{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:H6YJSM3ZSVHIFWX54XBEYSWDAZ","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":"eaf672a03a73f39ccb7c42a41af19e98433256d9e7374b75472e692494efe77e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-13T17:24:16Z","title_canon_sha256":"587f5b14d2f5b5dc61a64c7bb15a67d0f7b71435306beb6ae50c1b5f6f7ee1f0"},"schema_version":"1.0","source":{"id":"2110.06894","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06894","created_at":"2026-07-05T03:22:30Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06894v1","created_at":"2026-07-05T03:22:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06894","created_at":"2026-07-05T03:22:30Z"},{"alias_kind":"pith_short_12","alias_value":"H6YJSM3ZSVHI","created_at":"2026-07-05T03:22:30Z"},{"alias_kind":"pith_short_16","alias_value":"H6YJSM3ZSVHIFWX5","created_at":"2026-07-05T03:22:30Z"},{"alias_kind":"pith_short_8","alias_value":"H6YJSM3Z","created_at":"2026-07-05T03:22:30Z"}],"graph_snapshots":[{"event_id":"sha256:7079489d7f7a0911ca21ac72740704c90b5099b481a4ddef46c2dc7d3c465273","target":"graph","created_at":"2026-07-05T03:22:30Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2110.06894/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In previous work, we have proposed the Audio-Visual Scene-Aware Dialog (AVSD) task, collected an AVSD dataset, developed AVSD technologies, and hosted an AVSD challenge track at both the 7th and 8th Dialog System Technology Challenges (DSTC7, DSTC8). In these challenges, the best-performing systems relied heavily on human-generated descriptions of the video content, which were available in the datasets but would be unavailable in real-world applications. To promote further advancements for real-world applications, we proposed a third AVSD challenge, at DSTC10, with two modifications: 1) the hu","authors_text":"Ankit P. Shah, Anoop Cherian, Chiori Hori, Jonathan Le Roux, Peng Gao, Shijie Geng, Takaaki Hori, Tim K. Marks","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-13T17:24:16Z","title":"Audio-Visual Scene-Aware Dialog and Reasoning using Audio-Visual Transformers with Joint Student-Teacher Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06894","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:b41ce0c0cd1a15261b15b37dac722ebe2fa1364b24e1946a812c7b0663c95162","target":"record","created_at":"2026-07-05T03:22:30Z","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":"eaf672a03a73f39ccb7c42a41af19e98433256d9e7374b75472e692494efe77e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-13T17:24:16Z","title_canon_sha256":"587f5b14d2f5b5dc61a64c7bb15a67d0f7b71435306beb6ae50c1b5f6f7ee1f0"},"schema_version":"1.0","source":{"id":"2110.06894","kind":"arxiv","version":1}},"canonical_sha256":"3fb0993379954e82dafde5c24c4ac306573e06ad7bed51a72df4e1290c60dcb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fb0993379954e82dafde5c24c4ac306573e06ad7bed51a72df4e1290c60dcb2","first_computed_at":"2026-07-05T03:22:30.390208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:30.390208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gIQ9Vl2gBIIP4ntc5VuRw/SIcmX973GcSAOnq17Qylbb0JwWSA2RBvTpZcqJ7dfkj8hnzAX3EDXmHOy6WKk8Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:30.390635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.06894","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b41ce0c0cd1a15261b15b37dac722ebe2fa1364b24e1946a812c7b0663c95162","sha256:7079489d7f7a0911ca21ac72740704c90b5099b481a4ddef46c2dc7d3c465273"],"state_sha256":"6e5c0fece14ca6e69d7cbdb3cb1395b4c153c5544dbaf2b882c2710953adb91c"}