{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LK6USTKSO2E3PEBWGXR6WRPC5V","short_pith_number":"pith:LK6USTKS","schema_version":"1.0","canonical_sha256":"5abd494d527689b7903635e3eb45e2ed47bedb20144394594eac07d896ca6cbf","source":{"kind":"arxiv","id":"2007.03848","version":2},"attestation_state":"computed","paper":{"title":"Dynamic Graph Representation Learning for Video Dialog via Multi-Modal Shuffled Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anoop Cherian, Chiori Hori, Hongsheng Li, Jonathan Le Roux, Moitreya Chatterjee, Peng Gao, Shijie Geng, Yongfeng Zhang","submitted_at":"2020-07-08T02:00:22Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2007.03848","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-08T02:00:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e0702caf4f716c70116c97aa116c5325dc78c7ad12f3c44ca4b30c0733601c35","abstract_canon_sha256":"44fcb14201306cb70943c0786799a905daf9f409264a0e3bb8a0d488acaa17a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:19:55.129006Z","signature_b64":"3F3Qa/AV3FL+AKrmuw8DuXOLSGTjCEdAMnpguFSpEhSrQ4ooxQnqponMWExaygTQ00SD2ycfhAhr79rkhqX2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5abd494d527689b7903635e3eb45e2ed47bedb20144394594eac07d896ca6cbf","last_reissued_at":"2026-07-05T02:19:55.128528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:19:55.128528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Graph Representation Learning for Video Dialog via Multi-Modal Shuffled Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anoop Cherian, Chiori Hori, Hongsheng Li, Jonathan Le Roux, Moitreya Chatterjee, Peng Gao, Shijie Geng, Yongfeng Zhang","submitted_at":"2020-07-08T02:00:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03848","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.03848/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2007.03848","created_at":"2026-07-05T02:19:55.128592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.03848v2","created_at":"2026-07-05T02:19:55.128592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03848","created_at":"2026-07-05T02:19:55.128592+00:00"},{"alias_kind":"pith_short_12","alias_value":"LK6USTKSO2E3","created_at":"2026-07-05T02:19:55.128592+00:00"},{"alias_kind":"pith_short_16","alias_value":"LK6USTKSO2E3PEBW","created_at":"2026-07-05T02:19:55.128592+00:00"},{"alias_kind":"pith_short_8","alias_value":"LK6USTKS","created_at":"2026-07-05T02:19:55.128592+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LK6USTKSO2E3PEBWGXR6WRPC5V","json":"https://pith.science/pith/LK6USTKSO2E3PEBWGXR6WRPC5V.json","graph_json":"https://pith.science/api/pith-number/LK6USTKSO2E3PEBWGXR6WRPC5V/graph.json","events_json":"https://pith.science/api/pith-number/LK6USTKSO2E3PEBWGXR6WRPC5V/events.json","paper":"https://pith.science/paper/LK6USTKS"},"agent_actions":{"view_html":"https://pith.science/pith/LK6USTKSO2E3PEBWGXR6WRPC5V","download_json":"https://pith.science/pith/LK6USTKSO2E3PEBWGXR6WRPC5V.json","view_paper":"https://pith.science/paper/LK6USTKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.03848&json=true","fetch_graph":"https://pith.science/api/pith-number/LK6USTKSO2E3PEBWGXR6WRPC5V/graph.json","fetch_events":"https://pith.science/api/pith-number/LK6USTKSO2E3PEBWGXR6WRPC5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LK6USTKSO2E3PEBWGXR6WRPC5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LK6USTKSO2E3PEBWGXR6WRPC5V/action/storage_attestation","attest_author":"https://pith.science/pith/LK6USTKSO2E3PEBWGXR6WRPC5V/action/author_attestation","sign_citation":"https://pith.science/pith/LK6USTKSO2E3PEBWGXR6WRPC5V/action/citation_signature","submit_replication":"https://pith.science/pith/LK6USTKSO2E3PEBWGXR6WRPC5V/action/replication_record"}},"created_at":"2026-07-05T02:19:55.128592+00:00","updated_at":"2026-07-05T02:19:55.128592+00:00"}