{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KG56UVWQSATUYIIYUFP5KTOHTT","short_pith_number":"pith:KG56UVWQ","schema_version":"1.0","canonical_sha256":"51bbea56d090274c2118a15fd54dc79cd2cda00d33d593caa20300bff0da6fba","source":{"kind":"arxiv","id":"1807.03756","version":2},"attestation_state":"computed","paper":{"title":"Latent Alignment and Variational Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander M. Rush, Demi Guo, Justin Chiu, Yoon Kim, Yuntian Deng","submitted_at":"2018-07-10T16:59:12Z","abstract_excerpt":"Neural attention has become central to many state-of-the-art models in natural language processing and related domains. Attention networks are an easy-to-train and effective method for softly simulating alignment; however, the approach does not marginalize over latent alignments in a probabilistic sense. This property makes it difficult to compare attention to other alignment approaches, to compose it with probabilistic models, and to perform posterior inference conditioned on observed data. A related latent approach, hard attention, fixes these issues, but is generally harder to train and les"},"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":"1807.03756","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-10T16:59:12Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"eae6baa6afcf208fdd494c876c27e9f1faf6590aa0f63a5bcd2ae1acd92300db","abstract_canon_sha256":"552bb33e618dfe7ed6c87a51f5d8828b5155215dc6759ac763f625c07f5c98ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:19.366789Z","signature_b64":"98qjrY3SgHwkAqpF+ZMMymI5kjn23bJkD9xtr2zYCQ81NK31cGUy1ZM0TpP3E/AqQ7iBihEhbK0KKuIhvuxHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51bbea56d090274c2118a15fd54dc79cd2cda00d33d593caa20300bff0da6fba","last_reissued_at":"2026-05-18T00:01:19.366202Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:19.366202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Alignment and Variational Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander M. Rush, Demi Guo, Justin Chiu, Yoon Kim, Yuntian Deng","submitted_at":"2018-07-10T16:59:12Z","abstract_excerpt":"Neural attention has become central to many state-of-the-art models in natural language processing and related domains. Attention networks are an easy-to-train and effective method for softly simulating alignment; however, the approach does not marginalize over latent alignments in a probabilistic sense. This property makes it difficult to compare attention to other alignment approaches, to compose it with probabilistic models, and to perform posterior inference conditioned on observed data. A related latent approach, hard attention, fixes these issues, but is generally harder to train and les"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03756","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":"1807.03756","created_at":"2026-05-18T00:01:19.366294+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.03756v2","created_at":"2026-05-18T00:01:19.366294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03756","created_at":"2026-05-18T00:01:19.366294+00:00"},{"alias_kind":"pith_short_12","alias_value":"KG56UVWQSATU","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KG56UVWQSATUYIIY","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KG56UVWQ","created_at":"2026-05-18T12:32:33.847187+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":98,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KG56UVWQSATUYIIYUFP5KTOHTT","json":"https://pith.science/pith/KG56UVWQSATUYIIYUFP5KTOHTT.json","graph_json":"https://pith.science/api/pith-number/KG56UVWQSATUYIIYUFP5KTOHTT/graph.json","events_json":"https://pith.science/api/pith-number/KG56UVWQSATUYIIYUFP5KTOHTT/events.json","paper":"https://pith.science/paper/KG56UVWQ"},"agent_actions":{"view_html":"https://pith.science/pith/KG56UVWQSATUYIIYUFP5KTOHTT","download_json":"https://pith.science/pith/KG56UVWQSATUYIIYUFP5KTOHTT.json","view_paper":"https://pith.science/paper/KG56UVWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.03756&json=true","fetch_graph":"https://pith.science/api/pith-number/KG56UVWQSATUYIIYUFP5KTOHTT/graph.json","fetch_events":"https://pith.science/api/pith-number/KG56UVWQSATUYIIYUFP5KTOHTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KG56UVWQSATUYIIYUFP5KTOHTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KG56UVWQSATUYIIYUFP5KTOHTT/action/storage_attestation","attest_author":"https://pith.science/pith/KG56UVWQSATUYIIYUFP5KTOHTT/action/author_attestation","sign_citation":"https://pith.science/pith/KG56UVWQSATUYIIYUFP5KTOHTT/action/citation_signature","submit_replication":"https://pith.science/pith/KG56UVWQSATUYIIYUFP5KTOHTT/action/replication_record"}},"created_at":"2026-05-18T00:01:19.366294+00:00","updated_at":"2026-05-18T00:01:19.366294+00:00"}