{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QJ7F2GHJUSABKNVGYABH6JDRAY","short_pith_number":"pith:QJ7F2GHJ","schema_version":"1.0","canonical_sha256":"827e5d18e9a4801536a6c0027f2471060c988ab40a303c3b79faa7bf5e1fdd25","source":{"kind":"arxiv","id":"2502.04593","version":2},"attestation_state":"computed","paper":{"title":"The Alpha-Alternator: Dynamic Adaptation To Varying Noise Levels In Sequences Using The Vendi Score For Improved Robustness and Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adji Bousso Dieng, Mohammad Reza Rezaei","submitted_at":"2025-02-07T01:00:16Z","abstract_excerpt":"Current state-of-the-art dynamical models, such as Mamba, assume the same level of noisiness for all elements of a given sequence, which limits their performance on noisy temporal data. In this paper, we introduce the $\\alpha$-Alternator, a novel generative model for time-dependent data that dynamically adapts to the complexity introduced by varying noise levels in sequences. The $\\alpha$-Alternator leverages the Vendi Score (VS), a flexible similarity-based diversity metric, to adjust, at each time step $t$, the influence of the sequence element at time $t$ and the latent representation of th"},"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":"2502.04593","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T01:00:16Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"bed59555b54a354e5391dd61b8714495ed34068f0298693e23c98fd9bf6ea03c","abstract_canon_sha256":"e6689d87079ff3cc9578c69ff1079c86e02dec5a6394438f32e59f8ad9666e04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:15.938915Z","signature_b64":"/pnNDrL6u/OviI45VX267lxNpUgf/KAu4xN4AvP9ofVQFEnfjmAS/dxKCJ9bTV8XKKmUOk3jhYHt4A8XygDRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"827e5d18e9a4801536a6c0027f2471060c988ab40a303c3b79faa7bf5e1fdd25","last_reissued_at":"2026-07-05T11:08:15.938372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:15.938372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Alpha-Alternator: Dynamic Adaptation To Varying Noise Levels In Sequences Using The Vendi Score For Improved Robustness and Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adji Bousso Dieng, Mohammad Reza Rezaei","submitted_at":"2025-02-07T01:00:16Z","abstract_excerpt":"Current state-of-the-art dynamical models, such as Mamba, assume the same level of noisiness for all elements of a given sequence, which limits their performance on noisy temporal data. In this paper, we introduce the $\\alpha$-Alternator, a novel generative model for time-dependent data that dynamically adapts to the complexity introduced by varying noise levels in sequences. The $\\alpha$-Alternator leverages the Vendi Score (VS), a flexible similarity-based diversity metric, to adjust, at each time step $t$, the influence of the sequence element at time $t$ and the latent representation of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04593","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/2502.04593/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":"2502.04593","created_at":"2026-07-05T11:08:15.938436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04593v2","created_at":"2026-07-05T11:08:15.938436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04593","created_at":"2026-07-05T11:08:15.938436+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJ7F2GHJUSAB","created_at":"2026-07-05T11:08:15.938436+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJ7F2GHJUSABKNVG","created_at":"2026-07-05T11:08:15.938436+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJ7F2GHJ","created_at":"2026-07-05T11:08:15.938436+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/QJ7F2GHJUSABKNVGYABH6JDRAY","json":"https://pith.science/pith/QJ7F2GHJUSABKNVGYABH6JDRAY.json","graph_json":"https://pith.science/api/pith-number/QJ7F2GHJUSABKNVGYABH6JDRAY/graph.json","events_json":"https://pith.science/api/pith-number/QJ7F2GHJUSABKNVGYABH6JDRAY/events.json","paper":"https://pith.science/paper/QJ7F2GHJ"},"agent_actions":{"view_html":"https://pith.science/pith/QJ7F2GHJUSABKNVGYABH6JDRAY","download_json":"https://pith.science/pith/QJ7F2GHJUSABKNVGYABH6JDRAY.json","view_paper":"https://pith.science/paper/QJ7F2GHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04593&json=true","fetch_graph":"https://pith.science/api/pith-number/QJ7F2GHJUSABKNVGYABH6JDRAY/graph.json","fetch_events":"https://pith.science/api/pith-number/QJ7F2GHJUSABKNVGYABH6JDRAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJ7F2GHJUSABKNVGYABH6JDRAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJ7F2GHJUSABKNVGYABH6JDRAY/action/storage_attestation","attest_author":"https://pith.science/pith/QJ7F2GHJUSABKNVGYABH6JDRAY/action/author_attestation","sign_citation":"https://pith.science/pith/QJ7F2GHJUSABKNVGYABH6JDRAY/action/citation_signature","submit_replication":"https://pith.science/pith/QJ7F2GHJUSABKNVGYABH6JDRAY/action/replication_record"}},"created_at":"2026-07-05T11:08:15.938436+00:00","updated_at":"2026-07-05T11:08:15.938436+00:00"}