{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CJU47PWECR7D3RHQ67VXDOQXCN","short_pith_number":"pith:CJU47PWE","canonical_record":{"source":{"id":"2411.04933","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:12:49Z","cross_cats_sorted":[],"title_canon_sha256":"32e2da1e9441d1820adb50511e5653bc3aad3f9c6752c4efb6594f10128dfb99","abstract_canon_sha256":"560b8bf5dc49d916385587a93dadde25160f61a78c6d0a5de402f86c8f2d6ed6"},"schema_version":"1.0"},"canonical_sha256":"1269cfbec4147e3dc4f0f7eb71ba17135e748d7a70d7ae5d4da61a5106490564","source":{"kind":"arxiv","id":"2411.04933","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04933","created_at":"2026-07-05T09:33:40Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04933v3","created_at":"2026-07-05T09:33:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04933","created_at":"2026-07-05T09:33:40Z"},{"alias_kind":"pith_short_12","alias_value":"CJU47PWECR7D","created_at":"2026-07-05T09:33:40Z"},{"alias_kind":"pith_short_16","alias_value":"CJU47PWECR7D3RHQ","created_at":"2026-07-05T09:33:40Z"},{"alias_kind":"pith_short_8","alias_value":"CJU47PWE","created_at":"2026-07-05T09:33:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CJU47PWECR7D3RHQ67VXDOQXCN","target":"record","payload":{"canonical_record":{"source":{"id":"2411.04933","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:12:49Z","cross_cats_sorted":[],"title_canon_sha256":"32e2da1e9441d1820adb50511e5653bc3aad3f9c6752c4efb6594f10128dfb99","abstract_canon_sha256":"560b8bf5dc49d916385587a93dadde25160f61a78c6d0a5de402f86c8f2d6ed6"},"schema_version":"1.0"},"canonical_sha256":"1269cfbec4147e3dc4f0f7eb71ba17135e748d7a70d7ae5d4da61a5106490564","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:40.844602Z","signature_b64":"yH4Ys7fGcBOkxuGC4al8ROXS6K42zFbkx6ecdFhf3kVlXkVL0Ne7ln7QEMxLxFhpvQRfyzZeLmnzWufylAMkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1269cfbec4147e3dc4f0f7eb71ba17135e748d7a70d7ae5d4da61a5106490564","last_reissued_at":"2026-07-05T09:33:40.844065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:40.844065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.04933","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:33:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kjIC3ixd/nse3zeeo1Z8suevT1S5pjetKryd7Es5cXSQMJGNkf0H/AU1rqq1AklkgXb4PRWWicMTh3GxvAQzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T04:29:54.425554Z"},"content_sha256":"0c8a6be5e5c2b19a5d219ea46769fcba4d8400debd3d79d6dd1ff09ae66b765c","schema_version":"1.0","event_id":"sha256:0c8a6be5e5c2b19a5d219ea46769fcba4d8400debd3d79d6dd1ff09ae66b765c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CJU47PWECR7D3RHQ67VXDOQXCN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lisen Dai, Tianyu Yang, Xiangliang Zhang, Yapeng Tian, Yiyang Nan, Zhenwen Liang","submitted_at":"2024-11-07T18:12:49Z","abstract_excerpt":"Audio-Visual Question Answering (AVQA) is a challenging task that involves answering questions based on both auditory and visual information in videos. A significant challenge is interpreting complex multi-modal scenes, which include both visual objects and sound sources, and connecting them to the given question. In this paper, we introduce the Source-aware Semantic Representation Network (SaSR-Net), a novel model designed for AVQA. SaSR-Net utilizes source-wise learnable tokens to efficiently capture and align audio-visual elements with the corresponding question. It streamlines the fusion o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04933","kind":"arxiv","version":3},"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/2411.04933/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":"2026-07-05T09:33:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0+pQzmoifWmpS0bF+R9U7l9gROYkbqokRXKVO42tCdOPYPtOdUkk1DvvzseoCn5WWj8/aR8jIU8Bxf3hma5wAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T04:29:54.426059Z"},"content_sha256":"f2c2fd1d023e62252aa37a8bed801747a9b844b04cec5fb835447a30127baa1e","schema_version":"1.0","event_id":"sha256:f2c2fd1d023e62252aa37a8bed801747a9b844b04cec5fb835447a30127baa1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CJU47PWECR7D3RHQ67VXDOQXCN/bundle.json","state_url":"https://pith.science/pith/CJU47PWECR7D