{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KB6AIX3LJ4AOK2WNZNOCX4NN42","short_pith_number":"pith:KB6AIX3L","schema_version":"1.0","canonical_sha256":"507c045f6b4f00e56acdcb5c2bf1ade691bd93b97b44449a8d08f212024db309","source":{"kind":"arxiv","id":"2605.16048","version":1},"attestation_state":"computed","paper":{"title":"Looped SSMs: Depth-Recurrence and Input Reshaping for Time Series Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniela Rus, M\\'onika Farsang, Radu Grosu, Ramin Hasani","submitted_at":"2026-05-15T15:18:12Z","abstract_excerpt":"State Space Models (SSMs) are inherently recurrent along the sequence dimension, yet depth-recurrence - reusing the same block repeatedly across layers, as recently applied in looped transformers - has not been explored in this model family. We show that a looped SSM with $k$ parameters iterated $L$ times consistently closely matches or outperforms a standard SSM with $k \\cdot L$ independent parameters across four architectures (LRU, S5, LinOSS, LrcSSM) and six time series classification benchmarks, despite operating within a strictly smaller hypothesis space, as we formally establish. Since t"},"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":"2605.16048","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T15:18:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d97cba6865a67c6780932904c6da2767642a3c44cd0bdd1a2a68ee91dd86092","abstract_canon_sha256":"9105eb8dea30567b7a0360242991991a7b17d7942ec8228fc9fda5d9ae7dca10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:50.621589Z","signature_b64":"8pLyFk3cve6KE8243YHNOtWxmQUuUYGBq4e8TLa7rPPAG5lk9KKGoZKSPdTV6Mk85maBc3BsMusaa83+ijlRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"507c045f6b4f00e56acdcb5c2bf1ade691bd93b97b44449a8d08f212024db309","last_reissued_at":"2026-05-20T00:01:50.621007Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:50.621007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Looped SSMs: Depth-Recurrence and Input Reshaping for Time Series Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniela Rus, M\\'onika Farsang, Radu Grosu, Ramin Hasani","submitted_at":"2026-05-15T15:18:12Z","abstract_excerpt":"State Space Models (SSMs) are inherently recurrent along the sequence dimension, yet depth-recurrence - reusing the same block repeatedly across layers, as recently applied in looped transformers - has not been explored in this model family. We show that a looped SSM with $k$ parameters iterated $L$ times consistently closely matches or outperforms a standard SSM with $k \\cdot L$ independent parameters across four architectures (LRU, S5, LinOSS, LrcSSM) and six time series classification benchmarks, despite operating within a strictly smaller hypothesis space, as we formally establish. Since t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16048","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/2605.16048/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:41.556824Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.530775Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9e719061d769c3ce68e0cb5f7679ad22bc9c9c68ae6867fe5dd7b5730b12fae1"},"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":"2605.16048","created_at":"2026-05-20T00:01:50.621084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16048v1","created_at":"2026-05-20T00:01:50.621084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16048","created_at":"2026-05-20T00:01:50.621084+00:00"},{"alias_kind":"pith_short_12","alias_value":"KB6AIX3LJ4AO","created_at":"2026-05-20T00:01:50.621084+00:00"},{"alias_kind":"pith_short_16","alias_value":"KB6AIX3LJ4AOK2WN","created_at":"2026-05-20T00:01:50.621084+00:00"},{"alias_kind":"pith_short_8","alias_value":"KB6AIX3L","created_at":"2026-05-20T00:01:50.621084+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/KB6AIX3LJ4AOK2WNZNOCX4NN42","json":"https://pith.science/pith/KB6AIX3LJ4AOK2WNZNOCX4NN42.json","graph_json":"https://pith.science/api/pith-number/KB6AIX3LJ4AOK2WNZNOCX4NN42/graph.json","events_json":"https://pith.science/api/pith-number/KB6AIX3LJ4AOK2WNZNOCX4NN42/events.json","paper":"https://pith.science/paper/KB6AIX3L"},"agent_actions":{"view_html":"https://pith.science/pith/KB6AIX3LJ4AOK2WNZNOCX4NN42","download_json":"https://pith.science/pith/KB6AIX3LJ4AOK2WNZNOCX4NN42.json","view_paper":"https://pith.science/paper/KB6AIX3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16048&json=true","fetch_graph":"https://pith.science/api/pith-number/KB6AIX3LJ4AOK2WNZNOCX4NN42/graph.json","fetch_events":"https://pith.science/api/pith-number/KB6AIX3LJ4AOK2WNZNOCX4NN42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KB6AIX3LJ4AOK2WNZNOCX4NN42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KB6AIX3LJ4AOK2WNZNOCX4NN42/action/storage_attestation","attest_author":"https://pith.science/pith/KB6AIX3LJ4AOK2WNZNOCX4NN42/action/author_attestation","sign_citation":"https://pith.science/pith/KB6AIX3LJ4AOK2WNZNOCX4NN42/action/citation_signature","submit_replication":"https://pith.science/pith/KB6AIX3LJ4AOK2WNZNOCX4NN42/action/replication_record"}},"created_at":"2026-05-20T00:01:50.621084+00:00","updated_at":"2026-05-20T00:01:50.621084+00:00"}