{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:REQLGLWQCGYI7SKLMDVNDSY2GX","short_pith_number":"pith:REQLGLWQ","schema_version":"1.0","canonical_sha256":"8920b32ed011b08fc94b60ead1cb1a35c608f2d98491804c769bc77ed371f262","source":{"kind":"arxiv","id":"2406.04303","version":3},"attestation_state":"computed","paper":{"title":"Vision-LSTM: xLSTM as Generic Vision Backbone","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Benedikt Alkin, Johannes Brandstetter, Korbinian P\\\"oppel, Maximilian Beck, Sepp Hochreiter","submitted_at":"2024-06-06T17:49:21Z","abstract_excerpt":"Transformers are widely used as generic backbones in computer vision, despite initially introduced for natural language processing. Recently, the Long Short-Term Memory (LSTM) has been extended to a scalable and performant architecture - the xLSTM - which overcomes long-standing LSTM limitations via exponential gating and parallelizable matrix memory structure. In this report, we introduce Vision-LSTM (ViL), an adaption of the xLSTM building blocks to computer vision. ViL comprises a stack of xLSTM blocks where odd blocks process the sequence of patch tokens from top to bottom while even block"},"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":"2406.04303","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:49:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"01b20f7d988691c7c1446921b2f32297d4f4b21bf5115bb08eb20ec072e9ff49","abstract_canon_sha256":"7a84d687d68365d6b39153db17cc914f7d7ba4fbaba388b89bcb11eb8ac055e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:47.510534Z","signature_b64":"8lBWp2aarnypMmU3Y4+YTiaJP0YnxPZKc43FRwCWi/SQ5pR42qQBsT6RhpXHmFOvs9l0LEaGQ9NbXckV1UhqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8920b32ed011b08fc94b60ead1cb1a35c608f2d98491804c769bc77ed371f262","last_reissued_at":"2026-07-05T10:17:47.510095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:47.510095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-LSTM: xLSTM as Generic Vision Backbone","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Benedikt Alkin, Johannes Brandstetter, Korbinian P\\\"oppel, Maximilian Beck, Sepp Hochreiter","submitted_at":"2024-06-06T17:49:21Z","abstract_excerpt":"Transformers are widely used as generic backbones in computer vision, despite initially introduced for natural language processing. Recently, the Long Short-Term Memory (LSTM) has been extended to a scalable and performant architecture - the xLSTM - which overcomes long-standing LSTM limitations via exponential gating and parallelizable matrix memory structure. In this report, we introduce Vision-LSTM (ViL), an adaption of the xLSTM building blocks to computer vision. ViL comprises a stack of xLSTM blocks where odd blocks process the sequence of patch tokens from top to bottom while even block"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04303","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/2406.04303/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":"2406.04303","created_at":"2026-07-05T10:17:47.510159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04303v3","created_at":"2026-07-05T10:17:47.510159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04303","created_at":"2026-07-05T10:17:47.510159+00:00"},{"alias_kind":"pith_short_12","alias_value":"REQLGLWQCGYI","created_at":"2026-07-05T10:17:47.510159+00:00"},{"alias_kind":"pith_short_16","alias_value":"REQLGLWQCGYI7SKL","created_at":"2026-07-05T10:17:47.510159+00:00"},{"alias_kind":"pith_short_8","alias_value":"REQLGLWQ","created_at":"2026-07-05T10:17:47.510159+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/REQLGLWQCGYI7SKLMDVNDSY2GX","json":"https://pith.science/pith/REQLGLWQCGYI7SKLMDVNDSY2GX.json","graph_json":"https://pith.science/api/pith-number/REQLGLWQCGYI7SKLMDVNDSY2GX/graph.json","events_json":"https://pith.science/api/pith-number/REQLGLWQCGYI7SKLMDVNDSY2GX/events.json","paper":"https://pith.science/paper/REQLGLWQ"},"agent_actions":{"view_html":"https://pith.science/pith/REQLGLWQCGYI7SKLMDVNDSY2GX","download_json":"https://pith.science/pith/REQLGLWQCGYI7SKLMDVNDSY2GX.json","view_paper":"https://pith.science/paper/REQLGLWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04303&json=true","fetch_graph":"https://pith.science/api/pith-number/REQLGLWQCGYI7SKLMDVNDSY2GX/graph.json","fetch_events":"https://pith.science/api/pith-number/REQLGLWQCGYI7SKLMDVNDSY2GX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/REQLGLWQCGYI7SKLMDVNDSY2GX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/REQLGLWQCGYI7SKLMDVNDSY2GX/action/storage_attestation","attest_author":"https://pith.science/pith/REQLGLWQCGYI7SKLMDVNDSY2GX/action/author_attestation","sign_citation":"https://pith.science/pith/REQLGLWQCGYI7SKLMDVNDSY2GX/action/citation_signature","submit_replication":"https://pith.science/pith/REQLGLWQCGYI7SKLMDVNDSY2GX/action/replication_record"}},"created_at":"2026-07-05T10:17:47.510159+00:00","updated_at":"2026-07-05T10:17:47.510159+00:00"}