{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6Q3OHDX2RLLC5OABMU4EJVO7VF","short_pith_number":"pith:6Q3OHDX2","schema_version":"1.0","canonical_sha256":"f436e38efa8ad62eb801653844d5dfa94f35d9d979583052ab12e1d16e03be47","source":{"kind":"arxiv","id":"1811.00945","version":2},"attestation_state":"computed","paper":{"title":"Image Chat: Engaging Grounded Conversations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antoine Bordes, Jason Weston, Kurt Shuster, Samuel Humeau","submitted_at":"2018-11-02T15:54:15Z","abstract_excerpt":"To achieve the long-term goal of machines being able to engage humans in conversation, our models should captivate the interest of their speaking partners. Communication grounded in images, whereby a dialogue is conducted based on a given photo, is a setup naturally appealing to humans (Hu et al., 2014). In this work we study large-scale architectures and datasets for this goal. We test a set of neural architectures using state-of-the-art image and text representations, considering various ways to fuse the components. To test such models, we collect a dataset of grounded human-human conversati"},"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":"1811.00945","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T15:54:15Z","cross_cats_sorted":[],"title_canon_sha256":"505816a98a6bbc0e6df87e287ebede0669baa68dba72a30825c4f720dae36adc","abstract_canon_sha256":"b2e5a8595179858ebc7141765a7bb919cd455c4f9862c23f01cf280daa09d2a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:20.953148Z","signature_b64":"DhxML6g0GyJHdkGeb0hFHIiZJKzS0lDNEy2GPRtZkNZuCgrwaHN0PvZdphPKjszWkc42ik+hEtg9PcX+OWj0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f436e38efa8ad62eb801653844d5dfa94f35d9d979583052ab12e1d16e03be47","last_reissued_at":"2026-07-05T00:59:20.952095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:20.952095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Chat: Engaging Grounded Conversations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antoine Bordes, Jason Weston, Kurt Shuster, Samuel Humeau","submitted_at":"2018-11-02T15:54:15Z","abstract_excerpt":"To achieve the long-term goal of machines being able to engage humans in conversation, our models should captivate the interest of their speaking partners. Communication grounded in images, whereby a dialogue is conducted based on a given photo, is a setup naturally appealing to humans (Hu et al., 2014). In this work we study large-scale architectures and datasets for this goal. We test a set of neural architectures using state-of-the-art image and text representations, considering various ways to fuse the components. To test such models, we collect a dataset of grounded human-human conversati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00945","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1811.00945/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":"1811.00945","created_at":"2026-07-05T00:59:20.952215+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.00945v2","created_at":"2026-07-05T00:59:20.952215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00945","created_at":"2026-07-05T00:59:20.952215+00:00"},{"alias_kind":"pith_short_12","alias_value":"6Q3OHDX2RLLC","created_at":"2026-07-05T00:59:20.952215+00:00"},{"alias_kind":"pith_short_16","alias_value":"6Q3OHDX2RLLC5OAB","created_at":"2026-07-05T00:59:20.952215+00:00"},{"alias_kind":"pith_short_8","alias_value":"6Q3OHDX2","created_at":"2026-07-05T00:59:20.952215+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.09273","citing_title":"Why Build an Assistant in Minecraft?","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6Q3OHDX2RLLC5OABMU4EJVO7VF","json":"https://pith.science/pith/6Q3OHDX2RLLC5OABMU4EJVO7VF.json","graph_json":"https://pith.science/api/pith-number/6Q3OHDX2RLLC5OABMU4EJVO7VF/graph.json","events_json":"https://pith.science/api/pith-number/6Q3OHDX2RLLC5OABMU4EJVO7VF/events.json","paper":"https://pith.science/paper/6Q3OHDX2"},"agent_actions":{"view_html":"https://pith.science/pith/6Q3OHDX2RLLC5OABMU4EJVO7VF","download_json":"https://pith.science/pith/6Q3OHDX2RLLC5OABMU4EJVO7VF.json","view_paper":"https://pith.science/paper/6Q3OHDX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.00945&json=true","fetch_graph":"https://pith.science/api/pith-number/6Q3OHDX2RLLC5OABMU4EJVO7VF/graph.json","fetch_events":"https://pith.science/api/pith-number/6Q3OHDX2RLLC5OABMU4EJVO7VF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6Q3OHDX2RLLC5OABMU4EJVO7VF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6Q3OHDX2RLLC5OABMU4EJVO7VF/action/storage_attestation","attest_author":"https://pith.science/pith/6Q3OHDX2RLLC5OABMU4EJVO7VF/action/author_attestation","sign_citation":"https://pith.science/pith/6Q3OHDX2RLLC5OABMU4EJVO7VF/action/citation_signature","submit_replication":"https://pith.science/pith/6Q3OHDX2RLLC5OABMU4EJVO7VF/action/replication_record"}},"created_at":"2026-07-05T00:59:20.952215+00:00","updated_at":"2026-07-05T00:59:20.952215+00:00"}