{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:S5HCUU2JIMU6EZYAVT6EZ63NL2","short_pith_number":"pith:S5HCUU2J","schema_version":"1.0","canonical_sha256":"974e2a53494329e26700acfc4cfb6d5e88131eeedc7ab5328989efcb64b44f89","source":{"kind":"arxiv","id":"1812.07023","version":1},"attestation_state":"computed","paper":{"title":"From FiLM to Video: Multi-turn Question Answering with Multi-modal Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dat Tien Nguyen, Hannes Schulz, Layla El Asri, Shikhar Sharma","submitted_at":"2018-12-17T19:41:37Z","abstract_excerpt":"Understanding audio-visual content and the ability to have an informative conversation about it have both been challenging areas for intelligent systems. The Audio Visual Scene-aware Dialog (AVSD) challenge, organized as a track of the Dialog System Technology Challenge 7 (DSTC7), proposes a combined task, where a system has to answer questions pertaining to a video given a dialogue with previous question-answer pairs and the video itself. We propose for this task a hierarchical encoder-decoder model which computes a multi-modal embedding of the dialogue context. It first embeds the dialogue h"},"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":"1812.07023","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-17T19:41:37Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"cf121c1c32db802df0aad849728db450d7c58ebec414d689818ba95f2c4d8046","abstract_canon_sha256":"47a9ae647ce409386d6951abc292b7af12cec46542c540f4d0df118ff6cf5623"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:08.195383Z","signature_b64":"AiajGp4Pw9620cXMfw8JHQ33ATjjPcPoOePMa3hq+q1BQeEMMuoU9orTplxZL5ulQGc4JQvNA1D3zSZZj5HAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"974e2a53494329e26700acfc4cfb6d5e88131eeedc7ab5328989efcb64b44f89","last_reissued_at":"2026-05-17T23:58:08.194812Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:08.194812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From FiLM to Video: Multi-turn Question Answering with Multi-modal Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dat Tien Nguyen, Hannes Schulz, Layla El Asri, Shikhar Sharma","submitted_at":"2018-12-17T19:41:37Z","abstract_excerpt":"Understanding audio-visual content and the ability to have an informative conversation about it have both been challenging areas for intelligent systems. The Audio Visual Scene-aware Dialog (AVSD) challenge, organized as a track of the Dialog System Technology Challenge 7 (DSTC7), proposes a combined task, where a system has to answer questions pertaining to a video given a dialogue with previous question-answer pairs and the video itself. We propose for this task a hierarchical encoder-decoder model which computes a multi-modal embedding of the dialogue context. It first embeds the dialogue h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07023","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":""},"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":"1812.07023","created_at":"2026-05-17T23:58:08.194920+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.07023v1","created_at":"2026-05-17T23:58:08.194920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07023","created_at":"2026-05-17T23:58:08.194920+00:00"},{"alias_kind":"pith_short_12","alias_value":"S5HCUU2JIMU6","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"S5HCUU2JIMU6EZYA","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"S5HCUU2J","created_at":"2026-05-18T12:32:50.500415+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/S5HCUU2JIMU6EZYAVT6EZ63NL2","json":"https://pith.science/pith/S5HCUU2JIMU6EZYAVT6EZ63NL2.json","graph_json":"https://pith.science/api/pith-number/S5HCUU2JIMU6EZYAVT6EZ63NL2/graph.json","events_json":"https://pith.science/api/pith-number/S5HCUU2JIMU6EZYAVT6EZ63NL2/events.json","paper":"https://pith.science/paper/S5HCUU2J"},"agent_actions":{"view_html":"https://pith.science/pith/S5HCUU2JIMU6EZYAVT6EZ63NL2","download_json":"https://pith.science/pith/S5HCUU2JIMU6EZYAVT6EZ63NL2.json","view_paper":"https://pith.science/paper/S5HCUU2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.07023&json=true","fetch_graph":"https://pith.science/api/pith-number/S5HCUU2JIMU6EZYAVT6EZ63NL2/graph.json","fetch_events":"https://pith.science/api/pith-number/S5HCUU2JIMU6EZYAVT6EZ63NL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S5HCUU2JIMU6EZYAVT6EZ63NL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S5HCUU2JIMU6EZYAVT6EZ63NL2/action/storage_attestation","attest_author":"https://pith.science/pith/S5HCUU2JIMU6EZYAVT6EZ63NL2/action/author_attestation","sign_citation":"https://pith.science/pith/S5HCUU2JIMU6EZYAVT6EZ63NL2/action/citation_signature","submit_replication":"https://pith.science/pith/S5HCUU2JIMU6EZYAVT6EZ63NL2/action/replication_record"}},"created_at":"2026-05-17T23:58:08.194920+00:00","updated_at":"2026-05-17T23:58:08.194920+00:00"}