{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:N57XMHM5PWINTJ5AF3ALD7XLDA","short_pith_number":"pith:N57XMHM5","schema_version":"1.0","canonical_sha256":"6f7f761d9d7d90d9a7a02ec0b1feeb1830deb80f63ae0e9a26af35a8df63643b","source":{"kind":"arxiv","id":"2210.14512","version":1},"attestation_state":"computed","paper":{"title":"End-to-End Multimodal Representation Learning for Video Dialog","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anthony Bilic, Apoorva Beedu, Huda Alamri, Irfan Essa, Michael Hu","submitted_at":"2022-10-26T06:50:07Z","abstract_excerpt":"Video-based dialog task is a challenging multimodal learning task that has received increasing attention over the past few years with state-of-the-art obtaining new performance records. This progress is largely powered by the adaptation of the more powerful transformer-based language encoders. Despite this progress, existing approaches do not effectively utilize visual features to help solve tasks. Recent studies show that state-of-the-art models are biased toward textual information rather than visual cues. In order to better leverage the available visual information, this study proposes a ne"},"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":"2210.14512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-26T06:50:07Z","cross_cats_sorted":[],"title_canon_sha256":"2be651c7a63b25fe4577138a2f2bdc90184b8c3cab9836687239602d34243fe1","abstract_canon_sha256":"07155647b3790f2458205d30afaf1a877f5695393b99e2030099a12783ea40ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:46.100036Z","signature_b64":"wWpzfpAEA7Vpb52iH6mOaS92FJkj1mEewmBSbGoFmfaAWAT33eSrrP6KhTTOUxTOVBR02p/0Rcv2n7egZ1HoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f7f761d9d7d90d9a7a02ec0b1feeb1830deb80f63ae0e9a26af35a8df63643b","last_reissued_at":"2026-07-05T05:10:46.099621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:46.099621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Multimodal Representation Learning for Video Dialog","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anthony Bilic, Apoorva Beedu, Huda Alamri, Irfan Essa, Michael Hu","submitted_at":"2022-10-26T06:50:07Z","abstract_excerpt":"Video-based dialog task is a challenging multimodal learning task that has received increasing attention over the past few years with state-of-the-art obtaining new performance records. This progress is largely powered by the adaptation of the more powerful transformer-based language encoders. Despite this progress, existing approaches do not effectively utilize visual features to help solve tasks. Recent studies show that state-of-the-art models are biased toward textual information rather than visual cues. In order to better leverage the available visual information, this study proposes a ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14512","kind":"arxiv","version":1},"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/2210.14512/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":"2210.14512","created_at":"2026-07-05T05:10:46.099677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.14512v1","created_at":"2026-07-05T05:10:46.099677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14512","created_at":"2026-07-05T05:10:46.099677+00:00"},{"alias_kind":"pith_short_12","alias_value":"N57XMHM5PWIN","created_at":"2026-07-05T05:10:46.099677+00:00"},{"alias_kind":"pith_short_16","alias_value":"N57XMHM5PWINTJ5A","created_at":"2026-07-05T05:10:46.099677+00:00"},{"alias_kind":"pith_short_8","alias_value":"N57XMHM5","created_at":"2026-07-05T05:10:46.099677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.18689","citing_title":"HierSum: A Global and Local Attention Mechanism for Video Summarization","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N57XMHM5PWINTJ5AF3ALD7XLDA","json":"https://pith.science/pith/N57XMHM5PWINTJ5AF3ALD7XLDA.json","graph_json":"https://pith.science/api/pith-number/N57XMHM5PWINTJ5AF3ALD7XLDA/graph.json","events_json":"https://pith.science/api/pith-number/N57XMHM5PWINTJ5AF3ALD7XLDA/events.json","paper":"https://pith.science/paper/N57XMHM5"},"agent_actions":{"view_html":"https://pith.science/pith/N57XMHM5PWINTJ5AF3ALD7XLDA","download_json":"https://pith.science/pith/N57XMHM5PWINTJ5AF3ALD7XLDA.json","view_paper":"https://pith.science/paper/N57XMHM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.14512&json=true","fetch_graph":"https://pith.science/api/pith-number/N57XMHM5PWINTJ5AF3ALD7XLDA/graph.json","fetch_events":"https://pith.science/api/pith-number/N57XMHM5PWINTJ5AF3ALD7XLDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N57XMHM5PWINTJ5AF3ALD7XLDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N57XMHM5PWINTJ5AF3ALD7XLDA/action/storage_attestation","attest_author":"https://pith.science/pith/N57XMHM5PWINTJ5AF3ALD7XLDA/action/author_attestation","sign_citation":"https://pith.science/pith/N57XMHM5PWINTJ5AF3ALD7XLDA/action/citation_signature","submit_replication":"https://pith.science/pith/N57XMHM5PWINTJ5AF3ALD7XLDA/action/replication_record"}},"created_at":"2026-07-05T05:10:46.099677+00:00","updated_at":"2026-07-05T05:10:46.099677+00:00"}