{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MEEBBVMSDIKZW6AN6GS764QHQB","short_pith_number":"pith:MEEBBVMS","schema_version":"1.0","canonical_sha256":"610810d5921a159b780df1a5ff72078054fe73d80ad376783d93675a8adea5a0","source":{"kind":"arxiv","id":"2206.05519","version":1},"attestation_state":"computed","paper":{"title":"Bridging the Gap Between Training and Inference of Bayesian Controllable Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bingning Wang, Haijin Liang, Han Liu, Jianjin Xu, Ting Yao, Xiaolin Hu","submitted_at":"2022-06-11T12:52:32Z","abstract_excerpt":"Large-scale pre-trained language models have achieved great success on natural language generation tasks. However, it is difficult to control the pre-trained language models to generate sentences with the desired attribute such as topic and sentiment, etc. Recently, Bayesian Controllable Language Models (BCLMs) have been shown to be efficient in controllable language generation. Rather than fine-tuning the parameters of pre-trained language models, BCLMs use external discriminators to guide the generation of pre-trained language models. However, the mismatch between training and inference of B"},"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":"2206.05519","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-11T12:52:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1d6778b9ecf93d846fb9688e94f413aba121dc66a81a1c2b8c8a3ad2e17a7ae8","abstract_canon_sha256":"42bba80b41f1b1fe465fb35da321682366c24b34b85fcd9b88d7bb162c7bc9c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:00.176913Z","signature_b64":"ct4/mYnoZJbQ8XEkSMDMJNVmAGg7O4fTjCIKbGjYWP+W/9+pmSOpSk8tfMAvAgt4nI51ZNgMe6mbl/ezbG5OCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"610810d5921a159b780df1a5ff72078054fe73d80ad376783d93675a8adea5a0","last_reissued_at":"2026-07-05T04:31:00.176547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:00.176547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Gap Between Training and Inference of Bayesian Controllable Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bingning Wang, Haijin Liang, Han Liu, Jianjin Xu, Ting Yao, Xiaolin Hu","submitted_at":"2022-06-11T12:52:32Z","abstract_excerpt":"Large-scale pre-trained language models have achieved great success on natural language generation tasks. However, it is difficult to control the pre-trained language models to generate sentences with the desired attribute such as topic and sentiment, etc. Recently, Bayesian Controllable Language Models (BCLMs) have been shown to be efficient in controllable language generation. Rather than fine-tuning the parameters of pre-trained language models, BCLMs use external discriminators to guide the generation of pre-trained language models. However, the mismatch between training and inference of B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05519","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/2206.05519/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":"2206.05519","created_at":"2026-07-05T04:31:00.176603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.05519v1","created_at":"2026-07-05T04:31:00.176603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05519","created_at":"2026-07-05T04:31:00.176603+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEEBBVMSDIKZ","created_at":"2026-07-05T04:31:00.176603+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEEBBVMSDIKZW6AN","created_at":"2026-07-05T04:31:00.176603+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEEBBVMS","created_at":"2026-07-05T04:31:00.176603+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/MEEBBVMSDIKZW6AN6GS764QHQB","json":"https://pith.science/pith/MEEBBVMSDIKZW6AN6GS764QHQB.json","graph_json":"https://pith.science/api/pith-number/MEEBBVMSDIKZW6AN6GS764QHQB/graph.json","events_json":"https://pith.science/api/pith-number/MEEBBVMSDIKZW6AN6GS764QHQB/events.json","paper":"https://pith.science/paper/MEEBBVMS"},"agent_actions":{"view_html":"https://pith.science/pith/MEEBBVMSDIKZW6AN6GS764QHQB","download_json":"https://pith.science/pith/MEEBBVMSDIKZW6AN6GS764QHQB.json","view_paper":"https://pith.science/paper/MEEBBVMS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.05519&json=true","fetch_graph":"https://pith.science/api/pith-number/MEEBBVMSDIKZW6AN6GS764QHQB/graph.json","fetch_events":"https://pith.science/api/pith-number/MEEBBVMSDIKZW6AN6GS764QHQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEEBBVMSDIKZW6AN6GS764QHQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEEBBVMSDIKZW6AN6GS764QHQB/action/storage_attestation","attest_author":"https://pith.science/pith/MEEBBVMSDIKZW6AN6GS764QHQB/action/author_attestation","sign_citation":"https://pith.science/pith/MEEBBVMSDIKZW6AN6GS764QHQB/action/citation_signature","submit_replication":"https://pith.science/pith/MEEBBVMSDIKZW6AN6GS764QHQB/action/replication_record"}},"created_at":"2026-07-05T04:31:00.176603+00:00","updated_at":"2026-07-05T04:31:00.176603+00:00"}