{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TNFTLB6PLVXXXL5JYEFMXLMP4J","short_pith_number":"pith:TNFTLB6P","canonical_record":{"source":{"id":"2206.08155","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-16T13:18:20Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"4e116894bc4bcb4071808db27d36c7cfae46cf25df01c0209469c8853de9fd80","abstract_canon_sha256":"351359a044e5e2a2ecb725b867d288bd983672fc4d695f33376cfd15c0d7a86b"},"schema_version":"1.0"},"canonical_sha256":"9b4b3587cf5d6f7bafa9c10acbad8fe2764fbe46a43a47ac7f4d687ba16beb9e","source":{"kind":"arxiv","id":"2206.08155","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.08155","created_at":"2026-07-05T05:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2206.08155v2","created_at":"2026-07-05T05:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08155","created_at":"2026-07-05T05:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"TNFTLB6PLVXX","created_at":"2026-07-05T05:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"TNFTLB6PLVXXXL5J","created_at":"2026-07-05T05:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"TNFTLB6P","created_at":"2026-07-05T05:04:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TNFTLB6PLVXXXL5JYEFMXLMP4J","target":"record","payload":{"canonical_record":{"source":{"id":"2206.08155","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-16T13:18:20Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"4e116894bc4bcb4071808db27d36c7cfae46cf25df01c0209469c8853de9fd80","abstract_canon_sha256":"351359a044e5e2a2ecb725b867d288bd983672fc4d695f33376cfd15c0d7a86b"},"schema_version":"1.0"},"canonical_sha256":"9b4b3587cf5d6f7bafa9c10acbad8fe2764fbe46a43a47ac7f4d687ba16beb9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:49.480497Z","signature_b64":"Wzen+FCLFoAYDpAdX9DJYS6S7q8J1PHFhexa6FxyzXWOFI91qlA9suuWyaQdy1/7DANKb47E6or06xO+CRAeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b4b3587cf5d6f7bafa9c10acbad8fe2764fbe46a43a47ac7f4d687ba16beb9e","last_reissued_at":"2026-07-05T05:04:49.479963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:49.479963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.08155","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tPRkC8b15IoSnP2f+SglxbfBBj2Cq+XT0yaGu9leftORuCuzH8uFvHKPBEtmey92BuG7UB11dlkNu/IP1o0DBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:59:30.220423Z"},"content_sha256":"78fd983c4b0b81fd29e02c122f1bf808c3ed672a8d33028e527da917769c1d9c","schema_version":"1.0","event_id":"sha256:78fd983c4b0b81fd29e02c122f1bf808c3ed672a8d33028e527da917769c1d9c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TNFTLB6PLVXXXL5JYEFMXLMP4J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antoine Miech, Antoine Yang, Cordelia Schmid, Ivan Laptev, Josef Sivic","submitted_at":"2022-06-16T13:18:20Z","abstract_excerpt":"Video question answering (VideoQA) is a complex task that requires diverse multi-modal data for training. Manual annotation of question and answers for videos, however, is tedious and prohibits scalability. To tackle this problem, recent methods consider zero-shot settings with no manual annotation of visual question-answer. In particular, a promising approach adapts frozen autoregressive language models pretrained on Web-scale text-only data to multi-modal inputs. In contrast, we here build on frozen bidirectional language models (BiLM) and show that such an approach provides a stronger and c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08155","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/2206.08155/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":"2026-07-05T05:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rNDOq3yEO7WddYWxHYEGsX36SL7Dyu7z7Asnu+vmfhncTrcgUJXyQ6QoFNmc90QsrDSgk2lX6AJIOxBSB6LABg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:59:30.220939Z"},"content_sha256":"a799bb8eb583a4689a304388ef0fa76c28118f2ca53143f5a48ee8f9ffbd9d62","schema_version":"1.0","event_id":"sha256:a799bb8eb583a4689a304388ef0fa76c28118f2ca53143f5a48ee8f9ffbd9d62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TNFTLB6PLVXXXL5JYEFMXLMP4J/bundle.json","state_url":"https://pith.science/pith/TNFTLB6PLVXXXL5JYEFMXLMP4J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