{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S76TDHU7DUEGGYW7WB4MN5OH7Q","short_pith_number":"pith:S76TDHU7","schema_version":"1.0","canonical_sha256":"97fd319e9f1d086362dfb078c6f5c7fc3120e3235c35d4e1b19fd550ab381286","source":{"kind":"arxiv","id":"2501.10328","version":1},"attestation_state":"computed","paper":{"title":"BoK: Introducing Bag-of-Keywords Loss for Interpretable Dialogue Response Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maunendra Sankar Desarkar, Suvodip Dey","submitted_at":"2025-01-17T17:57:49Z","abstract_excerpt":"The standard language modeling (LM) loss by itself has been shown to be inadequate for effective dialogue modeling. As a result, various training approaches, such as auxiliary loss functions and leveraging human feedback, are being adopted to enrich open-domain dialogue systems. One such auxiliary loss function is Bag-of-Words (BoW) loss, defined as the cross-entropy loss for predicting all the words/tokens of the next utterance. In this work, we propose a novel auxiliary loss named Bag-of-Keywords (BoK) loss to capture the central thought of the response through keyword prediction and leverag"},"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":"2501.10328","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-17T17:57:49Z","cross_cats_sorted":[],"title_canon_sha256":"bc80c70860a91a4a6a5a0314adbe566f8d875b8d01a2e258fe85ec3503e1b515","abstract_canon_sha256":"bc6e110a6b5b8946054790506bf795ed89e0122dcba56990ece7267d12b016a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:20.300935Z","signature_b64":"fasAxptdD1jkKy7oK2e/u8HlddhOmSnvOEWn+fdS9mCvDn6EMvvpM0kz9R4RykQ8QdcNQ4UWoqcb7KDdk6grBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97fd319e9f1d086362dfb078c6f5c7fc3120e3235c35d4e1b19fd550ab381286","last_reissued_at":"2026-07-05T10:02:20.300352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:20.300352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BoK: Introducing Bag-of-Keywords Loss for Interpretable Dialogue Response Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maunendra Sankar Desarkar, Suvodip Dey","submitted_at":"2025-01-17T17:57:49Z","abstract_excerpt":"The standard language modeling (LM) loss by itself has been shown to be inadequate for effective dialogue modeling. As a result, various training approaches, such as auxiliary loss functions and leveraging human feedback, are being adopted to enrich open-domain dialogue systems. One such auxiliary loss function is Bag-of-Words (BoW) loss, defined as the cross-entropy loss for predicting all the words/tokens of the next utterance. In this work, we propose a novel auxiliary loss named Bag-of-Keywords (BoK) loss to capture the central thought of the response through keyword prediction and leverag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10328","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/2501.10328/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":"2501.10328","created_at":"2026-07-05T10:02:20.300412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10328v1","created_at":"2026-07-05T10:02:20.300412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10328","created_at":"2026-07-05T10:02:20.300412+00:00"},{"alias_kind":"pith_short_12","alias_value":"S76TDHU7DUEG","created_at":"2026-07-05T10:02:20.300412+00:00"},{"alias_kind":"pith_short_16","alias_value":"S76TDHU7DUEGGYW7","created_at":"2026-07-05T10:02:20.300412+00:00"},{"alias_kind":"pith_short_8","alias_value":"S76TDHU7","created_at":"2026-07-05T10:02:20.300412+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/S76TDHU7DUEGGYW7WB4MN5OH7Q","json":"https://pith.science/pith/S76TDHU7DUEGGYW7WB4MN5OH7Q.json","graph_json":"https://pith.science/api/pith-number/S76TDHU7DUEGGYW7WB4MN5OH7Q/graph.json","events_json":"https://pith.science/api/pith-number/S76TDHU7DUEGGYW7WB4MN5OH7Q/events.json","paper":"https://pith.science/paper/S76TDHU7"},"agent_actions":{"view_html":"https://pith.science/pith/S76TDHU7DUEGGYW7WB4MN5OH7Q","download_json":"https://pith.science/pith/S76TDHU7DUEGGYW7WB4MN5OH7Q.json","view_paper":"https://pith.science/paper/S76TDHU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10328&json=true","fetch_graph":"https://pith.science/api/pith-number/S76TDHU7DUEGGYW7WB4MN5OH7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/S76TDHU7DUEGGYW7WB4MN5OH7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S76TDHU7DUEGGYW7WB4MN5OH7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S76TDHU7DUEGGYW7WB4MN5OH7Q/action/storage_attestation","attest_author":"https://pith.science/pith/S76TDHU7DUEGGYW7WB4MN5OH7Q/action/author_attestation","sign_citation":"https://pith.science/pith/S76TDHU7DUEGGYW7WB4MN5OH7Q/action/citation_signature","submit_replication":"https://pith.science/pith/S76TDHU7DUEGGYW7WB4MN5OH7Q/action/replication_record"}},"created_at":"2026-07-05T10:02:20.300412+00:00","updated_at":"2026-07-05T10:02:20.300412+00:00"}