{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:WR2XTKWMDXAYLLFLNIF7NKXAUB","short_pith_number":"pith:WR2XTKWM","schema_version":"1.0","canonical_sha256":"b47579aacc1dc185acab6a0bf6aae0a040fd824ee9b79eb0ffd52a1697ccb0fc","source":{"kind":"arxiv","id":"1612.02879","version":2},"attestation_state":"computed","paper":{"title":"Learning Representations by Stochastic Meta-Gradient Descent in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Richard S. Sutton, Shangtong Zhang, Vivek Veeriah","submitted_at":"2016-12-09T00:56:42Z","abstract_excerpt":"Representations are fundamental to artificial intelligence. The performance of a learning system depends on the type of representation used for representing the data. Typically, these representations are hand-engineered using domain knowledge. More recently, the trend is to learn these representations through stochastic gradient descent in multi-layer neural networks, which is called backprop. Learning the representations directly from the incoming data stream reduces the human labour involved in designing a learning system. More importantly, this allows in scaling of a learning system for dif"},"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":"1612.02879","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-09T00:56:42Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"991b7112d0410fe179e7d333a759551b5a4e2a48943a689e4fd2951e8e2ec0f7","abstract_canon_sha256":"012adda5d17c765eb417b830346b0b2520d2f80a03abf85a09db5c63c2ee92c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:30.184532Z","signature_b64":"kiBN+IObv12Ls19T78JlJohX0pKZ7NRAOQjwzEdTApQrsnlGgsY3QnWt8LuKLoVO6h5LEpUeyHVjOS4msNvcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b47579aacc1dc185acab6a0bf6aae0a040fd824ee9b79eb0ffd52a1697ccb0fc","last_reissued_at":"2026-05-18T00:45:30.183940Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:30.183940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Representations by Stochastic Meta-Gradient Descent in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Richard S. Sutton, Shangtong Zhang, Vivek Veeriah","submitted_at":"2016-12-09T00:56:42Z","abstract_excerpt":"Representations are fundamental to artificial intelligence. The performance of a learning system depends on the type of representation used for representing the data. Typically, these representations are hand-engineered using domain knowledge. More recently, the trend is to learn these representations through stochastic gradient descent in multi-layer neural networks, which is called backprop. Learning the representations directly from the incoming data stream reduces the human labour involved in designing a learning system. More importantly, this allows in scaling of a learning system for dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.02879","kind":"arxiv","version":2},"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":"1612.02879","created_at":"2026-05-18T00:45:30.184049+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.02879v2","created_at":"2026-05-18T00:45:30.184049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.02879","created_at":"2026-05-18T00:45:30.184049+00:00"},{"alias_kind":"pith_short_12","alias_value":"WR2XTKWMDXAY","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"WR2XTKWMDXAYLLFL","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"WR2XTKWM","created_at":"2026-05-18T12:30:51.357362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WR2XTKWMDXAYLLFLNIF7NKXAUB","json":"https://pith.science/pith/WR2XTKWMDXAYLLFLNIF7NKXAUB.json","graph_json":"https://pith.science/api/pith-number/WR2XTKWMDXAYLLFLNIF7NKXAUB/graph.json","events_json":"https://pith.science/api/pith-number/WR2XTKWMDXAYLLFLNIF7NKXAUB/events.json","paper":"https://pith.science/paper/WR2XTKWM"},"agent_actions":{"view_html":"https://pith.science/pith/WR2XTKWMDXAYLLFLNIF7NKXAUB","download_json":"https://pith.science/pith/WR2XTKWMDXAYLLFLNIF7NKXAUB.json","view_paper":"https://pith.science/paper/WR2XTKWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.02879&json=true","fetch_graph":"https://pith.science/api/pith-number/WR2XTKWMDXAYLLFLNIF7NKXAUB/graph.json","fetch_events":"https://pith.science/api/pith-number/WR2XTKWMDXAYLLFLNIF7NKXAUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WR2XTKWMDXAYLLFLNIF7NKXAUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WR2XTKWMDXAYLLFLNIF7NKXAUB/action/storage_attestation","attest_author":"https://pith.science/pith/WR2XTKWMDXAYLLFLNIF7NKXAUB/action/author_attestation","sign_citation":"https://pith.science/pith/WR2XTKWMDXAYLLFLNIF7NKXAUB/action/citation_signature","submit_replication":"https://pith.science/pith/WR2XTKWMDXAYLLFLNIF7NKXAUB/action/replication_record"}},"created_at":"2026-05-18T00:45:30.184049+00:00","updated_at":"2026-05-18T00:45:30.184049+00:00"}