{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5ORKOYN2G6K4XLHLRIKFLVJCID","short_pith_number":"pith:5ORKOYN2","schema_version":"1.0","canonical_sha256":"eba2a761ba3795cbaceb8a1455d52240dd7cc6a04a0bcab046df7def687eb227","source":{"kind":"arxiv","id":"2405.15731","version":3},"attestation_state":"computed","paper":{"title":"Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Alexandre Didier, Antonio Orvieto, Carmen Amo Alonso, Jerome Sieber, Melanie N. Zeilinger","submitted_at":"2024-05-24T17:19:57Z","abstract_excerpt":"Softmax attention is the principle backbone of foundation models for various artificial intelligence applications, yet its quadratic complexity in sequence length can limit its inference throughput in long-context settings. To address this challenge, alternative architectures such as linear attention, State Space Models (SSMs), and Recurrent Neural Networks (RNNs) have been considered as more efficient alternatives. While connections between these approaches exist, such models are commonly developed in isolation and there is a lack of theoretical understanding of the shared principles underpin"},"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":"2405.15731","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T17:19:57Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"7ac20d1eadb416d989eb62f100bff524f2909b7c44647e083968c84ef0761615","abstract_canon_sha256":"30a2cfa1981c774f003856015e5c3fcbc3647c4455cacc31157446f994b8f212"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:49.230216Z","signature_b64":"Sn9pDA5M+kQz/f7DPxgmRxp27+rN7QZ6V3nqNlTgCL94FfSpfbgwffqwP4re+8UYsh+d1X2KusRMrNn9cROSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eba2a761ba3795cbaceb8a1455d52240dd7cc6a04a0bcab046df7def687eb227","last_reissued_at":"2026-07-05T09:45:49.229726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:49.229726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Alexandre Didier, Antonio Orvieto, Carmen Amo Alonso, Jerome Sieber, Melanie N. Zeilinger","submitted_at":"2024-05-24T17:19:57Z","abstract_excerpt":"Softmax attention is the principle backbone of foundation models for various artificial intelligence applications, yet its quadratic complexity in sequence length can limit its inference throughput in long-context settings. To address this challenge, alternative architectures such as linear attention, State Space Models (SSMs), and Recurrent Neural Networks (RNNs) have been considered as more efficient alternatives. While connections between these approaches exist, such models are commonly developed in isolation and there is a lack of theoretical understanding of the shared principles underpin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15731","kind":"arxiv","version":3},"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/2405.15731/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":"2405.15731","created_at":"2026-07-05T09:45:49.229784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15731v3","created_at":"2026-07-05T09:45:49.229784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15731","created_at":"2026-07-05T09:45:49.229784+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ORKOYN2G6K4","created_at":"2026-07-05T09:45:49.229784+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ORKOYN2G6K4XLHL","created_at":"2026-07-05T09:45:49.229784+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ORKOYN2","created_at":"2026-07-05T09:45:49.229784+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.04154","citing_title":"Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ORKOYN2G6K4XLHLRIKFLVJCID","json":"https://pith.science/pith/5ORKOYN2G6K4XLHLRIKFLVJCID.json","graph_json":"https://pith.science/api/pith-number/5ORKOYN2G6K4XLHLRIKFLVJCID/graph.json","events_json":"https://pith.science/api/pith-number/5ORKOYN2G6K4XLHLRIKFLVJCID/events.json","paper":"https://pith.science/paper/5ORKOYN2"},"agent_actions":{"view_html":"https://pith.science/pith/5ORKOYN2G6K4XLHLRIKFLVJCID","download_json":"https://pith.science/pith/5ORKOYN2G6K4XLHLRIKFLVJCID.json","view_paper":"https://pith.science/paper/5ORKOYN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15731&json=true","fetch_graph":"https://pith.science/api/pith-number/5ORKOYN2G6K4XLHLRIKFLVJCID/graph.json","fetch_events":"https://pith.science/api/pith-number/5ORKOYN2G6K4XLHLRIKFLVJCID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ORKOYN2G6K4XLHLRIKFLVJCID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ORKOYN2G6K4XLHLRIKFLVJCID/action/storage_attestation","attest_author":"https://pith.science/pith/5ORKOYN2G6K4XLHLRIKFLVJCID/action/author_attestation","sign_citation":"https://pith.science/pith/5ORKOYN2G6K4XLHLRIKFLVJCID/action/citation_signature","submit_replication":"https://pith.science/pith/5ORKOYN2G6K4XLHLRIKFLVJCID/action/replication_record"}},"created_at":"2026-07-05T09:45:49.229784+00:00","updated_at":"2026-07-05T09:45:49.229784+00:00"}