{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7PHMGRT5E26MJOFXK62UKMIRKD","short_pith_number":"pith:7PHMGRT5","canonical_record":{"source":{"id":"1806.08409","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-21T19:43:13Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"e315889c015e132a6b188664f85c11a4fd74d5c133cb91a37427426df431ac1b","abstract_canon_sha256":"5218f4041219ed378777184533bc4ed126727f107a52a382880ba32507d65a7b"},"schema_version":"1.0"},"canonical_sha256":"fbcec3467d26bcc4b8b757b545311150d0928faa790781c58096fc7fcc616a66","source":{"kind":"arxiv","id":"1806.08409","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.08409","created_at":"2026-05-18T00:11:56Z"},{"alias_kind":"arxiv_version","alias_value":"1806.08409v2","created_at":"2026-05-18T00:11:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08409","created_at":"2026-05-18T00:11:56Z"},{"alias_kind":"pith_short_12","alias_value":"7PHMGRT5E26M","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7PHMGRT5E26MJOFX","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7PHMGRT5","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7PHMGRT5E26MJOFXK62UKMIRKD","target":"record","payload":{"canonical_record":{"source":{"id":"1806.08409","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-21T19:43:13Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"e315889c015e132a6b188664f85c11a4fd74d5c133cb91a37427426df431ac1b","abstract_canon_sha256":"5218f4041219ed378777184533bc4ed126727f107a52a382880ba32507d65a7b"},"schema_version":"1.0"},"canonical_sha256":"fbcec3467d26bcc4b8b757b545311150d0928faa790781c58096fc7fcc616a66","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:56.575643Z","signature_b64":"/Xhfl/P99dgoWQkW8gKaQWwjItQZ/Vlb1McAqA/G8pLapXKrfjmASnoAM8Ly10kw65ojFdK1dyEYmTlu7eiUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbcec3467d26bcc4b8b757b545311150d0928faa790781c58096fc7fcc616a66","last_reissued_at":"2026-05-18T00:11:56.575006Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:56.575006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.08409","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K/EsIC88mNCa1h/5dFSXN8e87mj1lbYwfnrfeC2+/YJLzT8RiZxPjh19UJWHl7xGdAjRetbV312rgKDW7hE2BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:34:37.695351Z"},"content_sha256":"962e83ac63702764797146841e771c31522ad5f6a72fabff5dd2813aa384ed16","schema_version":"1.0","event_id":"sha256:962e83ac63702764797146841e771c31522ad5f6a72fabff5dd2813aa384ed16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7PHMGRT5E26MJOFXK62UKMIRKD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abhishek Das, Anoop Cherian, Chiori Hori, Devi Parikh, Dhruv Batra, Gordon Wichern, Huda Alamri, Irfan Essa, Jue Wang, Raphael Gontijo Lopes, Takaaki Hori, Tim K. Marks, Vincent Cartillier","submitted_at":"2018-06-21T19:43:13Z","abstract_excerpt":"Dialog systems need to understand dynamic visual scenes in order to have conversations with users about the objects and events around them. Scene-aware dialog systems for real-world applications could be developed by integrating state-of-the-art technologies from multiple research areas, including: end-to-end dialog technologies, which generate system responses using models trained from dialog data; visual question answering (VQA) technologies, which answer questions about images using learned image features; and video description technologies, in which descriptions/captions are generated from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08409","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F1k9bdkDyvxIS9/MqbM/hWlqVbxFDHGa/zHXi+x4bv9w91VY+p0AsRpSSzFZIQlcrUZYXw6jQUER9yNtabZeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:34:37.696034Z"},"content_sha256":"23bc75a60b7117cee7e99fdcd4044018104966f201a0a471c066b27399b2ed5f","schema_version":"1.0","event_id":"sha256:23bc75a60b7117cee7e99fdcd4044018104966f201a0a471c066b27399b2ed5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7PHMGRT5E26MJOFXK62UKMIRKD/bundle.json","state_url":"https://pith.science/pith/7PHMGRT5E26MJOFXK62UKMIRKD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7PHMGRT5E26MJOFXK62UKMIRKD/