{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7KLHWUBCBT3NOFZQPHXFAR5L3I","short_pith_number":"pith:7KLHWUBC","canonical_record":{"source":{"id":"2310.16754","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T16:40:09Z","cross_cats_sorted":[],"title_canon_sha256":"6877150727dc8ccc9ed37588364ad3fc7448fb5538c36a23d679ca4c3749f707","abstract_canon_sha256":"009b484ce5c875777e0bcd053a04574e3cd8f515c2e4fcde64fcc876850abc1f"},"schema_version":"1.0"},"canonical_sha256":"fa967b50220cf6d7173079ee5047abda37249c282fa89748efe6ca1000500920","source":{"kind":"arxiv","id":"2310.16754","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16754","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16754v2","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16754","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"pith_short_12","alias_value":"7KLHWUBCBT3N","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"pith_short_16","alias_value":"7KLHWUBCBT3NOFZQ","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"pith_short_8","alias_value":"7KLHWUBC","created_at":"2026-07-05T07:06:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7KLHWUBCBT3NOFZQPHXFAR5L3I","target":"record","payload":{"canonical_record":{"source":{"id":"2310.16754","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T16:40:09Z","cross_cats_sorted":[],"title_canon_sha256":"6877150727dc8ccc9ed37588364ad3fc7448fb5538c36a23d679ca4c3749f707","abstract_canon_sha256":"009b484ce5c875777e0bcd053a04574e3cd8f515c2e4fcde64fcc876850abc1f"},"schema_version":"1.0"},"canonical_sha256":"fa967b50220cf6d7173079ee5047abda37249c282fa89748efe6ca1000500920","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:06.373837Z","signature_b64":"jIpCBMghOPQZdSrwFHphfNnQ4TOaI6fsA93BW8wj8PoMZwbjTzHQGndHafgQOSf0qjw+vepukD41/2kCuA9EAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa967b50220cf6d7173079ee5047abda37249c282fa89748efe6ca1000500920","last_reissued_at":"2026-07-05T07:06:06.373405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:06.373405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.16754","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":"2026-07-05T07:06:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Ch4W9UpnD0wd6nAyBf2vzZntEla0rXhDC16eK47Yra6pn7Ah1Idt3zYF//C4nltZTtjTneK3Wk4LsN1ERD9BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:39:00.256163Z"},"content_sha256":"d5a9f2adbe30304e6777bf9cc61320de8f014131e17deb859881be231a5af47f","schema_version":"1.0","event_id":"sha256:d5a9f2adbe30304e6777bf9cc61320de8f014131e17deb859881be231a5af47f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7KLHWUBCBT3NOFZQPHXFAR5L3I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrian Hilton, Armin Mustafa, Asmar Nadeem, Graham Thomas, Robert Dawes","submitted_at":"2023-10-25T16:40:09Z","abstract_excerpt":"In the context of Audio Visual Question Answering (AVQA) tasks, the audio visual modalities could be learnt on three levels: 1) Spatial, 2) Temporal, and 3) Semantic. Existing AVQA methods suffer from two major shortcomings; the audio-visual (AV) information passing through the network isn't aligned on Spatial and Temporal levels; and, inter-modal (audio and visual) Semantic information is often not balanced within a context; this results in poor performance. In this paper, we propose a novel end-to-end Contextual Multi-modal Alignment (CAD) network that addresses the challenges in AVQA method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16754","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/2310.16754/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":"2026-07-05T07:06:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ukZ+6OQ5ceCeotur/NSARKHW3gjdIj9uy8NIno/uqjFq5a4b1fSs8O3UrY/fk5hbxux1oNZKE7wAq6iMMSbpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:39:00.257088Z"},"content_sha256":"16a1a5ba62878eafb02b206f0f0d6cab0f4cba1164bdc186a8cfc154251d0656","schema_version":"1.0","event_id":"sha256:16a1a5ba62878eafb02b206f0f0d6cab0f4cba1164bdc186a8cfc154251d0656"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7KLHWUBCBT3NOFZQPHXFAR5L3I/bundle.json","state_url":"https://pith.science/pith/7KLHWUBCBT3NOFZQPHXFAR5L3I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7KLHWUBCBT3NOFZQPHXFAR5L3I/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":"2026-08-03T20:39:00Z","links":{"resolver":"https://pith.science/pith/7KLHWUBCBT3NOFZQPHXFAR5L3I","bundle":"https://pith.science/pith/7KLHWUBCBT3NOFZQPHXFAR5L3I/bundle.json","state":"https://pith.science/pith/7KLHWUBCBT3NOFZQPHXFAR5L3I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7KLHWUBCBT3NOFZQPHXFAR5L3I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7KLHWUBCBT3NOFZQPHXFAR5L3I","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":"009b484ce5c875777e0bcd053a04574e3cd8f515c2e4fcde64fcc876850abc1f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T16:40:09Z","title_canon_sha256":"6877150727dc8ccc9ed37588364ad3fc7448fb5538c36a23d679ca4c3749f707"},"schema_version":"1.0","source":{"id":"2310.16754","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16754","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16754v2","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16754","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"pith_short_12","alias_value":"7KLHWUBCBT3N","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"pith_short_16","alias_value":"7KLHWUBCBT3NOFZQ","created_at":"2026-07-05T07:06:06Z"},{"alias_kind":"pith_short_8","alias_value":"7KLHWUBC","created_at":"2026-07-05T07:06:06Z"}],"graph_snapshots":[{"event_id":"sha256:16a1a5ba62878eafb02b206f0f0d6cab0f4cba1164bdc186a8cfc154251d0656","target":"graph","created_at":"2026-07-05T07:06:06Z","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/2310.16754/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the context of Audio Visual Question Answering (AVQA) tasks, the audio visual modalities could be learnt on three levels: 1) Spatial, 2) Temporal, and 3) Semantic. Existing AVQA methods suffer from two major shortcomings; the audio-visual (AV) information passing through the network isn't aligned on Spatial and Temporal levels; and, inter-modal (audio and visual) Semantic information is often not balanced within a context; this results in poor performance. In this paper, we propose a novel end-to-end Contextual Multi-modal Alignment (CAD) network that addresses the challenges in AVQA method","authors_text":"Adrian Hilton, Armin Mustafa, Asmar Nadeem, Graham Thomas, Robert Dawes","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T16:40:09Z","title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16754","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:d5a9f2adbe30304e6777bf9cc61320de8f014131e17deb859881be231a5af47f","target":"record","created_at":"2026-07-05T07:06:06Z","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":"009b484ce5c875777e0bcd053a04574e3cd8f515c2e4fcde64fcc876850abc1f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T16:40:09Z","title_canon_sha256":"6877150727dc8ccc9ed37588364ad3fc7448fb5538c36a23d679ca4c3749f707"},"schema_version":"1.0","source":{"id":"2310.16754","kind":"arxiv","version":2}},"canonical_sha256":"fa967b50220cf6d7173079ee5047abda37249c282fa89748efe6ca1000500920","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa967b50220cf6d7173079ee5047abda37249c282fa89748efe6ca1000500920","first_computed_at":"2026-07-05T07:06:06.373405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:06.373405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jIpCBMghOPQZdSrwFHphfNnQ4TOaI6fsA93BW8wj8PoMZwbjTzHQGndHafgQOSf0qjw+vepukD41/2kCuA9EAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:06.373837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16754","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5a9f2adbe30304e6777bf9cc61320de8f014131e17deb859881be231a5af47f","sha256:16a1a5ba62878eafb02b206f0f0d6cab0f4cba1164bdc186a8cfc154251d0656"],"state_sha256":"d7254bafd730dfa2de7204a2c6812132023db55093a58b60090381e956734af4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E7LXZLZkpP7voX7ot1zxk1fFQZ2UeQylbbmF6qjt0uqiNW6DjklByTwVdmjoCZddR6s1oEyH58jCTW96/dMvBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:39:00.264253Z","bundle_sha256":"1143586ef348dbec2b97b3aedb8267420e2d57b68346b229dac5cbfeeb51489d"}}