{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:M5YSSLRK5ZNJTYZBSFN3OWRDBU","short_pith_number":"pith:M5YSSLRK","schema_version":"1.0","canonical_sha256":"6771292e2aee5a99e321915bb75a230d3680b37815bc374b1b705014cd97ea58","source":{"kind":"arxiv","id":"2103.16289","version":1},"attestation_state":"computed","paper":{"title":"Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Debanjan Chaudhuri, Jens Lehmann, Md Rashad Al Hasan Rony","submitted_at":"2021-03-30T12:36:00Z","abstract_excerpt":"Generating knowledge grounded responses in both goal and non-goal oriented dialogue systems is an important research challenge. Knowledge Graphs (KG) can be viewed as an abstraction of the real world, which can potentially facilitate a dialogue system to produce knowledge grounded responses. However, integrating KGs into the dialogue generation process in an end-to-end manner is a non-trivial task. This paper proposes a novel architecture for integrating KGs into the response generation process by training a BERT model that learns to answer using the elements of the KG (entities and relations)"},"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":"2103.16289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-30T12:36:00Z","cross_cats_sorted":[],"title_canon_sha256":"9020ba806bbe29c532d91ed93d33027fb505f565d761d66970b6ded8ab843859","abstract_canon_sha256":"29c76134646b18e7f75fbdb1956997b9e38a95a88478fd004a2eed499a49606c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:50.320948Z","signature_b64":"kN1ahlX4qSE5fvIolevs+HgAzCWAqOVTCpZsgVckx/5AZLQ7HFu1/tv3L/0mAnHT3U5kADJIpuNailAaY8uYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6771292e2aee5a99e321915bb75a230d3680b37815bc374b1b705014cd97ea58","last_reissued_at":"2026-07-05T02:27:50.320480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:50.320480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Debanjan Chaudhuri, Jens Lehmann, Md Rashad Al Hasan Rony","submitted_at":"2021-03-30T12:36:00Z","abstract_excerpt":"Generating knowledge grounded responses in both goal and non-goal oriented dialogue systems is an important research challenge. Knowledge Graphs (KG) can be viewed as an abstraction of the real world, which can potentially facilitate a dialogue system to produce knowledge grounded responses. However, integrating KGs into the dialogue generation process in an end-to-end manner is a non-trivial task. This paper proposes a novel architecture for integrating KGs into the response generation process by training a BERT model that learns to answer using the elements of the KG (entities and relations)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16289","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/2103.16289/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":"2103.16289","created_at":"2026-07-05T02:27:50.320560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.16289v1","created_at":"2026-07-05T02:27:50.320560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16289","created_at":"2026-07-05T02:27:50.320560+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5YSSLRK5ZNJ","created_at":"2026-07-05T02:27:50.320560+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5YSSLRK5ZNJTYZB","created_at":"2026-07-05T02:27:50.320560+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5YSSLRK","created_at":"2026-07-05T02:27:50.320560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.26383","citing_title":"Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5YSSLRK5ZNJTYZBSFN3OWRDBU","json":"https://pith.science/pith/M5YSSLRK5ZNJTYZBSFN3OWRDBU.json","graph_json":"https://pith.science/api/pith-number/M5YSSLRK5ZNJTYZBSFN3OWRDBU/graph.json","events_json":"https://pith.science/api/pith-number/M5YSSLRK5ZNJTYZBSFN3OWRDBU/events.json","paper":"https://pith.science/paper/M5YSSLRK"},"agent_actions":{"view_html":"https://pith.science/pith/M5YSSLRK5ZNJTYZBSFN3OWRDBU","download_json":"https://pith.science/pith/M5YSSLRK5ZNJTYZBSFN3OWRDBU.json","view_paper":"https://pith.science/paper/M5YSSLRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.16289&json=true","fetch_graph":"https://pith.science/api/pith-number/M5YSSLRK5ZNJTYZBSFN3OWRDBU/graph.json","fetch_events":"https://pith.science/api/pith-number/M5YSSLRK5ZNJTYZBSFN3OWRDBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5YSSLRK5ZNJTYZBSFN3OWRDBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5YSSLRK5ZNJTYZBSFN3OWRDBU/action/storage_attestation","attest_author":"https://pith.science/pith/M5YSSLRK5ZNJTYZBSFN3OWRDBU/action/author_attestation","sign_citation":"https://pith.science/pith/M5YSSLRK5ZNJTYZBSFN3OWRDBU/action/citation_signature","submit_replication":"https://pith.science/pith/M5YSSLRK5ZNJTYZBSFN3OWRDBU/action/replication_record"}},"created_at":"2026-07-05T02:27:50.320560+00:00","updated_at":"2026-07-05T02:27:50.320560+00:00"}