{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:QUGEKN3BQFAQCKF4RBA5JUHNCY","short_pith_number":"pith:QUGEKN3B","schema_version":"1.0","canonical_sha256":"850c45376181410128bc8841d4d0ed16256b0b9db7731d878dd1f704dfe28d96","source":{"kind":"arxiv","id":"1512.06612","version":2},"attestation_state":"computed","paper":{"title":"Backward and Forward Language Modeling for Constrained Sentence Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Ge Li, Lili Mou, Lu Zhang, Rui Yan, Zhi Jin","submitted_at":"2015-12-21T13:07:31Z","abstract_excerpt":"Recent language models, especially those based on recurrent neural networks (RNNs), make it possible to generate natural language from a learned probability. Language generation has wide applications including machine translation, summarization, question answering, conversation systems, etc. Existing methods typically learn a joint probability of words conditioned on additional information, which is (either statically or dynamically) fed to RNN's hidden layer. In many applications, we are likely to impose hard constraints on the generated texts, i.e., a particular word must appear in the sente"},"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":"1512.06612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-12-21T13:07:31Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"fac6497ca7f641e05bcd5b45322f2c8425053ead6d5d95a29a88ab8e4e1efb14","abstract_canon_sha256":"e52fe262102f1ad51cf71b4f738a88c75ac2e8462a33dc410ef7ce975dafc58b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:28.571348Z","signature_b64":"mmM9PF6OafuaW2DlcNPuGTHr4k+PkVWca3RMqLMHYL1/RzBrUPqaezsfRJY+FYkw1+34387L1lAAmK4mxJlqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"850c45376181410128bc8841d4d0ed16256b0b9db7731d878dd1f704dfe28d96","last_reissued_at":"2026-05-18T01:23:28.570628Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:28.570628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Backward and Forward Language Modeling for Constrained Sentence Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Ge Li, Lili Mou, Lu Zhang, Rui Yan, Zhi Jin","submitted_at":"2015-12-21T13:07:31Z","abstract_excerpt":"Recent language models, especially those based on recurrent neural networks (RNNs), make it possible to generate natural language from a learned probability. Language generation has wide applications including machine translation, summarization, question answering, conversation systems, etc. Existing methods typically learn a joint probability of words conditioned on additional information, which is (either statically or dynamically) fed to RNN's hidden layer. In many applications, we are likely to impose hard constraints on the generated texts, i.e., a particular word must appear in the sente"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.06612","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":"1512.06612","created_at":"2026-05-18T01:23:28.570743+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.06612v2","created_at":"2026-05-18T01:23:28.570743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.06612","created_at":"2026-05-18T01:23:28.570743+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUGEKN3BQFAQ","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUGEKN3BQFAQCKF4","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUGEKN3B","created_at":"2026-05-18T12:29:39.896362+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/QUGEKN3BQFAQCKF4RBA5JUHNCY","json":"https://pith.science/pith/QUGEKN3BQFAQCKF4RBA5JUHNCY.json","graph_json":"https://pith.science/api/pith-number/QUGEKN3BQFAQCKF4RBA5JUHNCY/graph.json","events_json":"https://pith.science/api/pith-number/QUGEKN3BQFAQCKF4RBA5JUHNCY/events.json","paper":"https://pith.science/paper/QUGEKN3B"},"agent_actions":{"view_html":"https://pith.science/pith/QUGEKN3BQFAQCKF4RBA5JUHNCY","download_json":"https://pith.science/pith/QUGEKN3BQFAQCKF4RBA5JUHNCY.json","view_paper":"https://pith.science/paper/QUGEKN3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.06612&json=true","fetch_graph":"https://pith.science/api/pith-number/QUGEKN3BQFAQCKF4RBA5JUHNCY/graph.json","fetch_events":"https://pith.science/api/pith-number/QUGEKN3BQFAQCKF4RBA5JUHNCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUGEKN3BQFAQCKF4RBA5JUHNCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUGEKN3BQFAQCKF4RBA5JUHNCY/action/storage_attestation","attest_author":"https://pith.science/pith/QUGEKN3BQFAQCKF4RBA5JUHNCY/action/author_attestation","sign_citation":"https://pith.science/pith/QUGEKN3BQFAQCKF4RBA5JUHNCY/action/citation_signature","submit_replication":"https://pith.science/pith/QUGEKN3BQFAQCKF4RBA5JUHNCY/action/replication_record"}},"created_at":"2026-05-18T01:23:28.570743+00:00","updated_at":"2026-05-18T01:23:28.570743+00:00"}