{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HNOVS3LM3IL7DVD5FVKNNWG2WT","short_pith_number":"pith:HNOVS3LM","schema_version":"1.0","canonical_sha256":"3b5d596d6cda17f1d47d2d54d6d8dab4da28e3023e882707b4699d0e5be11856","source":{"kind":"arxiv","id":"2402.08132","version":2},"attestation_state":"computed","paper":{"title":"On the Resurgence of Recurrent Models for Long Sequences -- Survey and Research Opportunities in the Transformer Era","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Betti, Marco Gori, Matteo Tiezzi, Michele Casoni, Stefano Melacci, Tommaso Guidi","submitted_at":"2024-02-12T23:55:55Z","abstract_excerpt":"A longstanding challenge for the Machine Learning community is the one of developing models that are capable of processing and learning from very long sequences of data. The outstanding results of Transformers-based networks (e.g., Large Language Models) promotes the idea of parallel attention as the key to succeed in such a challenge, obfuscating the role of classic sequential processing of Recurrent Models. However, in the last few years, researchers who were concerned by the quadratic complexity of self-attention have been proposing a novel wave of neural models, which gets the best from th"},"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":"2402.08132","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T23:55:55Z","cross_cats_sorted":[],"title_canon_sha256":"72366b0b3c5a6c08fd1351a4ac875ccc3c70a7a8eb3792db7a8410233c30c19e","abstract_canon_sha256":"174b2a1d593653612efadfdcb10841de18ec5464205d66ee96f109fb34615799"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:00.478792Z","signature_b64":"EBMTcySYJuYnRRNeW8+TvGQ+2WWx2PvQHH2MNNzZLg3FYscyCDRxEFHlDUutJdltoWBpdiMJhAEq/AKYKyL2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b5d596d6cda17f1d47d2d54d6d8dab4da28e3023e882707b4699d0e5be11856","last_reissued_at":"2026-07-05T07:45:00.478045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:00.478045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Resurgence of Recurrent Models for Long Sequences -- Survey and Research Opportunities in the Transformer Era","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Betti, Marco Gori, Matteo Tiezzi, Michele Casoni, Stefano Melacci, Tommaso Guidi","submitted_at":"2024-02-12T23:55:55Z","abstract_excerpt":"A longstanding challenge for the Machine Learning community is the one of developing models that are capable of processing and learning from very long sequences of data. The outstanding results of Transformers-based networks (e.g., Large Language Models) promotes the idea of parallel attention as the key to succeed in such a challenge, obfuscating the role of classic sequential processing of Recurrent Models. However, in the last few years, researchers who were concerned by the quadratic complexity of self-attention have been proposing a novel wave of neural models, which gets the best from th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08132","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/2402.08132/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":"2402.08132","created_at":"2026-07-05T07:45:00.478294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.08132v2","created_at":"2026-07-05T07:45:00.478294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08132","created_at":"2026-07-05T07:45:00.478294+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNOVS3LM3IL7","created_at":"2026-07-05T07:45:00.478294+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNOVS3LM3IL7DVD5","created_at":"2026-07-05T07:45:00.478294+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNOVS3LM","created_at":"2026-07-05T07:45:00.478294+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23670","citing_title":"Tapered Language Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00663","citing_title":"Titans: Learning to Memorize at Test Time","ref_index":107,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNOVS3LM3IL7DVD5FVKNNWG2WT","json":"https://pith.science/pith/HNOVS3LM3IL7DVD5FVKNNWG2WT.json","graph_json":"https://pith.science/api/pith-number/HNOVS3LM3IL7DVD5FVKNNWG2WT/graph.json","events_json":"https://pith.science/api/pith-number/HNOVS3LM3IL7DVD5FVKNNWG2WT/events.json","paper":"https://pith.science/paper/HNOVS3LM"},"agent_actions":{"view_html":"https://pith.science/pith/HNOVS3LM3IL7DVD5FVKNNWG2WT","download_json":"https://pith.science/pith/HNOVS3LM3IL7DVD5FVKNNWG2WT.json","view_paper":"https://pith.science/paper/HNOVS3LM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.08132&json=true","fetch_graph":"https://pith.science/api/pith-number/HNOVS3LM3IL7DVD5FVKNNWG2WT/graph.json","fetch_events":"https://pith.science/api/pith-number/HNOVS3LM3IL7DVD5FVKNNWG2WT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNOVS3LM3IL7DVD5FVKNNWG2WT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNOVS3LM3IL7DVD5FVKNNWG2WT/action/storage_attestation","attest_author":"https://pith.science/pith/HNOVS3LM3IL7DVD5FVKNNWG2WT/action/author_attestation","sign_citation":"https://pith.science/pith/HNOVS3LM3IL7DVD5FVKNNWG2WT/action/citation_signature","submit_replication":"https://pith.science/pith/HNOVS3LM3IL7DVD5FVKNNWG2WT/action/replication_record"}},"created_at":"2026-07-05T07:45:00.478294+00:00","updated_at":"2026-07-05T07:45:00.478294+00:00"}