{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RONZAWYJ2NUBK466E2MA3F4SPL","short_pith_number":"pith:RONZAWYJ","schema_version":"1.0","canonical_sha256":"8b9b905b09d3681573de26980d97927ae88f44627d629691e97f1355df15c0dc","source":{"kind":"arxiv","id":"2106.13432","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Long Hoang Dang, Thao Minh Le, Truyen Tran, Vuong Le","submitted_at":"2021-06-25T05:12:42Z","abstract_excerpt":"Video Question Answering (Video QA) is a powerful testbed to develop new AI capabilities. This task necessitates learning to reason about objects, relations, and events across visual and linguistic domains in space-time. High-level reasoning demands lifting from associative visual pattern recognition to symbol-like manipulation over objects, their behavior and interactions. Toward reaching this goal we propose an object-oriented reasoning approach in that video is abstracted as a dynamic stream of interacting objects. At each stage of the video event flow, these objects interact with each othe"},"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":"2106.13432","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T05:12:42Z","cross_cats_sorted":[],"title_canon_sha256":"1f6df6d8cc285c8418c72cf2824429998e90a8ed3da23e14e9be0f45b535e80c","abstract_canon_sha256":"adfa02ca6fd3b7167afc9e7b34e2151713df5ea8ac2eab84779948b7e19470e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:08:46.409411Z","signature_b64":"GsAEXigJ3tEswv2EFIIZaQ8HP5VDM0HnZu+2m49O3j5QCCdHiuteNETS/43Q2gpZVgoVqXx/QNN+xft3f593BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b9b905b09d3681573de26980d97927ae88f44627d629691e97f1355df15c0dc","last_reissued_at":"2026-07-05T03:08:46.408897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:08:46.408897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Long Hoang Dang, Thao Minh Le, Truyen Tran, Vuong Le","submitted_at":"2021-06-25T05:12:42Z","abstract_excerpt":"Video Question Answering (Video QA) is a powerful testbed to develop new AI capabilities. This task necessitates learning to reason about objects, relations, and events across visual and linguistic domains in space-time. High-level reasoning demands lifting from associative visual pattern recognition to symbol-like manipulation over objects, their behavior and interactions. Toward reaching this goal we propose an object-oriented reasoning approach in that video is abstracted as a dynamic stream of interacting objects. At each stage of the video event flow, these objects interact with each othe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13432","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/2106.13432/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":"2106.13432","created_at":"2026-07-05T03:08:46.408955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13432v2","created_at":"2026-07-05T03:08:46.408955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13432","created_at":"2026-07-05T03:08:46.408955+00:00"},{"alias_kind":"pith_short_12","alias_value":"RONZAWYJ2NUB","created_at":"2026-07-05T03:08:46.408955+00:00"},{"alias_kind":"pith_short_16","alias_value":"RONZAWYJ2NUBK466","created_at":"2026-07-05T03:08:46.408955+00:00"},{"alias_kind":"pith_short_8","alias_value":"RONZAWYJ","created_at":"2026-07-05T03:08:46.408955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09200","citing_title":"THYME: Temporal Hierarchical-Cyclic Interactivity Modeling for Video Scene Graphs in Aerial Footage","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RONZAWYJ2NUBK466E2MA3F4SPL","json":"https://pith.science/pith/RONZAWYJ2NUBK466E2MA3F4SPL.json","graph_json":"https://pith.science/api/pith-number/RONZAWYJ2NUBK466E2MA3F4SPL/graph.json","events_json":"https://pith.science/api/pith-number/RONZAWYJ2NUBK466E2MA3F4SPL/events.json","paper":"https://pith.science/paper/RONZAWYJ"},"agent_actions":{"view_html":"https://pith.science/pith/RONZAWYJ2NUBK466E2MA3F4SPL","download_json":"https://pith.science/pith/RONZAWYJ2NUBK466E2MA3F4SPL.json","view_paper":"https://pith.science/paper/RONZAWYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13432&json=true","fetch_graph":"https://pith.science/api/pith-number/RONZAWYJ2NUBK466E2MA3F4SPL/graph.json","fetch_events":"https://pith.science/api/pith-number/RONZAWYJ2NUBK466E2MA3F4SPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RONZAWYJ2NUBK466E2MA3F4SPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RONZAWYJ2NUBK466E2MA3F4SPL/action/storage_attestation","attest_author":"https://pith.science/pith/RONZAWYJ2NUBK466E2MA3F4SPL/action/author_attestation","sign_citation":"https://pith.science/pith/RONZAWYJ2NUBK466E2MA3F4SPL/action/citation_signature","submit_replication":"https://pith.science/pith/RONZAWYJ2NUBK466E2MA3F4SPL/action/replication_record"}},"created_at":"2026-07-05T03:08:46.408955+00:00","updated_at":"2026-07-05T03:08:46.408955+00:00"}