{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:GQVTFBSH42UJU6UUUWILZWMK4W","short_pith_number":"pith:GQVTFBSH","schema_version":"1.0","canonical_sha256":"342b328647e6a89a7a94a590bcd98ae5b4aab515e34e673a01970bbae97dcecc","source":{"kind":"arxiv","id":"1611.02554","version":2},"attestation_state":"computed","paper":{"title":"The Neural Noisy Channel","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CL","authors_text":"Chris Dyer, Edward Grefenstette, Lei Yu, Phil Blunsom, Tomas Kocisky","submitted_at":"2016-11-08T15:18:44Z","abstract_excerpt":"We formulate sequence to sequence transduction as a noisy channel decoding problem and use recurrent neural networks to parameterise the source and channel models. Unlike direct models which can suffer from explaining-away effects during training, noisy channel models must produce outputs that explain their inputs, and their component models can be trained with not only paired training samples but also unpaired samples from the marginal output distribution. Using a latent variable to control how much of the conditioning sequence the channel model needs to read in order to generate a subsequent"},"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":"1611.02554","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-08T15:18:44Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"b0e7dd7dac41dc175bb05724253dd6d251ec11634eb6b4bf34683dbddd9d692d","abstract_canon_sha256":"fc6370d8f55ae4c726c19ea1c3ec9f84f73ac8e70b19a6d9eda1d506334b055d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:31.821378Z","signature_b64":"1FlGbv/0B7pljEofzWKj6z/3UydCbtUqrPkZMj3K4mhQo+WDL/AwdN6Yxb3YduXr7/hUZ8B9fYk0gvOkyA1DDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"342b328647e6a89a7a94a590bcd98ae5b4aab515e34e673a01970bbae97dcecc","last_reissued_at":"2026-05-18T00:49:31.820855Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:31.820855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Neural Noisy Channel","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CL","authors_text":"Chris Dyer, Edward Grefenstette, Lei Yu, Phil Blunsom, Tomas Kocisky","submitted_at":"2016-11-08T15:18:44Z","abstract_excerpt":"We formulate sequence to sequence transduction as a noisy channel decoding problem and use recurrent neural networks to parameterise the source and channel models. Unlike direct models which can suffer from explaining-away effects during training, noisy channel models must produce outputs that explain their inputs, and their component models can be trained with not only paired training samples but also unpaired samples from the marginal output distribution. Using a latent variable to control how much of the conditioning sequence the channel model needs to read in order to generate a subsequent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.02554","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":"1611.02554","created_at":"2026-05-18T00:49:31.820933+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.02554v2","created_at":"2026-05-18T00:49:31.820933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.02554","created_at":"2026-05-18T00:49:31.820933+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQVTFBSH42UJ","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQVTFBSH42UJU6UU","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQVTFBSH","created_at":"2026-05-18T12:30:19.053100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1910.03771","citing_title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","ref_index":120,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQVTFBSH42UJU6UUUWILZWMK4W","json":"https://pith.science/pith/GQVTFBSH42UJU6UUUWILZWMK4W.json","graph_json":"https://pith.science/api/pith-number/GQVTFBSH42UJU6UUUWILZWMK4W/graph.json","events_json":"https://pith.science/api/pith-number/GQVTFBSH42UJU6UUUWILZWMK4W/events.json","paper":"https://pith.science/paper/GQVTFBSH"},"agent_actions":{"view_html":"https://pith.science/pith/GQVTFBSH42UJU6UUUWILZWMK4W","download_json":"https://pith.science/pith/GQVTFBSH42UJU6UUUWILZWMK4W.json","view_paper":"https://pith.science/paper/GQVTFBSH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.02554&json=true","fetch_graph":"https://pith.science/api/pith-number/GQVTFBSH42UJU6UUUWILZWMK4W/graph.json","fetch_events":"https://pith.science/api/pith-number/GQVTFBSH42UJU6UUUWILZWMK4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQVTFBSH42UJU6UUUWILZWMK4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQVTFBSH42UJU6UUUWILZWMK4W/action/storage_attestation","attest_author":"https://pith.science/pith/GQVTFBSH42UJU6UUUWILZWMK4W/action/author_attestation","sign_citation":"https://pith.science/pith/GQVTFBSH42UJU6UUUWILZWMK4W/action/citation_signature","submit_replication":"https://pith.science/pith/GQVTFBSH42UJU6UUUWILZWMK4W/action/replication_record"}},"created_at":"2026-05-18T00:49:31.820933+00:00","updated_at":"2026-05-18T00:49:31.820933+00:00"}