{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TUUZ3CG466LRI7J3M63OMFOFRV","short_pith_number":"pith:TUUZ3CG4","schema_version":"1.0","canonical_sha256":"9d299d88dcf797147d3b67b6e615c58d7e2300a6f9cf5fca01b17a723913fb82","source":{"kind":"arxiv","id":"2209.00930","version":1},"attestation_state":"computed","paper":{"title":"Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chaehyeong Kim, Hyungjoo Chae, Jinyoung Yeo, Se June Joo, Seungone Kim, Seung-won Hwang","submitted_at":"2022-09-02T10:08:28Z","abstract_excerpt":"In this paper, we propose to leverage the unique characteristics of dialogues sharing commonsense knowledge across participants, to resolve the difficulties in summarizing them. We present SICK, a framework that uses commonsense inferences as additional context. Compared to previous work that solely relies on the input dialogue, SICK uses an external knowledge model to generate a rich set of commonsense inferences and selects the most probable one with a similarity-based selection method. Built upon SICK, SICK++ utilizes commonsense as supervision, where the task of generating commonsense infe"},"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":"2209.00930","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-02T10:08:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4ecd10df6715bc6b16a8d0805f87b947c7d214f69e736374edef02e40f1648dd","abstract_canon_sha256":"a48ae7a0de9955e6f2626f1ff099e9c3d19b0dd5a2106a6bccf9d2115b2f0686"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:06.675797Z","signature_b64":"IksKyXdTaabYFn9S/5vhmPP8zXrOyWGXkmf3sPTxQp2mQJAdlmELlIvPAhSorX5MZVCSXZCs7XQS1jHk6AHDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d299d88dcf797147d3b67b6e615c58d7e2300a6f9cf5fca01b17a723913fb82","last_reissued_at":"2026-07-05T04:54:06.675380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:06.675380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chaehyeong Kim, Hyungjoo Chae, Jinyoung Yeo, Se June Joo, Seungone Kim, Seung-won Hwang","submitted_at":"2022-09-02T10:08:28Z","abstract_excerpt":"In this paper, we propose to leverage the unique characteristics of dialogues sharing commonsense knowledge across participants, to resolve the difficulties in summarizing them. We present SICK, a framework that uses commonsense inferences as additional context. Compared to previous work that solely relies on the input dialogue, SICK uses an external knowledge model to generate a rich set of commonsense inferences and selects the most probable one with a similarity-based selection method. Built upon SICK, SICK++ utilizes commonsense as supervision, where the task of generating commonsense infe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.00930","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/2209.00930/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":"2209.00930","created_at":"2026-07-05T04:54:06.675443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.00930v1","created_at":"2026-07-05T04:54:06.675443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.00930","created_at":"2026-07-05T04:54:06.675443+00:00"},{"alias_kind":"pith_short_12","alias_value":"TUUZ3CG466LR","created_at":"2026-07-05T04:54:06.675443+00:00"},{"alias_kind":"pith_short_16","alias_value":"TUUZ3CG466LRI7J3","created_at":"2026-07-05T04:54:06.675443+00:00"},{"alias_kind":"pith_short_8","alias_value":"TUUZ3CG4","created_at":"2026-07-05T04:54:06.675443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13364","citing_title":"OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TUUZ3CG466LRI7J3M63OMFOFRV","json":"https://pith.science/pith/TUUZ3CG466LRI7J3M63OMFOFRV.json","graph_json":"https://pith.science/api/pith-number/TUUZ3CG466LRI7J3M63OMFOFRV/graph.json","events_json":"https://pith.science/api/pith-number/TUUZ3CG466LRI7J3M63OMFOFRV/events.json","paper":"https://pith.science/paper/TUUZ3CG4"},"agent_actions":{"view_html":"https://pith.science/pith/TUUZ3CG466LRI7J3M63OMFOFRV","download_json":"https://pith.science/pith/TUUZ3CG466LRI7J3M63OMFOFRV.json","view_paper":"https://pith.science/paper/TUUZ3CG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.00930&json=true","fetch_graph":"https://pith.science/api/pith-number/TUUZ3CG466LRI7J3M63OMFOFRV/graph.json","fetch_events":"https://pith.science/api/pith-number/TUUZ3CG466LRI7J3M63OMFOFRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TUUZ3CG466LRI7J3M63OMFOFRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TUUZ3CG466LRI7J3M63OMFOFRV/action/storage_attestation","attest_author":"https://pith.science/pith/TUUZ3CG466LRI7J3M63OMFOFRV/action/author_attestation","sign_citation":"https://pith.science/pith/TUUZ3CG466LRI7J3M63OMFOFRV/action/citation_signature","submit_replication":"https://pith.science/pith/TUUZ3CG466LRI7J3M63OMFOFRV/action/replication_record"}},"created_at":"2026-07-05T04:54:06.675443+00:00","updated_at":"2026-07-05T04:54:06.675443+00:00"}