TNFTLB6PLVXXXL5JYEFMXLMP4J/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":"2026-08-15T21:59:30Z","links":{"resolver":"https://pith.science/pith/TNFTLB6PLVXXXL5JYEFMXLMP4J","bundle":"https://pith.science/pith/TNFTLB6PLVXXXL5JYEFMXLMP4J/bundle.json","state":"https://pith.science/pith/TNFTLB6PLVXXXL5JYEFMXLMP4J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TNFTLB6PLVXXXL5JYEFMXLMP4J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TNFTLB6PLVXXXL5JYEFMXLMP4J","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":"351359a044e5e2a2ecb725b867d288bd983672fc4d695f33376cfd15c0d7a86b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-16T13:18:20Z","title_canon_sha256":"4e116894bc4bcb4071808db27d36c7cfae46cf25df01c0209469c8853de9fd80"},"schema_version":"1.0","source":{"id":"2206.08155","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.08155","created_at":"2026-07-05T05:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2206.08155v2","created_at":"2026-07-05T05:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08155","created_at":"2026-07-05T05:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"TNFTLB6PLVXX","created_at":"2026-07-05T05:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"TNFTLB6PLVXXXL5J","created_at":"2026-07-05T05:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"TNFTLB6P","created_at":"2026-07-05T05:04:49Z"}],"graph_snapshots":[{"event_id":"sha256:a799bb8eb583a4689a304388ef0fa76c28118f2ca53143f5a48ee8f9ffbd9d62","target":"graph","created_at":"2026-07-05T05:04:49Z","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/2206.08155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video question answering (VideoQA) is a complex task that requires diverse multi-modal data for training. Manual annotation of question and answers for videos, however, is tedious and prohibits scalability. To tackle this problem, recent methods consider zero-shot settings with no manual annotation of visual question-answer. In particular, a promising approach adapts frozen autoregressive language models pretrained on Web-scale text-only data to multi-modal inputs. In contrast, we here build on frozen bidirectional language models (BiLM) and show that such an approach provides a stronger and c","authors_text":"Antoine Miech, Antoine Yang, Cordelia Schmid, Ivan Laptev, Josef Sivic","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-16T13:18:20Z","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08155","kind":"arxiv","version":2},"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":"sha256:78fd983c4b0b81fd29e02c122f1bf808c3ed672a8d33028e527da917769c1d9c","target":"record","created_at":"2026-07-05T05:04:49Z","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":"351359a044e5e2a2ecb725b867d288bd983672fc4d695f33376cfd15c0d7a86b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-16T13:18:20Z","title_canon_sha256":"4e116894bc4bcb4071808db27d36c7cfae46cf25df01c0209469c8853de9fd80"},"schema_version":"1.0","source":{"id":"2206.08155","kind":"arxiv","version":2}},"canonical_sha256":"9b4b3587cf5d6f7bafa9c10acbad8fe2764fbe46a43a47ac7f4d687ba16beb9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b4b3587cf5d6f7bafa9c10acbad8fe2764fbe46a43a47ac7f4d687ba16beb9e","first_computed_at":"2026-07-05T05:04:49.479963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:49.479963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wzen+FCLFoAYDpAdX9DJYS6S7q8J1PHFhexa6FxyzXWOFI91qlA9suuWyaQdy1/7DANKb47E6or06xO+CRAeBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:49.480497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.08155","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78fd983c4b0b81fd29e02c122f1bf808c3ed672a8d33028e527da917769c1d9c","sha256:a799bb8eb583a4689a304388ef0fa76c28118f2ca53143f5a48ee8f9ffbd9d62"],"state_sha256":"112c0d066e4e4f89d18a65353d729bc4c2dbef97c4a0498f6e1df9af47d0891d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Td249GsJ3iFpCsxsxIKEChu/xcOAgyikPcOhgyOiJUNGj+HvAdurxrWos8V2RWQD3yk1XVY6/3AuYmpMf26bCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T21:59:30.226414Z","bundle_sha256":"2dab6186d0b469de6ec7c9a876cb6cea06725d5e5636caf910eb23fa9bd8b1a2"}}