{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:37O6RMJZYBKEB56HFZZKDWPSRI","short_pith_number":"pith:37O6RMJZ","schema_version":"1.0","canonical_sha256":"dfdde8b139c05440f7c72e72a1d9f28a27a287b31e510c34b081008d8a36591a","source":{"kind":"arxiv","id":"2101.06644","version":1},"attestation_state":"computed","paper":{"title":"HySTER: A Hybrid Spatio-Temporal Event Reasoner","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LO"],"primary_cat":"cs.CV","authors_text":"Alessandra Russo, Nuri Cingillioglu, Theophile Sautory","submitted_at":"2021-01-17T11:07:17Z","abstract_excerpt":"The task of Video Question Answering (VideoQA) consists in answering natural language questions about a video and serves as a proxy to evaluate the performance of a model in scene sequence understanding. Most methods designed for VideoQA up-to-date are end-to-end deep learning architectures which struggle at complex temporal and causal reasoning and provide limited transparency in reasoning steps. We present the HySTER: a Hybrid Spatio-Temporal Event Reasoner to reason over physical events in videos. Our model leverages the strength of deep learning methods to extract information from video fr"},"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":"2101.06644","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-17T11:07:17Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LO"],"title_canon_sha256":"f2dce442795e36aeff7a3d644bb1c77c1ea57c626aefcebe20e43175f60604eb","abstract_canon_sha256":"253565dcbb11d18fe51ea7515faf5b20290a63fb1fe2d2b2416f35e07c0eb0a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:35.670363Z","signature_b64":"ZHu5gHwGkjlSDnwzyM2bxkCPMOZ7APn5abu5Lm/w8s1qNBkyHkIc+Xv52ifp2BkON6mb6v+ylQZKtWh0jfcGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfdde8b139c05440f7c72e72a1d9f28a27a287b31e510c34b081008d8a36591a","last_reissued_at":"2026-07-05T02:07:35.670003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:35.670003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HySTER: A Hybrid Spatio-Temporal Event Reasoner","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LO"],"primary_cat":"cs.CV","authors_text":"Alessandra Russo, Nuri Cingillioglu, Theophile Sautory","submitted_at":"2021-01-17T11:07:17Z","abstract_excerpt":"The task of Video Question Answering (VideoQA) consists in answering natural language questions about a video and serves as a proxy to evaluate the performance of a model in scene sequence understanding. Most methods designed for VideoQA up-to-date are end-to-end deep learning architectures which struggle at complex temporal and causal reasoning and provide limited transparency in reasoning steps. We present the HySTER: a Hybrid Spatio-Temporal Event Reasoner to reason over physical events in videos. Our model leverages the strength of deep learning methods to extract information from video fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.06644","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/2101.06644/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":"2101.06644","created_at":"2026-07-05T02:07:35.670057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.06644v1","created_at":"2026-07-05T02:07:35.670057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.06644","created_at":"2026-07-05T02:07:35.670057+00:00"},{"alias_kind":"pith_short_12","alias_value":"37O6RMJZYBKE","created_at":"2026-07-05T02:07:35.670057+00:00"},{"alias_kind":"pith_short_16","alias_value":"37O6RMJZYBKEB56H","created_at":"2026-07-05T02:07:35.670057+00:00"},{"alias_kind":"pith_short_8","alias_value":"37O6RMJZ","created_at":"2026-07-05T02:07:35.670057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09519","citing_title":"Weighted Rules under the Stable Model Semantics","ref_index":106,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37O6RMJZYBKEB56HFZZKDWPSRI","json":"https://pith.science/pith/37O6RMJZYBKEB56HFZZKDWPSRI.json","graph_json":"https://pith.science/api/pith-number/37O6RMJZYBKEB56HFZZKDWPSRI/graph.json","events_json":"https://pith.science/api/pith-number/37O6RMJZYBKEB56HFZZKDWPSRI/events.json","paper":"https://pith.science/paper/37O6RMJZ"},"agent_actions":{"view_html":"https://pith.science/pith/37O6RMJZYBKEB56HFZZKDWPSRI","download_json":"https://pith.science/pith/37O6RMJZYBKEB56HFZZKDWPSRI.json","view_paper":"https://pith.science/paper/37O6RMJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.06644&json=true","fetch_graph":"https://pith.science/api/pith-number/37O6RMJZYBKEB56HFZZKDWPSRI/graph.json","fetch_events":"https://pith.science/api/pith-number/37O6RMJZYBKEB56HFZZKDWPSRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37O6RMJZYBKEB56HFZZKDWPSRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37O6RMJZYBKEB56HFZZKDWPSRI/action/storage_attestation","attest_author":"https://pith.science/pith/37O6RMJZYBKEB56HFZZKDWPSRI/action/author_attestation","sign_citation":"https://pith.science/pith/37O6RMJZYBKEB56HFZZKDWPSRI/action/citation_signature","submit_replication":"https://pith.science/pith/37O6RMJZYBKEB56HFZZKDWPSRI/action/replication_record"}},"created_at":"2026-07-05T02:07:35.670057+00:00","updated_at":"2026-07-05T02:07:35.670057+00:00"}