{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:D7RHQIKQYOGHTSSZCPNNCVG2UC","short_pith_number":"pith:D7RHQIKQ","schema_version":"1.0","canonical_sha256":"1fe2782150c38c79ca5913dad154daa092f7653025085c7e39de8fc32976ec76","source":{"kind":"arxiv","id":"2007.08557","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Text Generation by Learning from Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Irwin King, Jingjing Li, Lili Mou, Michael R. Lyu, Xin Jiang, Zichao Li","submitted_at":"2020-07-09T04:34:48Z","abstract_excerpt":"In this work, we present TGLS, a novel framework to unsupervised Text Generation by Learning from Search. We start by applying a strong search algorithm (in particular, simulated annealing) towards a heuristically defined objective that (roughly) estimates the quality of sentences. Then, a conditional generative model learns from the search results, and meanwhile smooth out the noise of search. The alternation between search and learning can be repeated for performance bootstrapping. We demonstrate the effectiveness of TGLS on two real-world natural language generation tasks, paraphrase genera"},"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":"2007.08557","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-09T04:34:48Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG","stat.ML"],"title_canon_sha256":"ef30f56e478ec94b12f6e975be29a9bb7228297e7310fb9ee7b49715281fd850","abstract_canon_sha256":"a2ca682404d5b126f8d03ca973c751bc0de9292ab855a5031bae8fe05aecca95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:19:54.225617Z","signature_b64":"FsgMt0T7IANhJ5w4440E6xP36FrrjQlIbROYtbgcR5a43zxM1L6zncT3H95fek4Yl/ZfEKJJ5W61nJV10rJkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fe2782150c38c79ca5913dad154daa092f7653025085c7e39de8fc32976ec76","last_reissued_at":"2026-07-05T01:19:54.225053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:19:54.225053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Text Generation by Learning from Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Irwin King, Jingjing Li, Lili Mou, Michael R. Lyu, Xin Jiang, Zichao Li","submitted_at":"2020-07-09T04:34:48Z","abstract_excerpt":"In this work, we present TGLS, a novel framework to unsupervised Text Generation by Learning from Search. We start by applying a strong search algorithm (in particular, simulated annealing) towards a heuristically defined objective that (roughly) estimates the quality of sentences. Then, a conditional generative model learns from the search results, and meanwhile smooth out the noise of search. The alternation between search and learning can be repeated for performance bootstrapping. We demonstrate the effectiveness of TGLS on two real-world natural language generation tasks, paraphrase genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.08557","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.08557/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2007.08557","created_at":"2026-07-05T01:19:54.225110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.08557v1","created_at":"2026-07-05T01:19:54.225110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.08557","created_at":"2026-07-05T01:19:54.225110+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7RHQIKQYOGH","created_at":"2026-07-05T01:19:54.225110+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7RHQIKQYOGHTSSZ","created_at":"2026-07-05T01:19:54.225110+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7RHQIKQ","created_at":"2026-07-05T01:19:54.225110+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/D7RHQIKQYOGHTSSZCPNNCVG2UC","json":"https://pith.science/pith/D7RHQIKQYOGHTSSZCPNNCVG2UC.json","graph_json":"https://pith.science/api/pith-number/D7RHQIKQYOGHTSSZCPNNCVG2UC/graph.json","events_json":"https://pith.science/api/pith-number/D7RHQIKQYOGHTSSZCPNNCVG2UC/events.json","paper":"https://pith.science/paper/D7RHQIKQ"},"agent_actions":{"view_html":"https://pith.science/pith/D7RHQIKQYOGHTSSZCPNNCVG2UC","download_json":"https://pith.science/pith/D7RHQIKQYOGHTSSZCPNNCVG2UC.json","view_paper":"https://pith.science/paper/D7RHQIKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.08557&json=true","fetch_graph":"https://pith.science/api/pith-number/D7RHQIKQYOGHTSSZCPNNCVG2UC/graph.json","fetch_events":"https://pith.science/api/pith-number/D7RHQIKQYOGHTSSZCPNNCVG2UC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7RHQIKQYOGHTSSZCPNNCVG2UC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7RHQIKQYOGHTSSZCPNNCVG2UC/action/storage_attestation","attest_author":"https://pith.science/pith/D7RHQIKQYOGHTSSZCPNNCVG2UC/action/author_attestation","sign_citation":"https://pith.science/pith/D7RHQIKQYOGHTSSZCPNNCVG2UC/action/citation_signature","submit_replication":"https://pith.science/pith/D7RHQIKQYOGHTSSZCPNNCVG2UC/action/replication_record"}},"created_at":"2026-07-05T01:19:54.225110+00:00","updated_at":"2026-07-05T01:19:54.225110+00:00"}