{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EOKBE5XPMLGOO4BDIUDTN3YTZS","short_pith_number":"pith:EOKBE5XP","canonical_record":{"source":{"id":"2407.07239","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-09T21:37:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1a387174e9195758ce9983f87c28c29a1be83211d1511032799c2b080875a056","abstract_canon_sha256":"ac9975ba3bc2807dba05ffbd64aea939a64e10f4d66f953942a0679c21b8c837"},"schema_version":"1.0"},"canonical_sha256":"23941276ef62cce77023450736ef13cc96cd2fb020f7e6394af04795d84b17a6","source":{"kind":"arxiv","id":"2407.07239","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07239","created_at":"2026-06-25T00:18:10Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07239v3","created_at":"2026-06-25T00:18:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07239","created_at":"2026-06-25T00:18:10Z"},{"alias_kind":"pith_short_12","alias_value":"EOKBE5XPMLGO","created_at":"2026-06-25T00:18:10Z"},{"alias_kind":"pith_short_16","alias_value":"EOKBE5XPMLGOO4BD","created_at":"2026-06-25T00:18:10Z"},{"alias_kind":"pith_short_8","alias_value":"EOKBE5XP","created_at":"2026-06-25T00:18:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EOKBE5XPMLGOO4BDIUDTN3YTZS","target":"record","payload":{"canonical_record":{"source":{"id":"2407.07239","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-09T21:37:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1a387174e9195758ce9983f87c28c29a1be83211d1511032799c2b080875a056","abstract_canon_sha256":"ac9975ba3bc2807dba05ffbd64aea939a64e10f4d66f953942a0679c21b8c837"},"schema_version":"1.0"},"canonical_sha256":"23941276ef62cce77023450736ef13cc96cd2fb020f7e6394af04795d84b17a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:18:10.767346Z","signature_b64":"KeXV7yf6prgABYF6D+UALteizLlQgN//VD/ot6Jwk3Drl+WV/OShWGzrEavoAVTsWmmj+01CWHlmYbctE2JbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23941276ef62cce77023450736ef13cc96cd2fb020f7e6394af04795d84b17a6","last_reissued_at":"2026-06-25T00:18:10.766794Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:18:10.766794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.07239","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-25T00:18:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xdYwyuCc5/wRR9aS5qi2FQirb0Zrwhhu05sFGIK8wSADddflBmJl3B6sLZFwYpWrQLlT1jAO/aN6/gNLad7iBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T19:14:14.654172Z"},"content_sha256":"cc8d86cd296798aa4549983ad212904ba2bd257261b154a30341812ccc4babfe","schema_version":"1.0","event_id":"sha256:cc8d86cd296798aa4549983ad212904ba2bd257261b154a30341812ccc4babfe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EOKBE5XPMLGOO4BDIUDTN3YTZS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RotRNN: Modelling Long Sequences with Rotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Barber, Jake Cunningham, Kai Biegun, Rares Dolga","submitted_at":"2024-07-09T21:37:36Z","abstract_excerpt":"Linear recurrent neural networks, such as State Space Models (SSMs) and Linear Recurrent Units (LRUs), have recently shown state-of-the-art performance on long sequence modelling benchmarks. Despite their success, their empirical performance is not well understood and they come with a number of drawbacks, most notably their complex initialisation and normalisation schemes. In this work, we address some of these issues by proposing RotRNN -- a linear recurrent model which utilises the convenient properties of rotation matrices. We show that RotRNN provides a simple and efficient model with a ro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07239","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/2407.07239/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-25T00:18:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OPIMb5Mg/KlMi2S5AFRkJyv5bCXyghSRtIZ+8T+IiYMGuXpCH9OXUJGE3zDIvotbkYR14cc/V6Oupd7jzBzqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T19:14:14.654552Z"},"content_sha256":"600b09516ef9377f94f8acbe98e9f441713d9aeb72241f05d82618b7b40f0734","schema_version":"1.0","event_id":"sha256:600b09516ef9377f94f8acbe98e9f441713d9aeb72241f05d82618b7b40f0734"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EOKBE5XPMLGOO4BDIUDTN3YTZS/bundle.json","state_url":"https://pith