{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:M5SGWWQ5KMNOSYWPJHYWSW5SRR","short_pith_number":"pith:M5SGWWQ5","schema_version":"1.0","canonical_sha256":"67646b5a1d531ae962cf49f1695bb28c71433607f92b0cd855d3fe8e2968baa6","source":{"kind":"arxiv","id":"1705.08209","version":1},"attestation_state":"computed","paper":{"title":"Unbiasing Truncated Backpropagation Through Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Corentin Tallec, Yann Ollivier","submitted_at":"2017-05-23T12:32:48Z","abstract_excerpt":"Truncated Backpropagation Through Time (truncated BPTT) is a widespread method for learning recurrent computational graphs. Truncated BPTT keeps the computational benefits of Backpropagation Through Time (BPTT) while relieving the need for a complete backtrack through the whole data sequence at every step. However, truncation favors short-term dependencies: the gradient estimate of truncated BPTT is biased, so that it does not benefit from the convergence guarantees from stochastic gradient theory. We introduce Anticipated Reweighted Truncated Backpropagation (ARTBP), an algorithm that keeps t"},"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":"1705.08209","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-05-23T12:32:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aaa1a33b7fba9b812003e98962f5952fd646bf596a64ec69f283face63954641","abstract_canon_sha256":"3181fa23478d4826becfa50920b7049a4c622210d220ba29389a1f799dd388c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:49.069710Z","signature_b64":"CP/Quk+Vs0Hlb2h8VQ820qPeXWMdlnOeG1TOhLyDwAZ/fYvsoV1QGzXwLPrZ4KoUMukMuyeSQ0KYnuIO2DkRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67646b5a1d531ae962cf49f1695bb28c71433607f92b0cd855d3fe8e2968baa6","last_reissued_at":"2026-05-18T00:43:49.069048Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:49.069048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unbiasing Truncated Backpropagation Through Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Corentin Tallec, Yann Ollivier","submitted_at":"2017-05-23T12:32:48Z","abstract_excerpt":"Truncated Backpropagation Through Time (truncated BPTT) is a widespread method for learning recurrent computational graphs. Truncated BPTT keeps the computational benefits of Backpropagation Through Time (BPTT) while relieving the need for a complete backtrack through the whole data sequence at every step. However, truncation favors short-term dependencies: the gradient estimate of truncated BPTT is biased, so that it does not benefit from the convergence guarantees from stochastic gradient theory. We introduce Anticipated Reweighted Truncated Backpropagation (ARTBP), an algorithm that keeps t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08209","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":"1705.08209","created_at":"2026-05-18T00:43:49.069162+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.08209v1","created_at":"2026-05-18T00:43:49.069162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08209","created_at":"2026-05-18T00:43:49.069162+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5SGWWQ5KMNO","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5SGWWQ5KMNOSYWP","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5SGWWQ5","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.19376","citing_title":"Generative Recursive Reasoning","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20613","citing_title":"HRM-Text: Efficient Pretraining Beyond Scaling","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19376","citing_title":"Generative Recursive Reasoning","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5SGWWQ5KMNOSYWPJHYWSW5SRR","json":"https://pith.science/pith/M5SGWWQ5KMNOSYWPJHYWSW5SRR.json","graph_json":"https://pith.science/api/pith-number/M5SGWWQ5KMNOSYWPJHYWSW5SRR/graph.json","events_json":"https://pith.science/api/pith-number/M5SGWWQ5KMNOSYWPJHYWSW5SRR/events.json","paper":"https://pith.science/paper/M5SGWWQ5"},"agent_actions":{"view_html":"https://pith.science/pith/M5SGWWQ5KMNOSYWPJHYWSW5SRR","download_json":"https://pith.science/pith/M5SGWWQ5KMNOSYWPJHYWSW5SRR.json","view_paper":"https://pith.science/paper/M5SGWWQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.08209&json=true","fetch_graph":"https://pith.science/api/pith-number/M5SGWWQ5KMNOSYWPJHYWSW5SRR/graph.json","fetch_events":"https://pith.science/api/pith-number/M5SGWWQ5KMNOSYWPJHYWSW5SRR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5SGWWQ5KMNOSYWPJHYWSW5SRR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5SGWWQ5KMNOSYWPJHYWSW5SRR/action/storage_attestation","attest_author":"https://pith.science/pith/M5SGWWQ5KMNOSYWPJHYWSW5SRR/action/author_attestation","sign_citation":"https://pith.science/pith/M5SGWWQ5KMNOSYWPJHYWSW5SRR/action/citation_signature","submit_replication":"https://pith.science/pith/M5SGWWQ5KMNOSYWPJHYWSW5SRR/action/replication_record"}},"created_at":"2026-05-18T00:43:49.069162+00:00","updated_at":"2026-05-18T00:43:49.069162+00:00"}