{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:OP3LMYE4FSKPWE2HJEC6X44KTD","short_pith_number":"pith:OP3LMYE4","schema_version":"1.0","canonical_sha256":"73f6b6609c2c94fb13474905ebf38a98c5c33a518344893f151c3b09a4189667","source":{"kind":"arxiv","id":"1603.00954","version":5},"attestation_state":"computed","paper":{"title":"Training Input-Output Recurrent Neural Networks through Spectral Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Hanie Sedghi","submitted_at":"2016-03-03T03:14:47Z","abstract_excerpt":"We consider the problem of training input-output recurrent neural networks (RNN) for sequence labeling tasks. We propose a novel spectral approach for learning the network parameters. It is based on decomposition of the cross-moment tensor between the output and a non-linear transformation of the input, based on score functions. We guarantee consistent learning with polynomial sample and computational complexity under transparent conditions such as non-degeneracy of model parameters, polynomial activations for the neurons, and a Markovian evolution of the input sequence. We also extend our res"},"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":"1603.00954","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-03T03:14:47Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"3efb8e68a05896c881edc548d1b497ba8ba72270086dd635f7b731e4968d8e87","abstract_canon_sha256":"80ed350c096d22cae30999c72796e9a58695e10f7dd5f9bd5d5bd73c97deca51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:53.261132Z","signature_b64":"USrUTvr2UvJhjyhLIqVELmY449PCeR2WUG6teiLDCcbAdhDxEpUHeA7RyGRNHjUWdBTQdfGWwbMlHEeXhRwkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73f6b6609c2c94fb13474905ebf38a98c5c33a518344893f151c3b09a4189667","last_reissued_at":"2026-05-18T01:00:53.260506Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:53.260506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Input-Output Recurrent Neural Networks through Spectral Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Hanie Sedghi","submitted_at":"2016-03-03T03:14:47Z","abstract_excerpt":"We consider the problem of training input-output recurrent neural networks (RNN) for sequence labeling tasks. We propose a novel spectral approach for learning the network parameters. It is based on decomposition of the cross-moment tensor between the output and a non-linear transformation of the input, based on score functions. We guarantee consistent learning with polynomial sample and computational complexity under transparent conditions such as non-degeneracy of model parameters, polynomial activations for the neurons, and a Markovian evolution of the input sequence. We also extend our res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.00954","kind":"arxiv","version":5},"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":"1603.00954","created_at":"2026-05-18T01:00:53.260611+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.00954v5","created_at":"2026-05-18T01:00:53.260611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.00954","created_at":"2026-05-18T01:00:53.260611+00:00"},{"alias_kind":"pith_short_12","alias_value":"OP3LMYE4FSKP","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"OP3LMYE4FSKPWE2H","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"OP3LMYE4","created_at":"2026-05-18T12:30:36.002864+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/OP3LMYE4FSKPWE2HJEC6X44KTD","json":"https://pith.science/pith/OP3LMYE4FSKPWE2HJEC6X44KTD.json","graph_json":"https://pith.science/api/pith-number/OP3LMYE4FSKPWE2HJEC6X44KTD/graph.json","events_json":"https://pith.science/api/pith-number/OP3LMYE4FSKPWE2HJEC6X44KTD/events.json","paper":"https://pith.science/paper/OP3LMYE4"},"agent_actions":{"view_html":"https://pith.science/pith/OP3LMYE4FSKPWE2HJEC6X44KTD","download_json":"https://pith.science/pith/OP3LMYE4FSKPWE2HJEC6X44KTD.json","view_paper":"https://pith.science/paper/OP3LMYE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.00954&json=true","fetch_graph":"https://pith.science/api/pith-number/OP3LMYE4FSKPWE2HJEC6X44KTD/graph.json","fetch_events":"https://pith.science/api/pith-number/OP3LMYE4FSKPWE2HJEC6X44KTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OP3LMYE4FSKPWE2HJEC6X44KTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OP3LMYE4FSKPWE2HJEC6X44KTD/action/storage_attestation","attest_author":"https://pith.science/pith/OP3LMYE4FSKPWE2HJEC6X44KTD/action/author_attestation","sign_citation":"https://pith.science/pith/OP3LMYE4FSKPWE2HJEC6X44KTD/action/citation_signature","submit_replication":"https://pith.science/pith/OP3LMYE4FSKPWE2HJEC6X44KTD/action/replication_record"}},"created_at":"2026-05-18T01:00:53.260611+00:00","updated_at":"2026-05-18T01:00:53.260611+00:00"}