{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:XRWI6Z364OREKKAEGBHSAIHWZD","short_pith_number":"pith:XRWI6Z36","schema_version":"1.0","canonical_sha256":"bc6c8f677ee3a2452804304f2020f6c8d4e966ebc5e89aa27b07ec5caf78507e","source":{"kind":"arxiv","id":"1509.00838","version":2},"attestation_state":"computed","paper":{"title":"What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Hongyuan Mei, Matthew R. Walter, Mohit Bansal","submitted_at":"2015-09-02T19:52:56Z","abstract_excerpt":"We propose an end-to-end, domain-independent neural encoder-aligner-decoder model for selective generation, i.e., the joint task of content selection and surface realization. Our model first encodes a full set of over-determined database event records via an LSTM-based recurrent neural network, then utilizes a novel coarse-to-fine aligner to identify the small subset of salient records to talk about, and finally employs a decoder to generate free-form descriptions of the aligned, selected records. Our model achieves the best selection and generation results reported to-date (with 59% relative "},"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":"1509.00838","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-02T19:52:56Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"0176d565bea9f56a51f74c84d15c41da9fd6016a1b8b0c672bc888a140327502","abstract_canon_sha256":"6ba3e249104a8266cdceb74f22dd732588f72f299fc7b796b6b59176c3336a77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:08.144410Z","signature_b64":"lccrRXjz0qPHb/tkEOu+L8pkYcijqSp8AAmkRguvwxHq/MVAenDXIP5Th4Fto+eV2EELssWuHRpr4/P/yby9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc6c8f677ee3a2452804304f2020f6c8d4e966ebc5e89aa27b07ec5caf78507e","last_reissued_at":"2026-05-18T01:23:08.143807Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:08.143807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Hongyuan Mei, Matthew R. Walter, Mohit Bansal","submitted_at":"2015-09-02T19:52:56Z","abstract_excerpt":"We propose an end-to-end, domain-independent neural encoder-aligner-decoder model for selective generation, i.e., the joint task of content selection and surface realization. Our model first encodes a full set of over-determined database event records via an LSTM-based recurrent neural network, then utilizes a novel coarse-to-fine aligner to identify the small subset of salient records to talk about, and finally employs a decoder to generate free-form descriptions of the aligned, selected records. Our model achieves the best selection and generation results reported to-date (with 59% relative "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.00838","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":"1509.00838","created_at":"2026-05-18T01:23:08.143904+00:00"},{"alias_kind":"arxiv_version","alias_value":"1509.00838v2","created_at":"2026-05-18T01:23:08.143904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.00838","created_at":"2026-05-18T01:23:08.143904+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRWI6Z364ORE","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRWI6Z364OREKKAE","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRWI6Z36","created_at":"2026-05-18T12:29:50.041715+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/XRWI6Z364OREKKAEGBHSAIHWZD","json":"https://pith.science/pith/XRWI6Z364OREKKAEGBHSAIHWZD.json","graph_json":"https://pith.science/api/pith-number/XRWI6Z364OREKKAEGBHSAIHWZD/graph.json","events_json":"https://pith.science/api/pith-number/XRWI6Z364OREKKAEGBHSAIHWZD/events.json","paper":"https://pith.science/paper/XRWI6Z36"},"agent_actions":{"view_html":"https://pith.science/pith/XRWI6Z364OREKKAEGBHSAIHWZD","download_json":"https://pith.science/pith/XRWI6Z364OREKKAEGBHSAIHWZD.json","view_paper":"https://pith.science/paper/XRWI6Z36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1509.00838&json=true","fetch_graph":"https://pith.science/api/pith-number/XRWI6Z364OREKKAEGBHSAIHWZD/graph.json","fetch_events":"https://pith.science/api/pith-number/XRWI6Z364OREKKAEGBHSAIHWZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRWI6Z364OREKKAEGBHSAIHWZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRWI6Z364OREKKAEGBHSAIHWZD/action/storage_attestation","attest_author":"https://pith.science/pith/XRWI6Z364OREKKAEGBHSAIHWZD/action/author_attestation","sign_citation":"https://pith.science/pith/XRWI6Z364OREKKAEGBHSAIHWZD/action/citation_signature","submit_replication":"https://pith.science/pith/XRWI6Z364OREKKAEGBHSAIHWZD/action/replication_record"}},"created_at":"2026-05-18T01:23:08.143904+00:00","updated_at":"2026-05-18T01:23:08.143904+00:00"}