{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QCLWYWQHWLRY7PV52MAOTEVAAQ","short_pith_number":"pith:QCLWYWQH","schema_version":"1.0","canonical_sha256":"80976c5a07b2e38fbebdd300e992a00406ab712015d6b52a3edfe62e167d64ee","source":{"kind":"arxiv","id":"2407.09375","version":3},"attestation_state":"computed","paper":{"title":"HiPPO-Prophecy: State-Space Models can Provably Learn Dynamical Systems in Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Caglar Gulcehre, Federico Arangath Joseph, Kilian Konstantin Haefeli, Noah Liniger","submitted_at":"2024-07-12T15:56:11Z","abstract_excerpt":"This work explores the in-context learning capabilities of State Space Models (SSMs) and presents, to the best of our knowledge, the first theoretical explanation of a possible underlying mechanism. We introduce a novel weight construction for SSMs, enabling them to predict the next state of any dynamical system after observing previous states without parameter fine-tuning. This is accomplished by extending the HiPPO framework to demonstrate that continuous SSMs can approximate the derivative of any input signal. Specifically, we find an explicit weight construction for continuous SSMs and pro"},"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":"2407.09375","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-12T15:56:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"38f17441679dbc042a2c80e715e1744c856fac5157f3546a4f2b6e0504653717","abstract_canon_sha256":"c713e76bff67cd8f91b1d84a45c82c43eadda5ea8a6fc2251af9c0221cff51c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:12.680437Z","signature_b64":"mgdMGzKp3o8Y9iizMydWHO171BzyjfnJWhPY8b+pvX52YS4jEKamVxdd9VzTFwlJrmGc9tOq+N97g3fpHbRqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80976c5a07b2e38fbebdd300e992a00406ab712015d6b52a3edfe62e167d64ee","last_reissued_at":"2026-07-05T11:47:12.679920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:12.679920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiPPO-Prophecy: State-Space Models can Provably Learn Dynamical Systems in Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Caglar Gulcehre, Federico Arangath Joseph, Kilian Konstantin Haefeli, Noah Liniger","submitted_at":"2024-07-12T15:56:11Z","abstract_excerpt":"This work explores the in-context learning capabilities of State Space Models (SSMs) and presents, to the best of our knowledge, the first theoretical explanation of a possible underlying mechanism. We introduce a novel weight construction for SSMs, enabling them to predict the next state of any dynamical system after observing previous states without parameter fine-tuning. This is accomplished by extending the HiPPO framework to demonstrate that continuous SSMs can approximate the derivative of any input signal. Specifically, we find an explicit weight construction for continuous SSMs and pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09375","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/2407.09375/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":"2407.09375","created_at":"2026-07-05T11:47:12.679982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.09375v3","created_at":"2026-07-05T11:47:12.679982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09375","created_at":"2026-07-05T11:47:12.679982+00:00"},{"alias_kind":"pith_short_12","alias_value":"QCLWYWQHWLRY","created_at":"2026-07-05T11:47:12.679982+00:00"},{"alias_kind":"pith_short_16","alias_value":"QCLWYWQHWLRY7PV5","created_at":"2026-07-05T11:47:12.679982+00:00"},{"alias_kind":"pith_short_8","alias_value":"QCLWYWQH","created_at":"2026-07-05T11:47:12.679982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.18970","citing_title":"Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State- Space Architectures from S4 to Mamba","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QCLWYWQHWLRY7PV52MAOTEVAAQ","json":"https://pith.science/pith/QCLWYWQHWLRY7PV52MAOTEVAAQ.json","graph_json":"https://pith.science/api/pith-number/QCLWYWQHWLRY7PV52MAOTEVAAQ/graph.json","events_json":"https://pith.science/api/pith-number/QCLWYWQHWLRY7PV52MAOTEVAAQ/events.json","paper":"https://pith.science/paper/QCLWYWQH"},"agent_actions":{"view_html":"https://pith.science/pith/QCLWYWQHWLRY7PV52MAOTEVAAQ","download_json":"https://pith.science/pith/QCLWYWQHWLRY7PV52MAOTEVAAQ.json","view_paper":"https://pith.science/paper/QCLWYWQH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.09375&json=true","fetch_graph":"https://pith.science/api/pith-number/QCLWYWQHWLRY7PV52MAOTEVAAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QCLWYWQHWLRY7PV52MAOTEVAAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QCLWYWQHWLRY7PV52MAOTEVAAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QCLWYWQHWLRY7PV52MAOTEVAAQ/action/storage_attestation","attest_author":"https://pith.science/pith/QCLWYWQHWLRY7PV52MAOTEVAAQ/action/author_attestation","sign_citation":"https://pith.science/pith/QCLWYWQHWLRY7PV52MAOTEVAAQ/action/citation_signature","submit_replication":"https://pith.science/pith/QCLWYWQHWLRY7PV52MAOTEVAAQ/action/replication_record"}},"created_at":"2026-07-05T11:47:12.679982+00:00","updated_at":"2026-07-05T11:47:12.679982+00:00"}