{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KCLIGI5DXJZ4RSTXNSTRJKC4F3","short_pith_number":"pith:KCLIGI5D","canonical_record":{"source":{"id":"2306.17404","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-30T05:14:45Z","cross_cats_sorted":[],"title_canon_sha256":"052a7196826bbbb9ea7d8d7f5f3ab4aa6c03f395341977918575be51386fbd37","abstract_canon_sha256":"4446472f4f8c22367a0cd82562bd64a9c6ab5e9e1ba520d96cad37f6f244b76b"},"schema_version":"1.0"},"canonical_sha256":"50968323a3ba73c8ca776ca714a85c2eca3bffc88d7d57b7655cf7f587aac984","source":{"kind":"arxiv","id":"2306.17404","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17404","created_at":"2026-07-05T06:26:26Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17404v1","created_at":"2026-07-05T06:26:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17404","created_at":"2026-07-05T06:26:26Z"},{"alias_kind":"pith_short_12","alias_value":"KCLIGI5DXJZ4","created_at":"2026-07-05T06:26:26Z"},{"alias_kind":"pith_short_16","alias_value":"KCLIGI5DXJZ4RSTX","created_at":"2026-07-05T06:26:26Z"},{"alias_kind":"pith_short_8","alias_value":"KCLIGI5D","created_at":"2026-07-05T06:26:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KCLIGI5DXJZ4RSTXNSTRJKC4F3","target":"record","payload":{"canonical_record":{"source":{"id":"2306.17404","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-30T05:14:45Z","cross_cats_sorted":[],"title_canon_sha256":"052a7196826bbbb9ea7d8d7f5f3ab4aa6c03f395341977918575be51386fbd37","abstract_canon_sha256":"4446472f4f8c22367a0cd82562bd64a9c6ab5e9e1ba520d96cad37f6f244b76b"},"schema_version":"1.0"},"canonical_sha256":"50968323a3ba73c8ca776ca714a85c2eca3bffc88d7d57b7655cf7f587aac984","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:26.420322Z","signature_b64":"CofzTOVM1S1XYN17ix4D7yxksW7qhkv2b3jTIttcV0CDGvlhKbRYMJB74Zm8RX9+2aOAuw4HI0n4pGpz6ROdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50968323a3ba73c8ca776ca714a85c2eca3bffc88d7d57b7655cf7f587aac984","last_reissued_at":"2026-07-05T06:26:26.419826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:26.419826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.17404","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":"2026-07-05T06:26:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j/GLFcRAMCy2B27yYASF2O65HnhzKCG4XDd3JRODWrudWcl7jIT01BQLCCRg1ssl8+JqLzkJjVgTmFJg4rYKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:01:17.680447Z"},"content_sha256":"8e029c7381f480724210b1a4c586f9538fa9231a1a6c3085067bd76897f02f7c","schema_version":"1.0","event_id":"sha256:8e029c7381f480724210b1a4c586f9538fa9231a1a6c3085067bd76897f02f7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KCLIGI5DXJZ4RSTXNSTRJKC4F3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"QuAVF: Quality-aware Audio-Visual Fusion for Ego4D Talking to Me Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chien-Yi Wang, Hsi-Che Lin, Min-Hung Chen, Szu-Wei Fu, Yu-Chiang Frank Wang","submitted_at":"2023-06-30T05:14:45Z","abstract_excerpt":"This technical report describes our QuAVF@NTU-NVIDIA submission to the Ego4D Talking to Me (TTM) Challenge 2023. Based on the observation from the TTM task and the provided dataset, we propose to use two separate models to process the input videos and audio. By doing so, we can utilize all the labeled training data, including those without bounding box labels. Furthermore, we leverage the face quality score from a facial landmark prediction model for filtering noisy face input data. The face quality score is also employed in our proposed quality-aware fusion for integrating the results from tw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17404","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/2306.17404/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":"2026-07-05T06:26:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9x1CHKnSh01BoJjoatVeFX4Pxbq01xI5jFoEKairhCKz5xF1P7tY6cgquHA/+0ldk7xVMnopBcRnNEuVKK5xCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:01:17.680822Z"},"content_sha256":"3294e8696a940c06a23e29817d71732d9a7b0af32c6b2508242d236f0382be80","schema_version":"1.0","event_id":"sha256:3294e8696a940c06a23e29817d71732d9a7b0af32c6b2508242d236f0382be80"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KCLIGI5DXJZ4RSTXNSTRJKC4F3/bundle.json","state_url":"https://pith.science