{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3TMVUMHT2Y444ACGIRWMS422JJ","short_pith_number":"pith:3TMVUMHT","schema_version":"1.0","canonical_sha256":"dcd95a30f3d639ce0046446cc9735a4a48bf42e338a861077cc5bb548fd57a10","source":{"kind":"arxiv","id":"2608.01947","version":1},"attestation_state":"computed","paper":{"title":"Divisive Normalization Shapes Low-Rank Slow Manifolds for Continuous Working Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"q-bio.NC","authors_text":"Chang Liu, Dahui Wang, Jie Su, Tianyi Qian, Weiwei Wang, Zhaotian Gu","submitted_at":"2026-08-03T09:20:05Z","abstract_excerpt":"The ability to robustly maintain and update continuous variables is a hallmark of working memory. While classical continuous attractor networks suffer from severe fine-tuning fragility, standard artificial recurrent neural networks (RNNs) like GRUs and LSTMs typically fail to stably learn continuous manifolds, instead shattering the state space into discretized point attractors. To bridge this gap, we draw inspiration from divisive normalization, a canonical neural computation widely observed across cortical circuits, and propose the Recurrent Divisive Normalization Network (RDNN), a minimal a"},"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":"2608.01947","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.NC","submitted_at":"2026-08-03T09:20:05Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"28b86988c719eaf5a4987cce24a6660522beed8577e7ec5cf26cfdddb735dfe5","abstract_canon_sha256":"5a22e0ece528ec7bb407ea2f58b9b7f05ff3061628472732e565469989b59af1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:10:13.527859Z","signature_b64":"UG4GY+4l3OsFyrtNlu9OogH1ZZLp8fvAWVoAnfLFH9KNP2Qp/cBqXcTzd82A4zV1EyJBnB8dRF5hXLp0n3juAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcd95a30f3d639ce0046446cc9735a4a48bf42e338a861077cc5bb548fd57a10","last_reissued_at":"2026-08-04T02:10:13.525855Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:10:13.525855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Divisive Normalization Shapes Low-Rank Slow Manifolds for Continuous Working Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"q-bio.NC","authors_text":"Chang Liu, Dahui Wang, Jie Su, Tianyi Qian, Weiwei Wang, Zhaotian Gu","submitted_at":"2026-08-03T09:20:05Z","abstract_excerpt":"The ability to robustly maintain and update continuous variables is a hallmark of working memory. While classical continuous attractor networks suffer from severe fine-tuning fragility, standard artificial recurrent neural networks (RNNs) like GRUs and LSTMs typically fail to stably learn continuous manifolds, instead shattering the state space into discretized point attractors. To bridge this gap, we draw inspiration from divisive normalization, a canonical neural computation widely observed across cortical circuits, and propose the Recurrent Divisive Normalization Network (RDNN), a minimal a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01947","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/2608.01947/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":"2608.01947","created_at":"2026-08-04T02:10:13.527415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01947v1","created_at":"2026-08-04T02:10:13.527415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01947","created_at":"2026-08-04T02:10:13.527415+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TMVUMHT2Y44","created_at":"2026-08-04T02:10:13.527415+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TMVUMHT2Y444ACG","created_at":"2026-08-04T02:10:13.527415+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TMVUMHT","created_at":"2026-08-04T02:10:13.527415+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/3TMVUMHT2Y444ACGIRWMS422JJ","json":"https://pith.science/pith/3TMVUMHT2Y444ACGIRWMS422JJ.json","graph_json":"https://pith.science/api/pith-number/3TMVUMHT2Y444ACGIRWMS422JJ/graph.json","events_json":"https://pith.science/api/pith-number/3TMVUMHT2Y444ACGIRWMS422JJ/events.json","paper":"https://pith.science/paper/3TMVUMHT"},"agent_actions":{"view_html":"https://pith.science/pith/3TMVUMHT2Y444ACGIRWMS422JJ","download_json":"https://pith.science/pith/3TMVUMHT2Y444ACGIRWMS422JJ.json","view_paper":"https://pith.science/paper/3TMVUMHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01947&json=true","fetch_graph":"https://pith.science/api/pith-number/3TMVUMHT2Y444ACGIRWMS422JJ/graph.json","fetch_events":"https://pith.science/api/pith-number/3TMVUMHT2Y444ACGIRWMS422JJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TMVUMHT2Y444ACGIRWMS422JJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TMVUMHT2Y444ACGIRWMS422JJ/action/storage_attestation","attest_author":"https://pith.science/pith/3TMVUMHT2Y444ACGIRWMS422JJ/action/author_attestation","sign_citation":"https://pith.science/pith/3TMVUMHT2Y444ACGIRWMS422JJ/action/citation_signature","submit_replication":"https://pith.science/pith/3TMVUMHT2Y444ACGIRWMS422JJ/action/replication_record"}},"created_at":"2026-08-04T02:10:13.527415+00:00","updated_at":"2026-08-04T02:10:13.527415+00:00"}