.science/pith/EOKBE5XPMLGOO4BDIUDTN3YTZS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EOKBE5XPMLGOO4BDIUDTN3YTZS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-27T19:14:14Z","links":{"resolver":"https://pith.science/pith/EOKBE5XPMLGOO4BDIUDTN3YTZS","bundle":"https://pith.science/pith/EOKBE5XPMLGOO4BDIUDTN3YTZS/bundle.json","state":"https://pith.science/pith/EOKBE5XPMLGOO4BDIUDTN3YTZS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EOKBE5XPMLGOO4BDIUDTN3YTZS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EOKBE5XPMLGOO4BDIUDTN3YTZS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ac9975ba3bc2807dba05ffbd64aea939a64e10f4d66f953942a0679c21b8c837","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-09T21:37:36Z","title_canon_sha256":"1a387174e9195758ce9983f87c28c29a1be83211d1511032799c2b080875a056"},"schema_version":"1.0","source":{"id":"2407.07239","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07239","created_at":"2026-06-25T00:18:10Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07239v3","created_at":"2026-06-25T00:18:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07239","created_at":"2026-06-25T00:18:10Z"},{"alias_kind":"pith_short_12","alias_value":"EOKBE5XPMLGO","created_at":"2026-06-25T00:18:10Z"},{"alias_kind":"pith_short_16","alias_value":"EOKBE5XPMLGOO4BD","created_at":"2026-06-25T00:18:10Z"},{"alias_kind":"pith_short_8","alias_value":"EOKBE5XP","created_at":"2026-06-25T00:18:10Z"}],"graph_snapshots":[{"event_id":"sha256:600b09516ef9377f94f8acbe98e9f441713d9aeb72241f05d82618b7b40f0734","target":"graph","created_at":"2026-06-25T00:18:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.07239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Linear recurrent neural networks, such as State Space Models (SSMs) and Linear Recurrent Units (LRUs), have recently shown state-of-the-art performance on long sequence modelling benchmarks. Despite their success, their empirical performance is not well understood and they come with a number of drawbacks, most notably their complex initialisation and normalisation schemes. In this work, we address some of these issues by proposing RotRNN -- a linear recurrent model which utilises the convenient properties of rotation matrices. We show that RotRNN provides a simple and efficient model with a ro","authors_text":"David Barber, Jake Cunningham, Kai Biegun, Rares Dolga","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-09T21:37:36Z","title":"RotRNN: Modelling Long Sequences with Rotations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07239","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cc8d86cd296798aa4549983ad212904ba2bd257261b154a30341812ccc4babfe","target":"record","created_at":"2026-06-25T00:18:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ac9975ba3bc2807dba05ffbd64aea939a64e10f4d66f953942a0679c21b8c837","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-09T21:37:36Z","title_canon_sha256":"1a387174e9195758ce9983f87c28c29a1be83211d1511032799c2b080875a056"},"schema_version":"1.0","source":{"id":"2407.07239","kind":"arxiv","version":3}},"canonical_sha256":"23941276ef62cce77023450736ef13cc96cd2fb020f7e6394af04795d84b17a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23941276ef62cce77023450736ef13cc96cd2fb020f7e6394af04795d84b17a6","first_computed_at":"2026-06-25T00:18:10.766794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T00:18:10.766794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KeXV7yf6prgABYF6D+UALteizLlQgN//VD/ot6Jwk3Drl+WV/OShWGzrEavoAVTsWmmj+01CWHlmYbctE2JbCQ==","signature_status":"signed_v1","signed_at":"2026-06-25T00:18:10.767346Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.07239","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc8d86cd296798aa4549983ad212904ba2bd257261b154a30341812ccc4babfe","sha256:600b09516ef9377f94f8acbe98e9f441713d9aeb72241f05d82618b7b40f0734"],"state_sha256":"c43f33b7b0343764030d7e1aef1de29ac86d55fc6380711b54db37596d737bc3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h7NmPbNg7fqt0tM8EtU4ijiJyDGr0d26QK6ick/Qfkm+UnK6B13TAEchsKCpl6XHzUa9QeAjBVMYriKFdsVsBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T19:14:14.656496Z","bundle_sha256":"507dbfe9185adb8d2747a4ae203e6595d48925f346dac0a4343b0d09672fca7b"}}