{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:C5JGKFOFGVLQZNQOXOSWNADXLF","short_pith_number":"pith:C5JGKFOF","canonical_record":{"source":{"id":"2207.12783","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-26T10:01:02Z","cross_cats_sorted":[],"title_canon_sha256":"59bdc307299ae8850be1675b2d271f9e893ccb016bb1e3bf03f4845fd68ce5a8","abstract_canon_sha256":"b9116156fd1165dcd8e3cfb2a036626d91fe8bb8a08e5ce193d68de806c765c6"},"schema_version":"1.0"},"canonical_sha256":"17526515c535570cb60ebba5668077597218fe4f0bb171e7e1e6af4082a2d801","source":{"kind":"arxiv","id":"2207.12783","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.12783","created_at":"2026-07-05T04:43:26Z"},{"alias_kind":"arxiv_version","alias_value":"2207.12783v1","created_at":"2026-07-05T04:43:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.12783","created_at":"2026-07-05T04:43:26Z"},{"alias_kind":"pith_short_12","alias_value":"C5JGKFOFGVLQ","created_at":"2026-07-05T04:43:26Z"},{"alias_kind":"pith_short_16","alias_value":"C5JGKFOFGVLQZNQO","created_at":"2026-07-05T04:43:26Z"},{"alias_kind":"pith_short_8","alias_value":"C5JGKFOF","created_at":"2026-07-05T04:43:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:C5JGKFOFGVLQZNQOXOSWNADXLF","target":"record","payload":{"canonical_record":{"source":{"id":"2207.12783","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-26T10:01:02Z","cross_cats_sorted":[],"title_canon_sha256":"59bdc307299ae8850be1675b2d271f9e893ccb016bb1e3bf03f4845fd68ce5a8","abstract_canon_sha256":"b9116156fd1165dcd8e3cfb2a036626d91fe8bb8a08e5ce193d68de806c765c6"},"schema_version":"1.0"},"canonical_sha256":"17526515c535570cb60ebba5668077597218fe4f0bb171e7e1e6af4082a2d801","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:43:26.286442Z","signature_b64":"QiJdB8R9/Wann6Zbm33mJRNL++RMobx5Nm2V31uPNC8P3Yj572W3pZJHlOThLzBt5SkyZMqcv/C6i0ulV2bkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17526515c535570cb60ebba5668077597218fe4f0bb171e7e1e6af4082a2d801","last_reissued_at":"2026-07-05T04:43:26.286051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:43:26.286051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.12783","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:43:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7BzUk+RVyfZ0X6yUnkATJTI81+5HSUnfLOVXpiG2hGiRnpuFnUxOLK+DGcrpKVwhkHLktLqHAb+RqUJ4dt5rDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:10:36.970973Z"},"content_sha256":"2a10f5f14f6fedfc33e9b2086a3af458f51e982a2f1dd7a1188a7d56427e08c4","schema_version":"1.0","event_id":"sha256:2a10f5f14f6fedfc33e9b2086a3af458f51e982a2f1dd7a1188a7d56427e08c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:C5JGKFOFGVLQZNQOXOSWNADXLF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Equivariant and Invariant Grounding for Video Question Answering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Junbin Xiao, Tat-Seng Chua, Xiang Wang, Yicong Li","submitted_at":"2022-07-26T10:01:02Z","abstract_excerpt":"Video Question Answering (VideoQA) is the task of answering the natural language questions about a video. Producing an answer requires understanding the interplay across visual scenes in video and linguistic semantics in question. However, most leading VideoQA models work as black boxes, which make the visual-linguistic alignment behind the answering process obscure. Such black-box nature calls for visual explainability that reveals ``What part of the video should the model look at to answer the question?''. Only a few works present the visual explanations in a post-hoc fashion, which emulates"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.12783","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/2207.12783/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:43:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o/UD3IooPTm1VFXQcBaN7vK5FFmsBb41h3Vhp5TU3UCneVoqkyYyoBCACxt9JD3bKsO5S59tpI8gv6zjkYJ0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:10:36.971345Z"},"content_sha256":"d55ad2d4d7f5e5cfc3efc67a3ca46cac92d51a82fc4056ed717aaae0d0a06db4","schema_version":"1.0","event_id":"sha256:d55ad2d4d7f5e5cfc3efc67a3ca46cac92d51a82fc4056ed717aaae0d0a06db4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C5JGKFOFGVLQZNQOXOSWNADXLF/bundle.json","