{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:APKZ2TDD356WWUVSEAY73L5H57","short_pith_number":"pith:APKZ2TDD","schema_version":"1.0","canonical_sha256":"03d59d4c63df7d6b52b22031fdafa7efc4889e62d56e1df63cd4d09d74fa038c","source":{"kind":"arxiv","id":"2506.13892","version":1},"attestation_state":"computed","paper":{"title":"Scaling Algorithm Distillation for Continuous Control with Mamba","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Mehdi Mounsif, Samuel Beaussant","submitted_at":"2025-06-16T18:15:02Z","abstract_excerpt":"Algorithm Distillation (AD) was recently proposed as a new approach to perform In-Context Reinforcement Learning (ICRL) by modeling across-episodic training histories autoregressively with a causal transformer model. However, due to practical limitations induced by the attention mechanism, experiments were bottlenecked by the transformer's quadratic complexity and limited to simple discrete environments with short time horizons. In this work, we propose leveraging the recently proposed Selective Structured State Space Sequence (S6) models, which achieved state-of-the-art (SOTA) performance on "},"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":"2506.13892","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-16T18:15:02Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"e33ba6947c026be63f945049c7166d3be7cb72986deae2066fb1800c77784580","abstract_canon_sha256":"3af012f897037043b8a4e2f812f7c1067b5a4309492004342c67cd6a2776f790"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:45.275441Z","signature_b64":"bGR9Jgxl6bO9KdLIWtZZNJLBm2Lf4nK5rZpz9rZUpS2b56SxHL7cUFAFrmeVIAcAhleOsVDWNgj2v/rUYWdIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03d59d4c63df7d6b52b22031fdafa7efc4889e62d56e1df63cd4d09d74fa038c","last_reissued_at":"2026-07-05T11:22:45.274790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:45.274790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Algorithm Distillation for Continuous Control with Mamba","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Mehdi Mounsif, Samuel Beaussant","submitted_at":"2025-06-16T18:15:02Z","abstract_excerpt":"Algorithm Distillation (AD) was recently proposed as a new approach to perform In-Context Reinforcement Learning (ICRL) by modeling across-episodic training histories autoregressively with a causal transformer model. However, due to practical limitations induced by the attention mechanism, experiments were bottlenecked by the transformer's quadratic complexity and limited to simple discrete environments with short time horizons. In this work, we propose leveraging the recently proposed Selective Structured State Space Sequence (S6) models, which achieved state-of-the-art (SOTA) performance on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13892","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/2506.13892/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":"2506.13892","created_at":"2026-07-05T11:22:45.274883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13892v1","created_at":"2026-07-05T11:22:45.274883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13892","created_at":"2026-07-05T11:22:45.274883+00:00"},{"alias_kind":"pith_short_12","alias_value":"APKZ2TDD356W","created_at":"2026-07-05T11:22:45.274883+00:00"},{"alias_kind":"pith_short_16","alias_value":"APKZ2TDD356WWUVS","created_at":"2026-07-05T11:22:45.274883+00:00"},{"alias_kind":"pith_short_8","alias_value":"APKZ2TDD","created_at":"2026-07-05T11:22:45.274883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17431","citing_title":"MATE: Solving Contextual Markov Decision Processes with Memory of Accumulated Transition Embeddings","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/APKZ2TDD356WWUVSEAY73L5H57","json":"https://pith.science/pith/APKZ2TDD356WWUVSEAY73L5H57.json","graph_json":"https://pith.science/api/pith-number/APKZ2TDD356WWUVSEAY73L5H57/graph.json","events_json":"https://pith.science/api/pith-number/APKZ2TDD356WWUVSEAY73L5H57/events.json","paper":"https://pith.science/paper/APKZ2TDD"},"agent_actions":{"view_html":"https://pith.science/pith/APKZ2TDD356WWUVSEAY73L5H57","download_json":"https://pith.science/pith/APKZ2TDD356WWUVSEAY73L5H57.json","view_paper":"https://pith.science/paper/APKZ2TDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13892&json=true","fetch_graph":"https://pith.science/api/pith-number/APKZ2TDD356WWUVSEAY73L5H57/graph.json","fetch_events":"https://pith.science/api/pith-number/APKZ2TDD356WWUVSEAY73L5H57/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APKZ2TDD356WWUVSEAY73L5H57/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APKZ2TDD356WWUVSEAY73L5H57/action/storage_attestation","attest_author":"https://pith.science/pith/APKZ2TDD356WWUVSEAY73L5H57/action/author_attestation","sign_citation":"https://pith.science/pith/APKZ2TDD356WWUVSEAY73L5H57/action/citation_signature","submit_replication":"https://pith.science/pith/APKZ2TDD356WWUVSEAY73L5H57/action/replication_record"}},"created_at":"2026-07-05T11:22:45.274883+00:00","updated_at":"2026-07-05T11:22:45.274883+00:00"}