{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LK6USTKSO2E3PEBWGXR6WRPC5V","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":"44fcb14201306cb70943c0786799a905daf9f409264a0e3bb8a0d488acaa17a5","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-08T02:00:22Z","title_canon_sha256":"e0702caf4f716c70116c97aa116c5325dc78c7ad12f3c44ca4b30c0733601c35"},"schema_version":"1.0","source":{"id":"2007.03848","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03848","created_at":"2026-07-05T02:19:55Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03848v2","created_at":"2026-07-05T02:19:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03848","created_at":"2026-07-05T02:19:55Z"},{"alias_kind":"pith_short_12","alias_value":"LK6USTKSO2E3","created_at":"2026-07-05T02:19:55Z"},{"alias_kind":"pith_short_16","alias_value":"LK6USTKSO2E3PEBW","created_at":"2026-07-05T02:19:55Z"},{"alias_kind":"pith_short_8","alias_value":"LK6USTKS","created_at":"2026-07-05T02:19:55Z"}],"graph_snapshots":[{"event_id":"sha256:6dbd83bb122ea2d85784f0e15646c0345262f4cc84cada5dea557b561f0cb01c","target":"graph","created_at":"2026-07-05T02:19:55Z","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/2007.03848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Given an input video, its associated audio, and a brief caption, the audio-visual scene aware dialog (AVSD) task requires an agent to indulge in a question-answer dialog with a human about the audio-visual content. This task thus poses a challenging multi-modal representation learning and reasoning scenario, advancements into which could influence several human-machine interaction applications. To solve this task, we introduce a semantics-controlled multi-modal shuffled Transformer reasoning framework, consisting of a sequence of Transformer modules, each taking a modality as input and produci","authors_text":"Anoop Cherian, Chiori Hori, Hongsheng Li, Jonathan Le Roux, Moitreya Chatterjee, Peng Gao, Shijie Geng, Yongfeng Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-08T02:00:22Z","title":"Dynamic Graph Representation Learning for Video Dialog via Multi-Modal Shuffled Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03848","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":"sha256:0a97359f1e0cb74a0b1740d981a51261dcd6af3d6f8ddb44b55dd6ea7f20e190","target":"record","created_at":"2026-07-05T02:19:55Z","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":"44fcb14201306cb70943c0786799a905daf9f409264a0e3bb8a0d488acaa17a5","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-08T02:00:22Z","title_canon_sha256":"e0702caf4f716c70116c97aa116c5325dc78c7ad12f3c44ca4b30c0733601c35"},"schema_version":"1.0","source":{"id":"2007.03848","kind":"arxiv","version":2}},"canonical_sha256":"5abd494d527689b7903635e3eb45e2ed47bedb20144394594eac07d896ca6cbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5abd494d527689b7903635e3eb45e2ed47bedb20144394594eac07d896ca6cbf","first_computed_at":"2026-07-05T02:19:55.128528Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:19:55.128528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3F3Qa/AV3FL+AKrmuw8DuXOLSGTjCEdAMnpguFSpEhSrQ4ooxQnqponMWExaygTQ00SD2ycfhAhr79rkhqX2Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:19:55.129006Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.03848","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a97359f1e0cb74a0b1740d981a51261dcd6af3d6f8ddb44b55dd6ea7f20e190","sha256:6dbd83bb122ea2d85784f0e15646c0345262f4cc84cada5dea557b561f0cb01c"],"state_sha256":"f7f02bcbd20b7364d6eab9c575b89c5fdff6bed963a7ed827a088a97154284a7"}