state_url":"https://pith.science/pith/C5JGKFOFGVLQZNQOXOSWNADXLF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C5JGKFOFGVLQZNQOXOSWNADXLF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T11:10:36Z","links":{"resolver":"https://pith.science/pith/C5JGKFOFGVLQZNQOXOSWNADXLF","bundle":"https://pith.science/pith/C5JGKFOFGVLQZNQOXOSWNADXLF/bundle.json","state":"https://pith.science/pith/C5JGKFOFGVLQZNQOXOSWNADXLF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C5JGKFOFGVLQZNQOXOSWNADXLF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:C5JGKFOFGVLQZNQOXOSWNADXLF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b9116156fd1165dcd8e3cfb2a036626d91fe8bb8a08e5ce193d68de806c765c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-26T10:01:02Z","title_canon_sha256":"59bdc307299ae8850be1675b2d271f9e893ccb016bb1e3bf03f4845fd68ce5a8"},"schema_version":"1.0","source":{"id":"2207.12783","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.12783","created_at":"2026-07-05T04:43:26Z"},{"alias_kind":"arxiv_version","alias_value":"2207.12783v1","created_at":"2026-07-05T04:43:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.12783","created_at":"2026-07-05T04:43:26Z"},{"alias_kind":"pith_short_12","alias_value":"C5JGKFOFGVLQ","created_at":"2026-07-05T04:43:26Z"},{"alias_kind":"pith_short_16","alias_value":"C5JGKFOFGVLQZNQO","created_at":"2026-07-05T04:43:26Z"},{"alias_kind":"pith_short_8","alias_value":"C5JGKFOF","created_at":"2026-07-05T04:43:26Z"}],"graph_snapshots":[{"event_id":"sha256:d55ad2d4d7f5e5cfc3efc67a3ca46cac92d51a82fc4056ed717aaae0d0a06db4","target":"graph","created_at":"2026-07-05T04:43:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2207.12783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Question Answering (VideoQA) is the task of answering the natural language questions about a video. Producing an answer requires understanding the interplay across visual scenes in video and linguistic semantics in question. However, most leading VideoQA models work as black boxes, which make the visual-linguistic alignment behind the answering process obscure. Such black-box nature calls for visual explainability that reveals ``What part of the video should the model look at to answer the question?''. Only a few works present the visual explanations in a post-hoc fashion, which emulates","authors_text":"Junbin Xiao, Tat-Seng Chua, Xiang Wang, Yicong Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-26T10:01:02Z","title":"Equivariant and Invariant Grounding for Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.12783","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2a10f5f14f6fedfc33e9b2086a3af458f51e982a2f1dd7a1188a7d56427e08c4","target":"record","created_at":"2026-07-05T04:43:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b9116156fd1165dcd8e3cfb2a036626d91fe8bb8a08e5ce193d68de806c765c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-26T10:01:02Z","title_canon_sha256":"59bdc307299ae8850be1675b2d271f9e893ccb016bb1e3bf03f4845fd68ce5a8"},"schema_version":"1.0","source":{"id":"2207.12783","kind":"arxiv","version":1}},"canonical_sha256":"17526515c535570cb60ebba5668077597218fe4f0bb171e7e1e6af4082a2d801","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17526515c535570cb60ebba5668077597218fe4f0bb171e7e1e6af4082a2d801","first_computed_at":"2026-07-05T04:43:26.286051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:43:26.286051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QiJdB8R9/Wann6Zbm33mJRNL++RMobx5Nm2V31uPNC8P3Yj572W3pZJHlOThLzBt5SkyZMqcv/C6i0ulV2bkDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:43:26.286442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.12783","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a10f5f14f6fedfc33e9b2086a3af458f51e982a2f1dd7a1188a7d56427e08c4","sha256:d55ad2d4d7f5e5cfc3efc67a3ca46cac92d51a82fc4056ed717aaae0d0a06db4"],"state_sha256":"8f205b376a2157025a9a810ebfa7594c696fff88cfc044d6e849e8ee14a9a179"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3VsCMchQ90ZcnOpOaxqSuOFs+Ovh0vKvfrwQ1cOhLYbA7cd+pslf9koaVhk+l8hNH6cB/X8O3eI717TJPct0BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:10:36.973653Z","bundle_sha256":"0385d3935f437a8632025f272a6b61296393a623ac1b94ac75bb84ed1310ec08"}}