{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5PFV6EYXJDOIFIVPPQ3QRTXN7I","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":"6b4bb5e7993ebc915524457e80558249fdb08480ca66549ae66c75694592f008","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-01-17T09:18:00Z","title_canon_sha256":"cc9a5eed7a67a2b92e0f99eaf1caa476db384f6a317d34c12426f7ca172f7c7b"},"schema_version":"1.0","source":{"id":"2001.06206","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.06206","created_at":"2026-07-05T00:34:07Z"},{"alias_kind":"arxiv_version","alias_value":"2001.06206v1","created_at":"2026-07-05T00:34:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.06206","created_at":"2026-07-05T00:34:07Z"},{"alias_kind":"pith_short_12","alias_value":"5PFV6EYXJDOI","created_at":"2026-07-05T00:34:07Z"},{"alias_kind":"pith_short_16","alias_value":"5PFV6EYXJDOIFIVP","created_at":"2026-07-05T00:34:07Z"},{"alias_kind":"pith_short_8","alias_value":"5PFV6EYX","created_at":"2026-07-05T00:34:07Z"}],"graph_snapshots":[{"event_id":"sha256:55d16bc1803df5406ac79d00862158a18259417f9c0ea92648cd9058851678ee","target":"graph","created_at":"2026-07-05T00:34:07Z","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/2001.06206/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding dynamic scenes and dialogue contexts in order to converse with users has been challenging for multimodal dialogue systems. The 8-th Dialog System Technology Challenge (DSTC8) proposed an Audio Visual Scene-Aware Dialog (AVSD) task, which contains multiple modalities including audio, vision, and language, to evaluate how dialogue systems understand different modalities and response to users. In this paper, we proposed a multi-step joint-modality attention network (JMAN) based on recurrent neural network (RNN) to reason on videos. Our model performs a multi-step attention mechanism","authors_text":"Chao-Chun Hsu, Kuan-Yen Lin, Lun-Wei Ku, Yun-Wei Chu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-01-17T09:18:00Z","title":"Multi-step Joint-Modality Attention Network for Scene-Aware Dialogue System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.06206","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":"sha256:5b6b8ce55ccb2adf0bf6536667033bc83509d9190b52a2a8820f1da54a29058a","target":"record","created_at":"2026-07-05T00:34:07Z","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":"6b4bb5e7993ebc915524457e80558249fdb08480ca66549ae66c75694592f008","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-01-17T09:18:00Z","title_canon_sha256":"cc9a5eed7a67a2b92e0f99eaf1caa476db384f6a317d34c12426f7ca172f7c7b"},"schema_version":"1.0","source":{"id":"2001.06206","kind":"arxiv","version":1}},"canonical_sha256":"ebcb5f131748dc82a2af7c3708ceedfa099dd41179afa02439629939f2eec9cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebcb5f131748dc82a2af7c3708ceedfa099dd41179afa02439629939f2eec9cb","first_computed_at":"2026-07-05T00:34:07.979052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:34:07.979052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aGhhIgTNzMTAEfS3+6jAkk6fP1EflglMmjuUN8MZ6DRxYQ98MYHrBQlr8REKC0wy7cGmePBnks+FUQtU++KXCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:34:07.979424Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.06206","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b6b8ce55ccb2adf0bf6536667033bc83509d9190b52a2a8820f1da54a29058a","sha256:55d16bc1803df5406ac79d00862158a18259417f9c0ea92648cd9058851678ee"],"state_sha256":"03a2e5f5cd566240a1a2be557af5cfae30a04b653700d985c30a4ff6ba7ada9c"}