/pith/KCLIGI5DXJZ4RSTXNSTRJKC4F3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KCLIGI5DXJZ4RSTXNSTRJKC4F3/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":"2026-07-09T05:01:17Z","links":{"resolver":"https://pith.science/pith/KCLIGI5DXJZ4RSTXNSTRJKC4F3","bundle":"https://pith.science/pith/KCLIGI5DXJZ4RSTXNSTRJKC4F3/bundle.json","state":"https://pith.science/pith/KCLIGI5DXJZ4RSTXNSTRJKC4F3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KCLIGI5DXJZ4RSTXNSTRJKC4F3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KCLIGI5DXJZ4RSTXNSTRJKC4F3","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":"4446472f4f8c22367a0cd82562bd64a9c6ab5e9e1ba520d96cad37f6f244b76b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-30T05:14:45Z","title_canon_sha256":"052a7196826bbbb9ea7d8d7f5f3ab4aa6c03f395341977918575be51386fbd37"},"schema_version":"1.0","source":{"id":"2306.17404","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17404","created_at":"2026-07-05T06:26:26Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17404v1","created_at":"2026-07-05T06:26:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17404","created_at":"2026-07-05T06:26:26Z"},{"alias_kind":"pith_short_12","alias_value":"KCLIGI5DXJZ4","created_at":"2026-07-05T06:26:26Z"},{"alias_kind":"pith_short_16","alias_value":"KCLIGI5DXJZ4RSTX","created_at":"2026-07-05T06:26:26Z"},{"alias_kind":"pith_short_8","alias_value":"KCLIGI5D","created_at":"2026-07-05T06:26:26Z"}],"graph_snapshots":[{"event_id":"sha256:3294e8696a940c06a23e29817d71732d9a7b0af32c6b2508242d236f0382be80","target":"graph","created_at":"2026-07-05T06:26:26Z","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/2306.17404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This technical report describes our QuAVF@NTU-NVIDIA submission to the Ego4D Talking to Me (TTM) Challenge 2023. Based on the observation from the TTM task and the provided dataset, we propose to use two separate models to process the input videos and audio. By doing so, we can utilize all the labeled training data, including those without bounding box labels. Furthermore, we leverage the face quality score from a facial landmark prediction model for filtering noisy face input data. The face quality score is also employed in our proposed quality-aware fusion for integrating the results from tw","authors_text":"Chien-Yi Wang, Hsi-Che Lin, Min-Hung Chen, Szu-Wei Fu, Yu-Chiang Frank Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-30T05:14:45Z","title":"QuAVF: Quality-aware Audio-Visual Fusion for Ego4D Talking to Me Challenge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17404","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":"sha256:8e029c7381f480724210b1a4c586f9538fa9231a1a6c3085067bd76897f02f7c","target":"record","created_at":"2026-07-05T06:26:26Z","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":"4446472f4f8c22367a0cd82562bd64a9c6ab5e9e1ba520d96cad37f6f244b76b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-30T05:14:45Z","title_canon_sha256":"052a7196826bbbb9ea7d8d7f5f3ab4aa6c03f395341977918575be51386fbd37"},"schema_version":"1.0","source":{"id":"2306.17404","kind":"arxiv","version":1}},"canonical_sha256":"50968323a3ba73c8ca776ca714a85c2eca3bffc88d7d57b7655cf7f587aac984","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50968323a3ba73c8ca776ca714a85c2eca3bffc88d7d57b7655cf7f587aac984","first_computed_at":"2026-07-05T06:26:26.419826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:26.419826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CofzTOVM1S1XYN17ix4D7yxksW7qhkv2b3jTIttcV0CDGvlhKbRYMJB74Zm8RX9+2aOAuw4HI0n4pGpz6ROdCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:26.420322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.17404","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e029c7381f480724210b1a4c586f9538fa9231a1a6c3085067bd76897f02f7c","sha256:3294e8696a940c06a23e29817d71732d9a7b0af32c6b2508242d236f0382be80"],"state_sha256":"63f32a5e6aba9ccbe5fc54ba3d6a5e75343b4bd002f361047a4817623e22ad0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u8wvGETyL618OtC0pmW2bsw1/WFtd+rlpca5y7d31N7RUSJ++gJQenrmyX7bWvq7yK1MOyF7eeO6CLDnETLXDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:01:17.682835Z","bundle_sha256":"07855833a8301fcbadc868e87b30f38eda81865e35aa9dc8630a6a914fb34029"}}