3RHQ67VXDOQXCN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CJU47PWECR7D3RHQ67VXDOQXCN/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":"2026-08-22T04:29:54Z","links":{"resolver":"https://pith.science/pith/CJU47PWECR7D3RHQ67VXDOQXCN","bundle":"https://pith.science/pith/CJU47PWECR7D3RHQ67VXDOQXCN/bundle.json","state":"https://pith.science/pith/CJU47PWECR7D3RHQ67VXDOQXCN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CJU47PWECR7D3RHQ67VXDOQXCN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CJU47PWECR7D3RHQ67VXDOQXCN","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":"560b8bf5dc49d916385587a93dadde25160f61a78c6d0a5de402f86c8f2d6ed6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:12:49Z","title_canon_sha256":"32e2da1e9441d1820adb50511e5653bc3aad3f9c6752c4efb6594f10128dfb99"},"schema_version":"1.0","source":{"id":"2411.04933","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04933","created_at":"2026-07-05T09:33:40Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04933v3","created_at":"2026-07-05T09:33:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04933","created_at":"2026-07-05T09:33:40Z"},{"alias_kind":"pith_short_12","alias_value":"CJU47PWECR7D","created_at":"2026-07-05T09:33:40Z"},{"alias_kind":"pith_short_16","alias_value":"CJU47PWECR7D3RHQ","created_at":"2026-07-05T09:33:40Z"},{"alias_kind":"pith_short_8","alias_value":"CJU47PWE","created_at":"2026-07-05T09:33:40Z"}],"graph_snapshots":[{"event_id":"sha256:f2c2fd1d023e62252aa37a8bed801747a9b844b04cec5fb835447a30127baa1e","target":"graph","created_at":"2026-07-05T09:33:40Z","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/2411.04933/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Question Answering (AVQA) is a challenging task that involves answering questions based on both auditory and visual information in videos. A significant challenge is interpreting complex multi-modal scenes, which include both visual objects and sound sources, and connecting them to the given question. In this paper, we introduce the Source-aware Semantic Representation Network (SaSR-Net), a novel model designed for AVQA. SaSR-Net utilizes source-wise learnable tokens to efficiently capture and align audio-visual elements with the corresponding question. It streamlines the fusion o","authors_text":"Lisen Dai, Tianyu Yang, Xiangliang Zhang, Yapeng Tian, Yiyang Nan, Zhenwen Liang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:12:49Z","title":"SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04933","kind":"arxiv","version":3},"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":"sha256:0c8a6be5e5c2b19a5d219ea46769fcba4d8400debd3d79d6dd1ff09ae66b765c","target":"record","created_at":"2026-07-05T09:33:40Z","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":"560b8bf5dc49d916385587a93dadde25160f61a78c6d0a5de402f86c8f2d6ed6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:12:49Z","title_canon_sha256":"32e2da1e9441d1820adb50511e5653bc3aad3f9c6752c4efb6594f10128dfb99"},"schema_version":"1.0","source":{"id":"2411.04933","kind":"arxiv","version":3}},"canonical_sha256":"1269cfbec4147e3dc4f0f7eb71ba17135e748d7a70d7ae5d4da61a5106490564","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1269cfbec4147e3dc4f0f7eb71ba17135e748d7a70d7ae5d4da61a5106490564","first_computed_at":"2026-07-05T09:33:40.844065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:40.844065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yH4Ys7fGcBOkxuGC4al8ROXS6K42zFbkx6ecdFhf3kVlXkVL0Ne7ln7QEMxLxFhpvQRfyzZeLmnzWufylAMkCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:40.844602Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04933","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c8a6be5e5c2b19a5d219ea46769fcba4d8400debd3d79d6dd1ff09ae66b765c","sha256:f2c2fd1d023e62252aa37a8bed801747a9b844b04cec5fb835447a30127baa1e"],"state_sha256":"27b41b30ed1d518e14816e544c61557c4fa145e7fa96861740499ce72cac5bea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MUtQcSBVxKS9hX3f4SifkkrsT6Q83spKP/Hhz8hNxOs3sTtL8ktSqTbuTmSAiqmC+6qitp0ECperd4NqusLDAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T04:29:54.431280Z","bundle_sha256":"8cd29817b1a3caa752b93535f52c5ffd9f9d54b40892e914d224b4b4accf9f08"}}