{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LLU2MIGUQWDM7KST2AYX5SH5OQ","short_pith_number":"pith:LLU2MIGU","schema_version":"1.0","canonical_sha256":"5ae9a620d48586cfaa53d0317ec8fd7414c9f34484787b3e5a7fb2ab08a0f4ee","source":{"kind":"arxiv","id":"2505.23006","version":1},"attestation_state":"computed","paper":{"title":"A Practical Approach for Building Production-Grade Conversational Agents with Workflow Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aelim Ahn, Chiwan Park, Daeryong Kim, Hyerin Park, Hyosun Wang, JiHoon Kang, Jihyeon Roh, Kichang Yang, Min Seok Kim, Wonjun Jang, Woosung Hwang","submitted_at":"2025-05-29T02:30:27Z","abstract_excerpt":"The advancement of Large Language Models (LLMs) has led to significant improvements in various service domains, including search, recommendation, and chatbot applications. However, applying state-of-the-art (SOTA) research to industrial settings presents challenges, as it requires maintaining flexible conversational abilities while also strictly complying with service-specific constraints. This can be seen as two conflicting requirements due to the probabilistic nature of LLMs. In this paper, we propose our approach to addressing this challenge and detail the strategies we employed to overcome"},"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":"2505.23006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T02:30:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"feadcfb0fa953c202bae9b7651758f8346e54cf4fc9e41f7f51ed38d809ac611","abstract_canon_sha256":"1585d7a11d75d7d402d307ab958f2c6f30bdfc59823b3b2eea45805d76509597"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:53.359284Z","signature_b64":"3I3Rt1/sJp7GOr5uieNS1pq5rt3R6V4HPYS4Fiy7dipzweEe7Nmg4YfNXNF96Izqd5QqjPAnUp06TYQogK9yAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ae9a620d48586cfaa53d0317ec8fd7414c9f34484787b3e5a7fb2ab08a0f4ee","last_reissued_at":"2026-07-05T11:11:53.358822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:53.358822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Practical Approach for Building Production-Grade Conversational Agents with Workflow Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aelim Ahn, Chiwan Park, Daeryong Kim, Hyerin Park, Hyosun Wang, JiHoon Kang, Jihyeon Roh, Kichang Yang, Min Seok Kim, Wonjun Jang, Woosung Hwang","submitted_at":"2025-05-29T02:30:27Z","abstract_excerpt":"The advancement of Large Language Models (LLMs) has led to significant improvements in various service domains, including search, recommendation, and chatbot applications. However, applying state-of-the-art (SOTA) research to industrial settings presents challenges, as it requires maintaining flexible conversational abilities while also strictly complying with service-specific constraints. This can be seen as two conflicting requirements due to the probabilistic nature of LLMs. In this paper, we propose our approach to addressing this challenge and detail the strategies we employed to overcome"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23006","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/2505.23006/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":"2505.23006","created_at":"2026-07-05T11:11:53.358880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23006v1","created_at":"2026-07-05T11:11:53.358880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23006","created_at":"2026-07-05T11:11:53.358880+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLU2MIGUQWDM","created_at":"2026-07-05T11:11:53.358880+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLU2MIGUQWDM7KST","created_at":"2026-07-05T11:11:53.358880+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLU2MIGU","created_at":"2026-07-05T11:11:53.358880+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/LLU2MIGUQWDM7KST2AYX5SH5OQ","json":"https://pith.science/pith/LLU2MIGUQWDM7KST2AYX5SH5OQ.json","graph_json":"https://pith.science/api/pith-number/LLU2MIGUQWDM7KST2AYX5SH5OQ/graph.json","events_json":"https://pith.science/api/pith-number/LLU2MIGUQWDM7KST2AYX5SH5OQ/events.json","paper":"https://pith.science/paper/LLU2MIGU"},"agent_actions":{"view_html":"https://pith.science/pith/LLU2MIGUQWDM7KST2AYX5SH5OQ","download_json":"https://pith.science/pith/LLU2MIGUQWDM7KST2AYX5SH5OQ.json","view_paper":"https://pith.science/paper/LLU2MIGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23006&json=true","fetch_graph":"https://pith.science/api/pith-number/LLU2MIGUQWDM7KST2AYX5SH5OQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LLU2MIGUQWDM7KST2AYX5SH5OQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLU2MIGUQWDM7KST2AYX5SH5OQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLU2MIGUQWDM7KST2AYX5SH5OQ/action/storage_attestation","attest_author":"https://pith.science/pith/LLU2MIGUQWDM7KST2AYX5SH5OQ/action/author_attestation","sign_citation":"https://pith.science/pith/LLU2MIGUQWDM7KST2AYX5SH5OQ/action/citation_signature","submit_replication":"https://pith.science/pith/LLU2MIGUQWDM7KST2AYX5SH5OQ/action/replication_record"}},"created_at":"2026-07-05T11:11:53.358880+00:00","updated_at":"2026-07-05T11:11:53.358880+00:00"}