{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SAOYHAVGKKY77UASZKL376RMSH","short_pith_number":"pith:SAOYHAVG","canonical_record":{"source":{"id":"2306.11732","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T20:56:20Z","cross_cats_sorted":[],"title_canon_sha256":"2958918ffa22873fe259300a99088a49c21009e14a1960175a9bf7964b5d4534","abstract_canon_sha256":"bc946e066539e12cd8b2e1ea1614fc8c4ebefdb823d65c8ae172a538f93bd20e"},"schema_version":"1.0"},"canonical_sha256":"901d8382a652b1ffd012ca97bffa2c91f54fce119f6bc487b1dacac6f8b1a628","source":{"kind":"arxiv","id":"2306.11732","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11732","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11732v1","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11732","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"pith_short_12","alias_value":"SAOYHAVGKKY7","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"pith_short_16","alias_value":"SAOYHAVGKKY77UAS","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"pith_short_8","alias_value":"SAOYHAVG","created_at":"2026-07-05T06:22:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SAOYHAVGKKY77UASZKL376RMSH","target":"record","payload":{"canonical_record":{"source":{"id":"2306.11732","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T20:56:20Z","cross_cats_sorted":[],"title_canon_sha256":"2958918ffa22873fe259300a99088a49c21009e14a1960175a9bf7964b5d4534","abstract_canon_sha256":"bc946e066539e12cd8b2e1ea1614fc8c4ebefdb823d65c8ae172a538f93bd20e"},"schema_version":"1.0"},"canonical_sha256":"901d8382a652b1ffd012ca97bffa2c91f54fce119f6bc487b1dacac6f8b1a628","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:22:22.957950Z","signature_b64":"9n8ScG6tTIDFkdLI0R7MjaZV0uJY60AeC3Bdtj+xorUe87AdScwCzwMOkInYK+ZhLxYrmOTbA5kbdTnQG/y8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"901d8382a652b1ffd012ca97bffa2c91f54fce119f6bc487b1dacac6f8b1a628","last_reissued_at":"2026-07-05T06:22:22.957458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:22:22.957458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.11732","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":"2026-07-05T06:22:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xbx28F9HoEs8QNlgM7bJLVb5IK6SCtg+9UZVAbYinL45ZB9JIwmIyOlsKmWmOnsZGLlThyLoMJ5YwZZH0HvBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:07:44.612753Z"},"content_sha256":"c6f1e32c1f975667b751d7563416fd0f212fee1f5534a70b292ac853985f798f","schema_version":"1.0","event_id":"sha256:c6f1e32c1f975667b751d7563416fd0f212fee1f5534a70b292ac853985f798f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SAOYHAVGKKY77UASZKL376RMSH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Junting Pan, Renrui Zhang, Xiatian Zhu, Yi Wang, Yu Qiao, Yuying Ge, Ziyi Lin","submitted_at":"2023-06-15T20:56:20Z","abstract_excerpt":"Video Question Answering (VideoQA) has been significantly advanced from the scaling of recent Large Language Models (LLMs). The key idea is to convert the visual information into the language feature space so that the capacity of LLMs can be fully exploited. Existing VideoQA methods typically take two paradigms: (1) learning cross-modal alignment, and (2) using an off-the-shelf captioning model to describe the visual data. However, the first design needs costly training on many extra multi-modal data, whilst the second is further limited by limited domain generalization. To address these limit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11732","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/2306.11732/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":"2026-07-05T06:22:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9tz93agGy5EhWDvTr74k1UTFGo335pVPWJMF+AHLmiRD0IHx1jE5pxIBftB6vE+WmhG6wnpWlOZZ7f3CQT6JBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:07:44.613070Z"},"content_sha256":"8c1a4b8fa7d35c92d76d38daa7964807c966f345ef67e4e9d93a9cf591ef86d2","schema_version":"1.0","event_id":"sha256:8c1a4b8fa7d35c92d76d38daa7964807c966f345ef67e4e9d93a9cf591ef86d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SAOYHAVGKKY77UASZKL376RMSH/bundle.json","state_url":"https://pith.science/pith/SAOYHAVGKKY77UASZKL376RMSH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SAOYHAVGKKY77UASZKL376RMSH/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":"2026-08-11T14:07:44Z","links":{"resolver":"https://pith.science/pith/SAOYHAVGKKY77UASZKL376RMSH","bundle":"https://pith.science/pith/SAOYHAVGKKY77UASZKL376RMSH/bundle.json","state":"https://pith.science/pith/SAOYHAVGKKY77UASZKL376RMSH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SAOYHAVGKKY77UASZKL376RMSH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SAOYHAVGKKY77UASZKL376RMSH","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":"bc946e066539e12cd8b2e1ea1614fc8c4ebefdb823d65c8ae172a538f93bd20e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T20:56:20Z","title_canon_sha256":"2958918ffa22873fe259300a99088a49c21009e14a1960175a9bf7964b5d4534"},"schema_version":"1.0","source":{"id":"2306.11732","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11732","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11732v1","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11732","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"pith_short_12","alias_value":"SAOYHAVGKKY7","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"pith_short_16","alias_value":"SAOYHAVGKKY77UAS","created_at":"2026-07-05T06:22:22Z"},{"alias_kind":"pith_short_8","alias_value":"SAOYHAVG","created_at":"2026-07-05T06:22:22Z"}],"graph_snapshots":[{"event_id":"sha256:8c1a4b8fa7d35c92d76d38daa7964807c966f345ef67e4e9d93a9cf591ef86d2","target":"graph","created_at":"2026-07-05T06:22:22Z","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/2306.11732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Question Answering (VideoQA) has been significantly advanced from the scaling of recent Large Language Models (LLMs). The key idea is to convert the visual information into the language feature space so that the capacity of LLMs can be fully exploited. Existing VideoQA methods typically take two paradigms: (1) learning cross-modal alignment, and (2) using an off-the-shelf captioning model to describe the visual data. However, the first design needs costly training on many extra multi-modal data, whilst the second is further limited by limited domain generalization. To address these limit","authors_text":"Hongsheng Li, Junting Pan, Renrui Zhang, Xiatian Zhu, Yi Wang, Yu Qiao, Yuying Ge, Ziyi Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T20:56:20Z","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11732","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:c6f1e32c1f975667b751d7563416fd0f212fee1f5534a70b292ac853985f798f","target":"record","created_at":"2026-07-05T06:22:22Z","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":"bc946e066539e12cd8b2e1ea1614fc8c4ebefdb823d65c8ae172a538f93bd20e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T20:56:20Z","title_canon_sha256":"2958918ffa22873fe259300a99088a49c21009e14a1960175a9bf7964b5d4534"},"schema_version":"1.0","source":{"id":"2306.11732","kind":"arxiv","version":1}},"canonical_sha256":"901d8382a652b1ffd012ca97bffa2c91f54fce119f6bc487b1dacac6f8b1a628","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"901d8382a652b1ffd012ca97bffa2c91f54fce119f6bc487b1dacac6f8b1a628","first_computed_at":"2026-07-05T06:22:22.957458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:22:22.957458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9n8ScG6tTIDFkdLI0R7MjaZV0uJY60AeC3Bdtj+xorUe87AdScwCzwMOkInYK+ZhLxYrmOTbA5kbdTnQG/y8AA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:22:22.957950Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.11732","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6f1e32c1f975667b751d7563416fd0f212fee1f5534a70b292ac853985f798f","sha256:8c1a4b8fa7d35c92d76d38daa7964807c966f345ef67e4e9d93a9cf591ef86d2"],"state_sha256":"2adcd999a21375b6261e05e6788adaf8da7595fadee3088e9ee20db4348ac7f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oxzSTa9EtorYIcD09udwuoA/cqzEMggD3T1EASeHQv8RbXtyN+rpSDWxzWGTHggvPIY6YBpDb5S1Q8AdhXpODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T14:07:44.615954Z","bundle_sha256":"79d0c4343c9d4dea31821d7361bf5a1ef5b423d236be9a42fe0369f7889687c9"}}