{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KFFZTYORDEZTXV3R3F5OTWY5G2","short_pith_number":"pith:KFFZTYOR","schema_version":"1.0","canonical_sha256":"514b99e1d119333bd771d97ae9db1d369d881ac8ba377ae738a114e24d22c9b3","source":{"kind":"arxiv","id":"2306.10315","version":1},"attestation_state":"computed","paper":{"title":"FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Zeng, Jingang Wang, Keqing He, Weihao Zeng, Weiran Xu, Yejie Wang, Yunsen Xian","submitted_at":"2023-06-17T10:40:07Z","abstract_excerpt":"Pre-trained language models based on general text enable huge success in the NLP scenario. But the intrinsical difference of linguistic patterns between general text and task-oriented dialogues makes existing pre-trained language models less useful in practice. Current dialogue pre-training methods rely on a contrastive framework and face the challenges of both selecting true positives and hard negatives. In this paper, we propose a novel dialogue pre-training model, FutureTOD, which distills future knowledge to the representation of the previous dialogue context using a self-training framewor"},"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":"2306.10315","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-17T10:40:07Z","cross_cats_sorted":[],"title_canon_sha256":"341c61fb3181b6e89b07fc04552e5fac13793f5c27a1d41020ad232874a52acf","abstract_canon_sha256":"3eb32d171493e1b453fb3071ace09cf20078bcf68e768a9d63b145b52f2fee15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:36.350368Z","signature_b64":"DkYnYXiujbrk2DbEcm8OSQHfrwoIwOYDJm61ZPDelJE3u9fJSYDux3faSgUu1vaGIZhvCA173PZGDVemMfBoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"514b99e1d119333bd771d97ae9db1d369d881ac8ba377ae738a114e24d22c9b3","last_reissued_at":"2026-07-05T06:21:36.349893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:36.349893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Zeng, Jingang Wang, Keqing He, Weihao Zeng, Weiran Xu, Yejie Wang, Yunsen Xian","submitted_at":"2023-06-17T10:40:07Z","abstract_excerpt":"Pre-trained language models based on general text enable huge success in the NLP scenario. But the intrinsical difference of linguistic patterns between general text and task-oriented dialogues makes existing pre-trained language models less useful in practice. Current dialogue pre-training methods rely on a contrastive framework and face the challenges of both selecting true positives and hard negatives. In this paper, we propose a novel dialogue pre-training model, FutureTOD, which distills future knowledge to the representation of the previous dialogue context using a self-training framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10315","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/2306.10315/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":"2306.10315","created_at":"2026-07-05T06:21:36.349960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.10315v1","created_at":"2026-07-05T06:21:36.349960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10315","created_at":"2026-07-05T06:21:36.349960+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFFZTYORDEZT","created_at":"2026-07-05T06:21:36.349960+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFFZTYORDEZTXV3R","created_at":"2026-07-05T06:21:36.349960+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFFZTYOR","created_at":"2026-07-05T06:21:36.349960+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/KFFZTYORDEZTXV3R3F5OTWY5G2","json":"https://pith.science/pith/KFFZTYORDEZTXV3R3F5OTWY5G2.json","graph_json":"https://pith.science/api/pith-number/KFFZTYORDEZTXV3R3F5OTWY5G2/graph.json","events_json":"https://pith.science/api/pith-number/KFFZTYORDEZTXV3R3F5OTWY5G2/events.json","paper":"https://pith.science/paper/KFFZTYOR"},"agent_actions":{"view_html":"https://pith.science/pith/KFFZTYORDEZTXV3R3F5OTWY5G2","download_json":"https://pith.science/pith/KFFZTYORDEZTXV3R3F5OTWY5G2.json","view_paper":"https://pith.science/paper/KFFZTYOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.10315&json=true","fetch_graph":"https://pith.science/api/pith-number/KFFZTYORDEZTXV3R3F5OTWY5G2/graph.json","fetch_events":"https://pith.science/api/pith-number/KFFZTYORDEZTXV3R3F5OTWY5G2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFFZTYORDEZTXV3R3F5OTWY5G2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFFZTYORDEZTXV3R3F5OTWY5G2/action/storage_attestation","attest_author":"https://pith.science/pith/KFFZTYORDEZTXV3R3F5OTWY5G2/action/author_attestation","sign_citation":"https://pith.science/pith/KFFZTYORDEZTXV3R3F5OTWY5G2/action/citation_signature","submit_replication":"https://pith.science/pith/KFFZTYORDEZTXV3R3F5OTWY5G2/action/replication_record"}},"created_at":"2026-07-05T06:21:36.349960+00:00","updated_at":"2026-07-05T06:21:36.349960+00:00"}