{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4EQTUTSEJBZLQILQI2RNMELVCN","short_pith_number":"pith:4EQTUTSE","schema_version":"1.0","canonical_sha256":"e1213a4e444872b8217046a2d611751357918be00a5eafd12a07d88de0a3c404","source":{"kind":"arxiv","id":"2510.00399","version":2},"attestation_state":"computed","paper":{"title":"How Can Mamba Learn In Context with Outliers and Generalize Provably?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongkang Li, Meng Wang, Pin-Yu Chen, Songtao Lu, Xiaodong Cui","submitted_at":"2025-10-01T01:25:01Z","abstract_excerpt":"The Mamba model has gained significant attention for its computational advantages over Transformer-based models, while achieving comparable performance across a wide range of language tasks. Like Transformers, Mamba exhibits in-context learning (ICL) capabilities, i.e., making predictions for new tasks based on a prompt containing input-label pairs and a query, without requiring fine-tuning. Despite its empirical success, the theoretical understanding of Mamba remains limited, largely due to the nonlinearity introduced by its gating mechanism. To the best of our knowledge, this paper presents "},"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":"2510.00399","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-01T01:25:01Z","cross_cats_sorted":[],"title_canon_sha256":"944850128184d2ceb8efe097e22ce06ad59682e2291345af9febe3abfecb08b1","abstract_canon_sha256":"520d11755ebee56589b692de51e127697b36ba3f16af5a34a22518053bb151b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:20.595137Z","signature_b64":"Y3tEEVsw9ikA3RuY2o1jUTR7nu9+DxBNf/HwfMK7jYxJYm+wrbqW3LFp6g7W2nm6Uo/PkF7+vk26395AfXbvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1213a4e444872b8217046a2d611751357918be00a5eafd12a07d88de0a3c404","last_reissued_at":"2026-07-08T01:18:20.594509Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:20.594509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Can Mamba Learn In Context with Outliers and Generalize Provably?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongkang Li, Meng Wang, Pin-Yu Chen, Songtao Lu, Xiaodong Cui","submitted_at":"2025-10-01T01:25:01Z","abstract_excerpt":"The Mamba model has gained significant attention for its computational advantages over Transformer-based models, while achieving comparable performance across a wide range of language tasks. Like Transformers, Mamba exhibits in-context learning (ICL) capabilities, i.e., making predictions for new tasks based on a prompt containing input-label pairs and a query, without requiring fine-tuning. Despite its empirical success, the theoretical understanding of Mamba remains limited, largely due to the nonlinearity introduced by its gating mechanism. To the best of our knowledge, this paper presents "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.00399","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/2510.00399/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":"2510.00399","created_at":"2026-07-08T01:18:20.594586+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.00399v2","created_at":"2026-07-08T01:18:20.594586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.00399","created_at":"2026-07-08T01:18:20.594586+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EQTUTSEJBZL","created_at":"2026-07-08T01:18:20.594586+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EQTUTSEJBZLQILQ","created_at":"2026-07-08T01:18:20.594586+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EQTUTSE","created_at":"2026-07-08T01:18:20.594586+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.10074","citing_title":"Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4EQTUTSEJBZLQILQI2RNMELVCN","json":"https://pith.science/pith/4EQTUTSEJBZLQILQI2RNMELVCN.json","graph_json":"https://pith.science/api/pith-number/4EQTUTSEJBZLQILQI2RNMELVCN/graph.json","events_json":"https://pith.science/api/pith-number/4EQTUTSEJBZLQILQI2RNMELVCN/events.json","paper":"https://pith.science/paper/4EQTUTSE"},"agent_actions":{"view_html":"https://pith.science/pith/4EQTUTSEJBZLQILQI2RNMELVCN","download_json":"https://pith.science/pith/4EQTUTSEJBZLQILQI2RNMELVCN.json","view_paper":"https://pith.science/paper/4EQTUTSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.00399&json=true","fetch_graph":"https://pith.science/api/pith-number/4EQTUTSEJBZLQILQI2RNMELVCN/graph.json","fetch_events":"https://pith.science/api/pith-number/4EQTUTSEJBZLQILQI2RNMELVCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EQTUTSEJBZLQILQI2RNMELVCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EQTUTSEJBZLQILQI2RNMELVCN/action/storage_attestation","attest_author":"https://pith.science/pith/4EQTUTSEJBZLQILQI2RNMELVCN/action/author_attestation","sign_citation":"https://pith.science/pith/4EQTUTSEJBZLQILQI2RNMELVCN/action/citation_signature","submit_replication":"https://pith.science/pith/4EQTUTSEJBZLQILQI2RNMELVCN/action/replication_record"}},"created_at":"2026-07-08T01:18:20.594586+00:00","updated_at":"2026-07-08T01:18:20.594586+00:00"}