ55/action/storage_attestation","attest_author":"https://pith.science/pith/V6XONEXSXSB4VTP4CF3GHEXJ55/action/author_attestation","sign_citation":"https://pith.science/pith/V6XONEXSXSB4VTP4CF3GHEXJ55/action/citation_signature","submit_replication":"https://pith.science/pith/V6XONEXSXSB4VTP4CF3GHEXJ55/action/replication_record"}},"created_at":"2026-07-05T06:33:01.262937+00:00","updated_at":"2026-07-05T06:33:01.262937+00:00"}