{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DGDMK52GHDWPCP2N3HIPXR3K6H","short_pith_number":"pith:DGDMK52G","schema_version":"1.0","canonical_sha256":"1986c5774638ecf13f4dd9d0fbc76af1e5bd8dcd0dd44417d622c92893555f0c","source":{"kind":"arxiv","id":"1706.01554","version":2},"attestation_state":"computed","paper":{"title":"Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Anitha Kannan, Devi Parikh, Dhruv Batra, Jianwei Yang, Jiasen Lu","submitted_at":"2017-06-05T22:50:37Z","abstract_excerpt":"We present a novel training framework for neural sequence models, particularly for grounded dialog generation. The standard training paradigm for these models is maximum likelihood estimation (MLE), or minimizing the cross-entropy of the human responses. Across a variety of domains, a recurring problem with MLE trained generative neural dialog models (G) is that they tend to produce 'safe' and generic responses (\"I don't know\", \"I can't tell\"). In contrast, discriminative dialog models (D) that are trained to rank a list of candidate human responses outperform their generative counterparts; in"},"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":"1706.01554","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-05T22:50:37Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4ce813ab77b5a29ceb59a0d437ccdc6fd5813b684cd22cc5edc77b68fcb8e84b","abstract_canon_sha256":"d28d1fdd046c9ea51efb2c43dc91d41c24358b8680bddd4069012947918b012c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:50.968051Z","signature_b64":"9oNVBNKvR1GWlLBbF2phqZCY7S7I6jIvqARYm4dTqXqStNbQXZi/5+7piwKYw3sUoL8hrI79Y18725AJe2GCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1986c5774638ecf13f4dd9d0fbc76af1e5bd8dcd0dd44417d622c92893555f0c","last_reissued_at":"2026-05-18T00:31:50.967426Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:50.967426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Anitha Kannan, Devi Parikh, Dhruv Batra, Jianwei Yang, Jiasen Lu","submitted_at":"2017-06-05T22:50:37Z","abstract_excerpt":"We present a novel training framework for neural sequence models, particularly for grounded dialog generation. The standard training paradigm for these models is maximum likelihood estimation (MLE), or minimizing the cross-entropy of the human responses. Across a variety of domains, a recurring problem with MLE trained generative neural dialog models (G) is that they tend to produce 'safe' and generic responses (\"I don't know\", \"I can't tell\"). In contrast, discriminative dialog models (D) that are trained to rank a list of candidate human responses outperform their generative counterparts; in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01554","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1706.01554","created_at":"2026-05-18T00:31:50.967511+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.01554v2","created_at":"2026-05-18T00:31:50.967511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01554","created_at":"2026-05-18T00:31:50.967511+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGDMK52GHDWP","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGDMK52GHDWPCP2N","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGDMK52G","created_at":"2026-05-18T12:31:10.602751+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/DGDMK52GHDWPCP2N3HIPXR3K6H","json":"https://pith.science/pith/DGDMK52GHDWPCP2N3HIPXR3K6H.json","graph_json":"https://pith.science/api/pith-number/DGDMK52GHDWPCP2N3HIPXR3K6H/graph.json","events_json":"https://pith.science/api/pith-number/DGDMK52GHDWPCP2N3HIPXR3K6H/events.json","paper":"https://pith.science/paper/DGDMK52G"},"agent_actions":{"view_html":"https://pith.science/pith/DGDMK52GHDWPCP2N3HIPXR3K6H","download_json":"https://pith.science/pith/DGDMK52GHDWPCP2N3HIPXR3K6H.json","view_paper":"https://pith.science/paper/DGDMK52G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.01554&json=true","fetch_graph":"https://pith.science/api/pith-number/DGDMK52GHDWPCP2N3HIPXR3K6H/graph.json","fetch_events":"https://pith.science/api/pith-number/DGDMK52GHDWPCP2N3HIPXR3K6H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGDMK52GHDWPCP2N3HIPXR3K6H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGDMK52GHDWPCP2N3HIPXR3K6H/action/storage_attestation","attest_author":"https://pith.science/pith/DGDMK52GHDWPCP2N3HIPXR3K6H/action/author_attestation","sign_citation":"https://pith.science/pith/DGDMK52GHDWPCP2N3HIPXR3K6H/action/citation_signature","submit_replication":"https://pith.science/pith/DGDMK52GHDWPCP2N3HIPXR3K6H/action/replication_record"}},"created_at":"2026-05-18T00:31:50.967511+00:00","updated_at":"2026-05-18T00:31:50.967511+00:00"}