{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GEWT7TZR5P3VHGARJFJ7ISNHTC","short_pith_number":"pith:GEWT7TZR","schema_version":"1.0","canonical_sha256":"312d3fcf31ebf75398114953f449a798a49a6545f68859774f6ddeaf5edb12b5","source":{"kind":"arxiv","id":"2107.12270","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Wu, Haochen Shi, Juncheng Li, Linchao Zhu, Siliang Tang, Xuanwen Huang, Yi Yang, Yueting Zhuang","submitted_at":"2021-07-26T15:23:19Z","abstract_excerpt":"Video-and-Language Inference is a recently proposed task for joint video-and-language understanding. This new task requires a model to draw inference on whether a natural language statement entails or contradicts a given video clip. In this paper, we study how to address three critical challenges for this task: judging the global correctness of the statement involved multiple semantic meanings, joint reasoning over video and subtitles, and modeling long-range relationships and complex social interactions. First, we propose an adaptive hierarchical graph network that achieves in-depth understan"},"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":"2107.12270","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-26T15:23:19Z","cross_cats_sorted":[],"title_canon_sha256":"7a16a9a28e44ce0d0ab30daa5aeff52972ffd51eb775e48f3dd064b9c97b0a4a","abstract_canon_sha256":"e0b6732c7b1ed5a8a35b566ba45b491de8b7d1f1efdc11c42a7eb91fe4c1d97d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:06.099497Z","signature_b64":"VAHMU+zmNlGBhb03lx/K1P1gz4xu0qo0+tOm9QF1zSe0nYDBWNs3/GPPm7x4Rf7e3uSBzc8D77z+bZMd/4vBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"312d3fcf31ebf75398114953f449a798a49a6545f68859774f6ddeaf5edb12b5","last_reissued_at":"2026-07-05T03:04:06.099143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:06.099143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Wu, Haochen Shi, Juncheng Li, Linchao Zhu, Siliang Tang, Xuanwen Huang, Yi Yang, Yueting Zhuang","submitted_at":"2021-07-26T15:23:19Z","abstract_excerpt":"Video-and-Language Inference is a recently proposed task for joint video-and-language understanding. This new task requires a model to draw inference on whether a natural language statement entails or contradicts a given video clip. In this paper, we study how to address three critical challenges for this task: judging the global correctness of the statement involved multiple semantic meanings, joint reasoning over video and subtitles, and modeling long-range relationships and complex social interactions. First, we propose an adaptive hierarchical graph network that achieves in-depth understan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.12270","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/2107.12270/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":"2107.12270","created_at":"2026-07-05T03:04:06.099204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.12270v2","created_at":"2026-07-05T03:04:06.099204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.12270","created_at":"2026-07-05T03:04:06.099204+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEWT7TZR5P3V","created_at":"2026-07-05T03:04:06.099204+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEWT7TZR5P3VHGAR","created_at":"2026-07-05T03:04:06.099204+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEWT7TZR","created_at":"2026-07-05T03:04:06.099204+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/GEWT7TZR5P3VHGARJFJ7ISNHTC","json":"https://pith.science/pith/GEWT7TZR5P3VHGARJFJ7ISNHTC.json","graph_json":"https://pith.science/api/pith-number/GEWT7TZR5P3VHGARJFJ7ISNHTC/graph.json","events_json":"https://pith.science/api/pith-number/GEWT7TZR5P3VHGARJFJ7ISNHTC/events.json","paper":"https://pith.science/paper/GEWT7TZR"},"agent_actions":{"view_html":"https://pith.science/pith/GEWT7TZR5P3VHGARJFJ7ISNHTC","download_json":"https://pith.science/pith/GEWT7TZR5P3VHGARJFJ7ISNHTC.json","view_paper":"https://pith.science/paper/GEWT7TZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.12270&json=true","fetch_graph":"https://pith.science/api/pith-number/GEWT7TZR5P3VHGARJFJ7ISNHTC/graph.json","fetch_events":"https://pith.science/api/pith-number/GEWT7TZR5P3VHGARJFJ7ISNHTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEWT7TZR5P3VHGARJFJ7ISNHTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEWT7TZR5P3VHGARJFJ7ISNHTC/action/storage_attestation","attest_author":"https://pith.science/pith/GEWT7TZR5P3VHGARJFJ7ISNHTC/action/author_attestation","sign_citation":"https://pith.science/pith/GEWT7TZR5P3VHGARJFJ7ISNHTC/action/citation_signature","submit_replication":"https://pith.science/pith/GEWT7TZR5P3VHGARJFJ7ISNHTC/action/replication_record"}},"created_at":"2026-07-05T03:04:06.099204+00:00","updated_at":"2026-07-05T03:04:06.099204+00:00"}