{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:AXJYOOGQNIRUVVB2USU3RHJVUB","short_pith_number":"pith:AXJYOOGQ","schema_version":"1.0","canonical_sha256":"05d38738d06a234ad43aa4a9b89d35a06db42b1c0f1043b59751f7249022453b","source":{"kind":"arxiv","id":"1508.04582","version":1},"attestation_state":"computed","paper":{"title":"Learning to Predict Independent of Span","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hado van Hasselt, Richard S. Sutton","submitted_at":"2015-08-19T09:37:25Z","abstract_excerpt":"We consider how to learn multi-step predictions efficiently. Conventional algorithms wait until observing actual outcomes before performing the computations to update their predictions. If predictions are made at a high rate or span over a large amount of time, substantial computation can be required to store all relevant observations and to update all predictions when the outcome is finally observed. We show that the exact same predictions can be learned in a much more computationally congenial way, with uniform per-step computation that does not depend on the span of the predictions. We appl"},"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":"1508.04582","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-08-19T09:37:25Z","cross_cats_sorted":[],"title_canon_sha256":"0ff6283d10efdfc2a03ea4e9908ee0aebfe18cf63a3e78699d9b7d5e7622bd3e","abstract_canon_sha256":"5cf34ecea1029901b529f23f331a3efc980de35d35aa7997058cfa24b901e666"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:02.361055Z","signature_b64":"eADfbaFCcnl7UDcKLrcrTpqv8pRmBhFX+07HtaSdZKLDR8RSWp1b/yQUthXQayaBScXVXSFYRrFTUj66AEzvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05d38738d06a234ad43aa4a9b89d35a06db42b1c0f1043b59751f7249022453b","last_reissued_at":"2026-05-18T01:35:02.360415Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:02.360415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Predict Independent of Span","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hado van Hasselt, Richard S. Sutton","submitted_at":"2015-08-19T09:37:25Z","abstract_excerpt":"We consider how to learn multi-step predictions efficiently. Conventional algorithms wait until observing actual outcomes before performing the computations to update their predictions. If predictions are made at a high rate or span over a large amount of time, substantial computation can be required to store all relevant observations and to update all predictions when the outcome is finally observed. We show that the exact same predictions can be learned in a much more computationally congenial way, with uniform per-step computation that does not depend on the span of the predictions. We appl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.04582","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":""},"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":"1508.04582","created_at":"2026-05-18T01:35:02.360525+00:00"},{"alias_kind":"arxiv_version","alias_value":"1508.04582v1","created_at":"2026-05-18T01:35:02.360525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.04582","created_at":"2026-05-18T01:35:02.360525+00:00"},{"alias_kind":"pith_short_12","alias_value":"AXJYOOGQNIRU","created_at":"2026-05-18T12:29:10.953037+00:00"},{"alias_kind":"pith_short_16","alias_value":"AXJYOOGQNIRUVVB2","created_at":"2026-05-18T12:29:10.953037+00:00"},{"alias_kind":"pith_short_8","alias_value":"AXJYOOGQ","created_at":"2026-05-18T12:29:10.953037+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16318","citing_title":"Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AXJYOOGQNIRUVVB2USU3RHJVUB","json":"https://pith.science/pith/AXJYOOGQNIRUVVB2USU3RHJVUB.json","graph_json":"https://pith.science/api/pith-number/AXJYOOGQNIRUVVB2USU3RHJVUB/graph.json","events_json":"https://pith.science/api/pith-number/AXJYOOGQNIRUVVB2USU3RHJVUB/events.json","paper":"https://pith.science/paper/AXJYOOGQ"},"agent_actions":{"view_html":"https://pith.science/pith/AXJYOOGQNIRUVVB2USU3RHJVUB","download_json":"https://pith.science/pith/AXJYOOGQNIRUVVB2USU3RHJVUB.json","view_paper":"https://pith.science/paper/AXJYOOGQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1508.04582&json=true","fetch_graph":"https://pith.science/api/pith-number/AXJYOOGQNIRUVVB2USU3RHJVUB/graph.json","fetch_events":"https://pith.science/api/pith-number/AXJYOOGQNIRUVVB2USU3RHJVUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AXJYOOGQNIRUVVB2USU3RHJVUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AXJYOOGQNIRUVVB2USU3RHJVUB/action/storage_attestation","attest_author":"https://pith.science/pith/AXJYOOGQNIRUVVB2USU3RHJVUB/action/author_attestation","sign_citation":"https://pith.science/pith/AXJYOOGQNIRUVVB2USU3RHJVUB/action/citation_signature","submit_replication":"https://pith.science/pith/AXJYOOGQNIRUVVB2USU3RHJVUB/action/replication_record"}},"created_at":"2026-05-18T01:35:02.360525+00:00","updated_at":"2026-05-18T01:35:02.360525+00:00"}