{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:67ZSALW2JXGXBP6T2NIE3WHS5G","short_pith_number":"pith:67ZSALW2","schema_version":"1.0","canonical_sha256":"f7f3202eda4dcd70bfd3d3504dd8f2e9900aad708c0ffacd9ff6ba6c55112bad","source":{"kind":"arxiv","id":"2502.10178","version":2},"attestation_state":"computed","paper":{"title":"From Markov to Laplace: How Mamba In-Context Learns Markov Chains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Ashok Vardhan Makkuva, Caglar Gulcehre, Kannan Ramchandran, Marco Bondaschi, Michael Gastpar, Nived Rajaraman, Razvan Pascanu, Xiuying Wei","submitted_at":"2025-02-14T14:13:55Z","abstract_excerpt":"While transformer-based language models have driven the AI revolution thus far, their computational complexity has spurred growing interest in viable alternatives, such as structured state space sequence models (SSMs) and Selective SSMs. Among these, Mamba (S6) and its variant Mamba-2 have shown remarkable inference speed-ups over transformers while achieving comparable or superior performance on complex language modeling tasks. However, despite these architectural innovations and empirical successes, the fundamental learning capabilities of Mamba remain poorly understood. In this paper, we ad"},"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":"2502.10178","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-14T14:13:55Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"b47a5b7b21cedd27bb099f968248667e5a940ac99a7f4dcabfdaa85a135795bf","abstract_canon_sha256":"23325d9b2bc1aba409b251555f38bbd799c516846b1241188a68012730bfc6a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:27.040524Z","signature_b64":"AY4zDHscYKOjckAQ4A3N/46urJVjDl18nwgmGn1EZPd3K0/8+F969uZYn1eZhFuX3vNxvuTnyUTM1bEc+GhQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7f3202eda4dcd70bfd3d3504dd8f2e9900aad708c0ffacd9ff6ba6c55112bad","last_reissued_at":"2026-06-23T03:14:27.040142Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:27.040142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Markov to Laplace: How Mamba In-Context Learns Markov Chains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Ashok Vardhan Makkuva, Caglar Gulcehre, Kannan Ramchandran, Marco Bondaschi, Michael Gastpar, Nived Rajaraman, Razvan Pascanu, Xiuying Wei","submitted_at":"2025-02-14T14:13:55Z","abstract_excerpt":"While transformer-based language models have driven the AI revolution thus far, their computational complexity has spurred growing interest in viable alternatives, such as structured state space sequence models (SSMs) and Selective SSMs. Among these, Mamba (S6) and its variant Mamba-2 have shown remarkable inference speed-ups over transformers while achieving comparable or superior performance on complex language modeling tasks. However, despite these architectural innovations and empirical successes, the fundamental learning capabilities of Mamba remain poorly understood. In this paper, we ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10178","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/2502.10178/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":"2502.10178","created_at":"2026-06-23T03:14:27.040204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10178v2","created_at":"2026-06-23T03:14:27.040204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10178","created_at":"2026-06-23T03:14:27.040204+00:00"},{"alias_kind":"pith_short_12","alias_value":"67ZSALW2JXGX","created_at":"2026-06-23T03:14:27.040204+00:00"},{"alias_kind":"pith_short_16","alias_value":"67ZSALW2JXGXBP6T","created_at":"2026-06-23T03:14:27.040204+00:00"},{"alias_kind":"pith_short_8","alias_value":"67ZSALW2","created_at":"2026-06-23T03:14:27.040204+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/67ZSALW2JXGXBP6T2NIE3WHS5G","json":"https://pith.science/pith/67ZSALW2JXGXBP6T2NIE3WHS5G.json","graph_json":"https://pith.science/api/pith-number/67ZSALW2JXGXBP6T2NIE3WHS5G/graph.json","events_json":"https://pith.science/api/pith-number/67ZSALW2JXGXBP6T2NIE3WHS5G/events.json","paper":"https://pith.science/paper/67ZSALW2"},"agent_actions":{"view_html":"https://pith.science/pith/67ZSALW2JXGXBP6T2NIE3WHS5G","download_json":"https://pith.science/pith/67ZSALW2JXGXBP6T2NIE3WHS5G.json","view_paper":"https://pith.science/paper/67ZSALW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10178&json=true","fetch_graph":"https://pith.science/api/pith-number/67ZSALW2JXGXBP6T2NIE3WHS5G/graph.json","fetch_events":"https://pith.science/api/pith-number/67ZSALW2JXGXBP6T2NIE3WHS5G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67ZSALW2JXGXBP6T2NIE3WHS5G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67ZSALW2JXGXBP6T2NIE3WHS5G/action/storage_attestation","attest_author":"https://pith.science/pith/67ZSALW2JXGXBP6T2NIE3WHS5G/action/author_attestation","sign_citation":"https://pith.science/pith/67ZSALW2JXGXBP6T2NIE3WHS5G/action/citation_signature","submit_replication":"https://pith.science/pith/67ZSALW2JXGXBP6T2NIE3WHS5G/action/replication_record"}},"created_at":"2026-06-23T03:14:27.040204+00:00","updated_at":"2026-06-23T03:14:27.040204+00:00"}