{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:S5HCUU2JIMU6EZYAVT6EZ63NL2","short_pith_number":"pith:S5HCUU2J","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"},"canonical_sha256":"974e2a53494329e26700acfc4cfb6d5e88131eeedc7ab5328989efcb64b44f89","source":{"kind":"arxiv","id":"1812.07023","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.07023","created_at":"2026-05-17T23:58:08Z"},{"alias_kind":"arxiv_version","alias_value":"1812.07023v1","created_at":"2026-05-17T23:58:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07023","created_at":"2026-05-17T23:58:08Z"},{"alias_kind":"pith_short_12","alias_value":"S5HCUU2JIMU6","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"S5HCUU2JIMU6EZYA","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"S5HCUU2J","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:S5HCUU2JIMU6EZYAVT6EZ63NL2","target":"record","payload":{"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"},"canonical_sha256":"974e2a53494329e26700acfc4cfb6d5e88131eeedc7ab5328989efcb64b44f89","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"},"source_kind":"arxiv","source_id":"1812.07023","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Q2D1WTQlyydCJ+ga7xOLPyZRh+SmQMZLh8JppLAhbXTkuk3NCMteJzFXLspRc83ZZflU5nCpN5gj4sqpqB6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T11:39:30.612458Z"},"content_sha256":"862967427a770c3741f4c657f6c5e96ab5a0405807856a8ede7f15766998fd2d","schema_version":"1.0","event_id":"sha256:862967427a770c3741f4c657f6c5e96ab5a0405807856a8ede7f15766998fd2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:S5HCUU2JIMU6EZYAVT6EZ63NL2","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4qJ/fkDs2g/ID9aERQC718dbbhk6zNpZ/66zPA4VK697EUZqNrQMWAO/WxW9mdo743yzf/PUOvcyT3Ue/U2ABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T11:39:30.612808Z"},"content_sha256":"df0b2117f015d00fa97db82c9b9158f63f412efe6a4a5fd4f1b70098c5153622","schema_version":"1.0","event_id":"sha256:df0b2117f015d00fa97db82c9b9158f63f412efe6a4a5fd4f1b70098c5153622"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S5HCUU2JIMU6EZYAVT6EZ63NL2/bundle.json","state_url":"https://pith.science/pith/S5HCUU2JIMU6EZYAVT6EZ63NL2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S5HCUU2JIMU6EZYAVT6EZ63NL2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T11:39:30Z","links":{"resolver":"https://pith.science/pith/S5HCUU2JIMU6EZYAVT6EZ63NL2","bundle":"https://pith.science/pith/S5HCUU2JIMU6EZYAVT6EZ63NL2/bundle.json","state":"https://pith.science/pith/S5HCUU2JIMU6EZYAVT6EZ63NL2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S5HCUU2JIMU6EZYAVT6EZ63NL2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:S5HCUU2JIMU6EZYAVT6EZ63NL2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"47a9ae647ce409386d6951abc292b7af12cec46542c540f4d0df118ff6cf5623","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-17T19:41:37Z","title_canon_sha256":"cf121c1c32db802df0aad849728db450d7c58ebec414d689818ba95f2c4d8046"},"schema_version":"1.0","source":{"id":"1812.07023","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.07023","created_at":"2026-05-17T23:58:08Z"},{"alias_kind":"arxiv_version","alias_value":"1812.07023v1","created_at":"2026-05-17T23:58:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07023","created_at":"2026-05-17T23:58:08Z"},{"alias_kind":"pith_short_12","alias_value":"S5HCUU2JIMU6","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"S5HCUU2JIMU6EZYA","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"S5HCUU2J","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:df0b2117f015d00fa97db82c9b9158f63f412efe6a4a5fd4f1b70098c5153622","target":"graph","created_at":"2026-05-17T23:58:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Dat Tien Nguyen, Hannes Schulz, Layla El Asri, Shikhar Sharma","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-17T19:41:37Z","title":"From FiLM to Video: Multi-turn Question Answering with Multi-modal Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07023","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:862967427a770c3741f4c657f6c5e96ab5a0405807856a8ede7f15766998fd2d","target":"record","created_at":"2026-05-17T23:58:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"47a9ae647ce409386d6951abc292b7af12cec46542c540f4d0df118ff6cf5623","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-17T19:41:37Z","title_canon_sha256":"cf121c1c32db802df0aad849728db450d7c58ebec414d689818ba95f2c4d8046"},"schema_version":"1.0","source":{"id":"1812.07023","kind":"arxiv","version":1}},"canonical_sha256":"974e2a53494329e26700acfc4cfb6d5e88131eeedc7ab5328989efcb64b44f89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"974e2a53494329e26700acfc4cfb6d5e88131eeedc7ab5328989efcb64b44f89","first_computed_at":"2026-05-17T23:58:08.194812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:08.194812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AiajGp4Pw9620cXMfw8JHQ33ATjjPcPoOePMa3hq+q1BQeEMMuoU9orTplxZL5ulQGc4JQvNA1D3zSZZj5HAAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:08.195383Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.07023","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:862967427a770c3741f4c657f6c5e96ab5a0405807856a8ede7f15766998fd2d","sha256:df0b2117f015d00fa97db82c9b9158f63f412efe6a4a5fd4f1b70098c5153622"],"state_sha256":"533eff8c5c9aaac7b4caa8dc711b0f84191041e23eda3004f9acdbdb87fd2091"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y9w9naTD7LGt/GwTkVeyjnargD2DectrSFvGMmiitPhPdFVWsiAMBVvhI3075ZUwZNIGqybyynj+2F/z96bjAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T11:39:30.615801Z","bundle_sha256":"dac08c5c89da6e9a5fd8b2802837bb209cca9fac0c52f6922cb81de047e92f37"}}