{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:527QI25WAQLLT7T7XE3CQNZJGZ","short_pith_number":"pith:527QI25W","schema_version":"1.0","canonical_sha256":"eebf046bb60416b9fe7fb936283729366cc56f3ecfd3fc998daa675e46aef5d2","source":{"kind":"arxiv","id":"2409.04641","version":1},"attestation_state":"computed","paper":{"title":"Stacked Universal Successor Feature Approximators for Safety in Reinforcement Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ian Cannon, Ian Leong, Jared Culbertson, Joseph Saurine, Thomas Gresavage, Washington Garcia","submitted_at":"2024-09-06T22:20:07Z","abstract_excerpt":"Real-world problems often involve complex objective structures that resist distillation into reinforcement learning environments with a single objective. Operation costs must be balanced with multi-dimensional task performance and end-states' effects on future availability, all while ensuring safety for other agents in the environment and the reinforcement learning agent itself. System redundancy through secondary backup controllers has proven to be an effective method to ensure safety in real-world applications where the risk of violating constraints is extremely high. In this work, we invest"},"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":"2409.04641","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-06T22:20:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8a8d73d3493039320fef8e206b6bc6e79f10ec06d3cd6377119930904af7c4bd","abstract_canon_sha256":"05b48f3d6d7ed7242aedba20f466093d3d72f09578b13ca0d589c8cfd6538d45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:15.609496Z","signature_b64":"Tk0dpdMj1u4SRMB31Tpa+SAatRyxAl3ptIFwyEucpDR3vp1/TervkatFlm9y2Ilj5MolCX9keBtL6jcyTxywCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eebf046bb60416b9fe7fb936283729366cc56f3ecfd3fc998daa675e46aef5d2","last_reissued_at":"2026-07-05T09:04:15.609022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:15.609022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stacked Universal Successor Feature Approximators for Safety in Reinforcement Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ian Cannon, Ian Leong, Jared Culbertson, Joseph Saurine, Thomas Gresavage, Washington Garcia","submitted_at":"2024-09-06T22:20:07Z","abstract_excerpt":"Real-world problems often involve complex objective structures that resist distillation into reinforcement learning environments with a single objective. Operation costs must be balanced with multi-dimensional task performance and end-states' effects on future availability, all while ensuring safety for other agents in the environment and the reinforcement learning agent itself. System redundancy through secondary backup controllers has proven to be an effective method to ensure safety in real-world applications where the risk of violating constraints is extremely high. In this work, we invest"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04641","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/2409.04641/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":"2409.04641","created_at":"2026-07-05T09:04:15.609077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.04641v1","created_at":"2026-07-05T09:04:15.609077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04641","created_at":"2026-07-05T09:04:15.609077+00:00"},{"alias_kind":"pith_short_12","alias_value":"527QI25WAQLL","created_at":"2026-07-05T09:04:15.609077+00:00"},{"alias_kind":"pith_short_16","alias_value":"527QI25WAQLLT7T7","created_at":"2026-07-05T09:04:15.609077+00:00"},{"alias_kind":"pith_short_8","alias_value":"527QI25W","created_at":"2026-07-05T09:04:15.609077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.05984","citing_title":"The Safe Trusted Autonomy for Responsible Space Program","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/527QI25WAQLLT7T7XE3CQNZJGZ","json":"https://pith.science/pith/527QI25WAQLLT7T7XE3CQNZJGZ.json","graph_json":"https://pith.science/api/pith-number/527QI25WAQLLT7T7XE3CQNZJGZ/graph.json","events_json":"https://pith.science/api/pith-number/527QI25WAQLLT7T7XE3CQNZJGZ/events.json","paper":"https://pith.science/paper/527QI25W"},"agent_actions":{"view_html":"https://pith.science/pith/527QI25WAQLLT7T7XE3CQNZJGZ","download_json":"https://pith.science/pith/527QI25WAQLLT7T7XE3CQNZJGZ.json","view_paper":"https://pith.science/paper/527QI25W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.04641&json=true","fetch_graph":"https://pith.science/api/pith-number/527QI25WAQLLT7T7XE3CQNZJGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/527QI25WAQLLT7T7XE3CQNZJGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/527QI25WAQLLT7T7XE3CQNZJGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/527QI25WAQLLT7T7XE3CQNZJGZ/action/storage_attestation","attest_author":"https://pith.science/pith/527QI25WAQLLT7T7XE3CQNZJGZ/action/author_attestation","sign_citation":"https://pith.science/pith/527QI25WAQLLT7T7XE3CQNZJGZ/action/citation_signature","submit_replication":"https://pith.science/pith/527QI25WAQLLT7T7XE3CQNZJGZ/action/replication_record"}},"created_at":"2026-07-05T09:04:15.609077+00:00","updated_at":"2026-07-05T09:04:15.609077+00:00"}