{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:EEDKAA3TKFJYJPEA3WJPEDQUII","short_pith_number":"pith:EEDKAA3T","schema_version":"1.0","canonical_sha256":"2106a00373515384bc80dd92f20e144217539447fae36642570c5f7e29406038","source":{"kind":"arxiv","id":"1701.08251","version":2},"attestation_state":"computed","paper":{"title":"Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Bill Dolan, Chris Brockett, Georgios P. Spithourakis, Jianfeng Gao, Lucy Vanderwende, Michel Galley, Nasrin Mostafazadeh","submitted_at":"2017-01-28T05:06:11Z","abstract_excerpt":"The popularity of image sharing on social media and the engagement it creates between users reflects the important role that visual context plays in everyday conversations. We present a novel task, Image-Grounded Conversations (IGC), in which natural-sounding conversations are generated about a shared image. To benchmark progress, we introduce a new multiple-reference dataset of crowd-sourced, event-centric conversations on images. IGC falls on the continuum between chit-chat and goal-directed conversation models, where visual grounding constrains the topic of conversation to event-driven utte"},"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":"1701.08251","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-28T05:06:11Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"5715d81771cedb94790a1f64041e68f81bedc9e2a3d6a16abfc9222c00474991","abstract_canon_sha256":"055133fa2290f70eeb71d3410e16d5161b540c2e07f5c59ec0cf0d52a3169c98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:04.075099Z","signature_b64":"IbMtk27KRHCLSrxc1K9557mCPEroc8VsvJzm+eX9A88UBLyKxMn+Manj+2Jo3aiGmwev0LFkvoCMU8/tQQy7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2106a00373515384bc80dd92f20e144217539447fae36642570c5f7e29406038","last_reissued_at":"2026-05-18T00:46:04.074578Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:04.074578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Bill Dolan, Chris Brockett, Georgios P. Spithourakis, Jianfeng Gao, Lucy Vanderwende, Michel Galley, Nasrin Mostafazadeh","submitted_at":"2017-01-28T05:06:11Z","abstract_excerpt":"The popularity of image sharing on social media and the engagement it creates between users reflects the important role that visual context plays in everyday conversations. We present a novel task, Image-Grounded Conversations (IGC), in which natural-sounding conversations are generated about a shared image. To benchmark progress, we introduce a new multiple-reference dataset of crowd-sourced, event-centric conversations on images. IGC falls on the continuum between chit-chat and goal-directed conversation models, where visual grounding constrains the topic of conversation to event-driven utte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.08251","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":"1701.08251","created_at":"2026-05-18T00:46:04.074668+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.08251v2","created_at":"2026-05-18T00:46:04.074668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.08251","created_at":"2026-05-18T00:46:04.074668+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEDKAA3TKFJY","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEDKAA3TKFJYJPEA","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEDKAA3T","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.08948","citing_title":"Hindi Visual Genome: A Dataset for Multimodal English-to-Hindi Machine Translation","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EEDKAA3TKFJYJPEA3WJPEDQUII","json":"https://pith.science/pith/EEDKAA3TKFJYJPEA3WJPEDQUII.json","graph_json":"https://pith.science/api/pith-number/EEDKAA3TKFJYJPEA3WJPEDQUII/graph.json","events_json":"https://pith.science/api/pith-number/EEDKAA3TKFJYJPEA3WJPEDQUII/events.json","paper":"https://pith.science/paper/EEDKAA3T"},"agent_actions":{"view_html":"https://pith.science/pith/EEDKAA3TKFJYJPEA3WJPEDQUII","download_json":"https://pith.science/pith/EEDKAA3TKFJYJPEA3WJPEDQUII.json","view_paper":"https://pith.science/paper/EEDKAA3T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.08251&json=true","fetch_graph":"https://pith.science/api/pith-number/EEDKAA3TKFJYJPEA3WJPEDQUII/graph.json","fetch_events":"https://pith.science/api/pith-number/EEDKAA3TKFJYJPEA3WJPEDQUII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEDKAA3TKFJYJPEA3WJPEDQUII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEDKAA3TKFJYJPEA3WJPEDQUII/action/storage_attestation","attest_author":"https://pith.science/pith/EEDKAA3TKFJYJPEA3WJPEDQUII/action/author_attestation","sign_citation":"https://pith.science/pith/EEDKAA3TKFJYJPEA3WJPEDQUII/action/citation_signature","submit_replication":"https://pith.science/pith/EEDKAA3TKFJYJPEA3WJPEDQUII/action/replication_record"}},"created_at":"2026-05-18T00:46:04.074668+00:00","updated_at":"2026-05-18T00:46:04.074668+00:00"}