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":"2026-05-29T15:34:37Z","links":{"resolver":"https://pith.science/pith/7PHMGRT5E26MJOFXK62UKMIRKD","bundle":"https://pith.science/pith/7PHMGRT5E26MJOFXK62UKMIRKD/bundle.json","state":"https://pith.science/pith/7PHMGRT5E26MJOFXK62UKMIRKD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7PHMGRT5E26MJOFXK62UKMIRKD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7PHMGRT5E26MJOFXK62UKMIRKD","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":"5218f4041219ed378777184533bc4ed126727f107a52a382880ba32507d65a7b","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-21T19:43:13Z","title_canon_sha256":"e315889c015e132a6b188664f85c11a4fd74d5c133cb91a37427426df431ac1b"},"schema_version":"1.0","source":{"id":"1806.08409","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.08409","created_at":"2026-05-18T00:11:56Z"},{"alias_kind":"arxiv_version","alias_value":"1806.08409v2","created_at":"2026-05-18T00:11:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08409","created_at":"2026-05-18T00:11:56Z"},{"alias_kind":"pith_short_12","alias_value":"7PHMGRT5E26M","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7PHMGRT5E26MJOFX","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7PHMGRT5","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:23bc75a60b7117cee7e99fdcd4044018104966f201a0a471c066b27399b2ed5f","target":"graph","created_at":"2026-05-18T00:11:56Z","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":"Dialog systems need to understand dynamic visual scenes in order to have conversations with users about the objects and events around them. Scene-aware dialog systems for real-world applications could be developed by integrating state-of-the-art technologies from multiple research areas, including: end-to-end dialog technologies, which generate system responses using models trained from dialog data; visual question answering (VQA) technologies, which answer questions about images using learned image features; and video description technologies, in which descriptions/captions are generated from","authors_text":"Abhishek Das, Anoop Cherian, Chiori Hori, Devi Parikh, Dhruv Batra, Gordon Wichern, Huda Alamri, Irfan Essa, Jue Wang, Raphael Gontijo Lopes, Takaaki Hori, Tim K. Marks, Vincent Cartillier","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-21T19:43:13Z","title":"End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08409","kind":"arxiv","version":2},"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":"sha256:962e83ac63702764797146841e771c31522ad5f6a72fabff5dd2813aa384ed16","target":"record","created_at":"2026-05-18T00:11:56Z","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":"5218f4041219ed378777184533bc4ed126727f107a52a382880ba32507d65a7b","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-21T19:43:13Z","title_canon_sha256":"e315889c015e132a6b188664f85c11a4fd74d5c133cb91a37427426df431ac1b"},"schema_version":"1.0","source":{"id":"1806.08409","kind":"arxiv","version":2}},"canonical_sha256":"fbcec3467d26bcc4b8b757b545311150d0928faa790781c58096fc7fcc616a66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbcec3467d26bcc4b8b757b545311150d0928faa790781c58096fc7fcc616a66","first_computed_at":"2026-05-18T00:11:56.575006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:56.575006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Xhfl/P99dgoWQkW8gKaQWwjItQZ/Vlb1McAqA/G8pLapXKrfjmASnoAM8Ly10kw65ojFdK1dyEYmTlu7eiUAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:56.575643Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.08409","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:962e83ac63702764797146841e771c31522ad5f6a72fabff5dd2813aa384ed16","sha256:23bc75a60b7117cee7e99fdcd4044018104966f201a0a471c066b27399b2ed5f"],"state_sha256":"985e661dd51b42928f852552dfc94151fbb7cd2af1dd4d5b518ff6e39143af17"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"06jUXLjPtjh/sFxWLTE+t35GkLcpQl4MkeNu+gfBpaijlzUCVHzndkzhcuKQ1sQgfRH4XS6qWo9sUO2XRBA/AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T15:34:37.699805Z","bundle_sha256":"e3c523d7ac761b910caf5868bfb002e8be50ed97f70503224f41425934d37bbb"}}