{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LMR3LQ4HHR7DZXWYYBWNHQQQDP","short_pith_number":"pith:LMR3LQ4H","schema_version":"1.0","canonical_sha256":"5b23b5c3873c7e3cded8c06cd3c2101bc878a2cc8fc69e54b52161006d0f4906","source":{"kind":"arxiv","id":"2411.14489","version":1},"attestation_state":"computed","paper":{"title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Hang Zhou, Kai Han, Michael Bi Mi, Xiaoxu Zheng, Yunhe Wang","submitted_at":"2024-11-20T11:37:14Z","abstract_excerpt":"Recurrent neural network (RNNs) that are capable of modeling long-distance dependencies are widely used in various speech tasks, eg., keyword spotting (KWS) and speech enhancement (SE). Due to the limitation of power and memory in low-resource devices, efficient RNN models are urgently required for real-world applications. In this paper, we propose an efficient RNN architecture, GhostRNN, which reduces hidden state redundancy with cheap operations. In particular, we observe that partial dimensions of hidden states are similar to the others in trained RNN models, suggesting that redundancy exis"},"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":"2411.14489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-20T11:37:14Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"a8e56c34dd95f9f051fe08d0a599b521bf3b62d96258dff71a66151ddbe37b1c","abstract_canon_sha256":"504678530e7a52f4036de61723ee61f06b71d5a1b4eff45246d674f9a1777ab2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:52.073454Z","signature_b64":"BX6TVmGPape7KAPw76eaSAS9z8wEF+Eo4jE01J9zYeOBkCxo4sT+6p7u5KpuHcQq3mqrCvxTAiax6GDRR3FeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b23b5c3873c7e3cded8c06cd3c2101bc878a2cc8fc69e54b52161006d0f4906","last_reissued_at":"2026-07-05T09:38:52.072978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:52.072978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Hang Zhou, Kai Han, Michael Bi Mi, Xiaoxu Zheng, Yunhe Wang","submitted_at":"2024-11-20T11:37:14Z","abstract_excerpt":"Recurrent neural network (RNNs) that are capable of modeling long-distance dependencies are widely used in various speech tasks, eg., keyword spotting (KWS) and speech enhancement (SE). Due to the limitation of power and memory in low-resource devices, efficient RNN models are urgently required for real-world applications. In this paper, we propose an efficient RNN architecture, GhostRNN, which reduces hidden state redundancy with cheap operations. In particular, we observe that partial dimensions of hidden states are similar to the others in trained RNN models, suggesting that redundancy exis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14489","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/2411.14489/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":"2411.14489","created_at":"2026-07-05T09:38:52.073041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14489v1","created_at":"2026-07-05T09:38:52.073041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14489","created_at":"2026-07-05T09:38:52.073041+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMR3LQ4HHR7D","created_at":"2026-07-05T09:38:52.073041+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMR3LQ4HHR7DZXWY","created_at":"2026-07-05T09:38:52.073041+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMR3LQ4H","created_at":"2026-07-05T09:38:52.073041+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/LMR3LQ4HHR7DZXWYYBWNHQQQDP","json":"https://pith.science/pith/LMR3LQ4HHR7DZXWYYBWNHQQQDP.json","graph_json":"https://pith.science/api/pith-number/LMR3LQ4HHR7DZXWYYBWNHQQQDP/graph.json","events_json":"https://pith.science/api/pith-number/LMR3LQ4HHR7DZXWYYBWNHQQQDP/events.json","paper":"https://pith.science/paper/LMR3LQ4H"},"agent_actions":{"view_html":"https://pith.science/pith/LMR3LQ4HHR7DZXWYYBWNHQQQDP","download_json":"https://pith.science/pith/LMR3LQ4HHR7DZXWYYBWNHQQQDP.json","view_paper":"https://pith.science/paper/LMR3LQ4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14489&json=true","fetch_graph":"https://pith.science/api/pith-number/LMR3LQ4HHR7DZXWYYBWNHQQQDP/graph.json","fetch_events":"https://pith.science/api/pith-number/LMR3LQ4HHR7DZXWYYBWNHQQQDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMR3LQ4HHR7DZXWYYBWNHQQQDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMR3LQ4HHR7DZXWYYBWNHQQQDP/action/storage_attestation","attest_author":"https://pith.science/pith/LMR3LQ4HHR7DZXWYYBWNHQQQDP/action/author_attestation","sign_citation":"https://pith.science/pith/LMR3LQ4HHR7DZXWYYBWNHQQQDP/action/citation_signature","submit_replication":"https://pith.science/pith/LMR3LQ4HHR7DZXWYYBWNHQQQDP/action/replication_record"}},"created_at":"2026-07-05T09:38:52.073041+00:00","updated_at":"2026-07-05T09:38:52.073041+00:00"}