{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:E3A3BALLWSITSIGC54BUGD2ZHO","short_pith_number":"pith:E3A3BALL","schema_version":"1.0","canonical_sha256":"26c1b0816bb4913920c2ef03430f593b801940adb5d0c3f89f3f0417f28b7897","source":{"kind":"arxiv","id":"2110.11514","version":1},"attestation_state":"computed","paper":{"title":"SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baolin Peng, Chenguang Zhu, Chunyuan Li, Jianfeng Gao, Jinchao Li, Zhu Zhang","submitted_at":"2021-10-21T23:13:04Z","abstract_excerpt":"In this paper we explore the use of symbolic knowledge and machine teaching to reduce human data labeling efforts in building neural task bots. We propose SYNERGY, a hybrid learning framework where a task bot is developed in two steps: (i) Symbolic knowledge to neural networks: Large amounts of simulated dialog sessions are generated based on task-specific symbolic knowledge which is represented as a task schema consisting of dialog flows and task-oriented databases. Then a pre-trained neural dialog model, SOLOIST, is fine-tuned on the simulated dialogs to build a bot for the task. (ii) Neural"},"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":"2110.11514","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-21T23:13:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ec04ce92e55dba2c823bf5732632dde0d2902c88f91496b3d177952aabf1726e","abstract_canon_sha256":"1ebedc4f7522e02c2cd14e0eee12baadcc52eaa9fced308bdfc4309ca7459529"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:47.976549Z","signature_b64":"dKc1qCNgEJ+PM+Cx5uXK5+tO2v5owmwNOMmQxVd/NUHfYlLD/QUMiqKzyhJLhkMSYyjNdMVyk/Pk0BvVfiTsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26c1b0816bb4913920c2ef03430f593b801940adb5d0c3f89f3f0417f28b7897","last_reissued_at":"2026-07-05T03:24:47.976054Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:47.976054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baolin Peng, Chenguang Zhu, Chunyuan Li, Jianfeng Gao, Jinchao Li, Zhu Zhang","submitted_at":"2021-10-21T23:13:04Z","abstract_excerpt":"In this paper we explore the use of symbolic knowledge and machine teaching to reduce human data labeling efforts in building neural task bots. We propose SYNERGY, a hybrid learning framework where a task bot is developed in two steps: (i) Symbolic knowledge to neural networks: Large amounts of simulated dialog sessions are generated based on task-specific symbolic knowledge which is represented as a task schema consisting of dialog flows and task-oriented databases. Then a pre-trained neural dialog model, SOLOIST, is fine-tuned on the simulated dialogs to build a bot for the task. (ii) Neural"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.11514","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/2110.11514/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":"2110.11514","created_at":"2026-07-05T03:24:47.976129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.11514v1","created_at":"2026-07-05T03:24:47.976129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.11514","created_at":"2026-07-05T03:24:47.976129+00:00"},{"alias_kind":"pith_short_12","alias_value":"E3A3BALLWSIT","created_at":"2026-07-05T03:24:47.976129+00:00"},{"alias_kind":"pith_short_16","alias_value":"E3A3BALLWSITSIGC","created_at":"2026-07-05T03:24:47.976129+00:00"},{"alias_kind":"pith_short_8","alias_value":"E3A3BALL","created_at":"2026-07-05T03:24:47.976129+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/E3A3BALLWSITSIGC54BUGD2ZHO","json":"https://pith.science/pith/E3A3BALLWSITSIGC54BUGD2ZHO.json","graph_json":"https://pith.science/api/pith-number/E3A3BALLWSITSIGC54BUGD2ZHO/graph.json","events_json":"https://pith.science/api/pith-number/E3A3BALLWSITSIGC54BUGD2ZHO/events.json","paper":"https://pith.science/paper/E3A3BALL"},"agent_actions":{"view_html":"https://pith.science/pith/E3A3BALLWSITSIGC54BUGD2ZHO","download_json":"https://pith.science/pith/E3A3BALLWSITSIGC54BUGD2ZHO.json","view_paper":"https://pith.science/paper/E3A3BALL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.11514&json=true","fetch_graph":"https://pith.science/api/pith-number/E3A3BALLWSITSIGC54BUGD2ZHO/graph.json","fetch_events":"https://pith.science/api/pith-number/E3A3BALLWSITSIGC54BUGD2ZHO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E3A3BALLWSITSIGC54BUGD2ZHO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E3A3BALLWSITSIGC54BUGD2ZHO/action/storage_attestation","attest_author":"https://pith.science/pith/E3A3BALLWSITSIGC54BUGD2ZHO/action/author_attestation","sign_citation":"https://pith.science/pith/E3A3BALLWSITSIGC54BUGD2ZHO/action/citation_signature","submit_replication":"https://pith.science/pith/E3A3BALLWSITSIGC54BUGD2ZHO/action/replication_record"}},"created_at":"2026-07-05T03:24:47.976129+00:00","updated_at":"2026-07-05T03:24:47.976129+00:00"}