{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2V7ZMBUTP6XLMG6W3WZCMLEGWT","short_pith_number":"pith:2V7ZMBUT","canonical_record":{"source":{"id":"2408.14441","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T17:33:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c2bcc7466e9733185554a520c96e5ec55bc81ca3f29157804ad56ff8cf2cacc","abstract_canon_sha256":"471080c501c70243106f46245eaac03365ef8290e77b38af2eb02249d2a2299d"},"schema_version":"1.0"},"canonical_sha256":"d57f9606937faeb61bd6ddb2262c86b4d6b1af008553560af85e50e69fea664f","source":{"kind":"arxiv","id":"2408.14441","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14441","created_at":"2026-07-05T08:59:20Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14441v1","created_at":"2026-07-05T08:59:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14441","created_at":"2026-07-05T08:59:20Z"},{"alias_kind":"pith_short_12","alias_value":"2V7ZMBUTP6XL","created_at":"2026-07-05T08:59:20Z"},{"alias_kind":"pith_short_16","alias_value":"2V7ZMBUTP6XLMG6W","created_at":"2026-07-05T08:59:20Z"},{"alias_kind":"pith_short_8","alias_value":"2V7ZMBUT","created_at":"2026-07-05T08:59:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2V7ZMBUTP6XLMG6W3WZCMLEGWT","target":"record","payload":{"canonical_record":{"source":{"id":"2408.14441","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T17:33:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c2bcc7466e9733185554a520c96e5ec55bc81ca3f29157804ad56ff8cf2cacc","abstract_canon_sha256":"471080c501c70243106f46245eaac03365ef8290e77b38af2eb02249d2a2299d"},"schema_version":"1.0"},"canonical_sha256":"d57f9606937faeb61bd6ddb2262c86b4d6b1af008553560af85e50e69fea664f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:20.885789Z","signature_b64":"HJwemMv59mFGWh/L7JWiuhIMIqIttorAo+DRcqly8+nFax59RmHNjEUvxzgzbXi3PmopXuJA4ZVfn+F0AC2ZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d57f9606937faeb61bd6ddb2262c86b4d6b1af008553560af85e50e69fea664f","last_reissued_at":"2026-07-05T08:59:20.885300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:20.885300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.14441","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":"2026-07-05T08:59:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L2aFqPy1n3Aa1qz6WD9IyQ+1QTDCJoLL0+7596nGQL5pbaPGbm5/RgJFuwEKC4OG2ceKGNKT2X5iURbOFoHeAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:15:13.957565Z"},"content_sha256":"9a553eb66f6dfe9ebdf6eb02cfc9dd4467c340d5322d0c02cf7247e463c6dfc8","schema_version":"1.0","event_id":"sha256:9a553eb66f6dfe9ebdf6eb02cfc9dd4467c340d5322d0c02cf7247e463c6dfc8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2V7ZMBUTP6XLMG6W3WZCMLEGWT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attend-Fusion: Efficient Audio-Visual Fusion for Video Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Armin Mustafa, Asmar Nadeem, Mahrukh Awan, Muhammad Junaid Awan, Syed Sameed Husain","submitted_at":"2024-08-26T17:33:47Z","abstract_excerpt":"Exploiting both audio and visual modalities for video classification is a challenging task, as the existing methods require large model architectures, leading to high computational complexity and resource requirements. Smaller architectures, on the other hand, struggle to achieve optimal performance. In this paper, we propose Attend-Fusion, an audio-visual (AV) fusion approach that introduces a compact model architecture specifically designed to capture intricate audio-visual relationships in video data. Through extensive experiments on the challenging YouTube-8M dataset, we demonstrate that A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14441","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/2408.14441/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":"2026-07-05T08:59:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XvRIUHMTD5W+KFFPRvCrofWRlJFK3+TF+JmP3pyiRbRuz4two2tiEmiuM9+iH3Amkc29nm5dkYwAD11NQRCMAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:15:13.958443Z"},"content_sha256":"51c8afab0542bc138b8569da501d5d10caa2de95c984f63b67e5cf05daec8df9","schema_version":"1.0","event_id":"sha256:51c8afab0542bc138b8569da501d5d10caa2de95c984f63b67e5cf05daec8df9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2V7ZMBUTP6XLMG6W3WZCMLEGWT/bundle.json","state_url":"https://pith.science/pith/2V7ZMBUTP6XLMG6W3WZCMLEGWT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2V7ZMBUTP6XLMG6W3WZCMLEGWT/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":"2026-07-08T07:15:13Z","links":{"resolver":"https://pith.science/pith/2V7ZMBUTP6XLMG6W3WZCMLEGWT","bundle":"https://pith.science/pith/2V7ZMBUTP6XLMG6W3WZCMLEGWT/bundle.json","state":"https://pith.science/pith/2V7ZMBUTP6XLMG6W3WZCMLEGWT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2V7ZMBUTP6XLMG6W3WZCMLEGWT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2V7ZMBUTP6XLMG6W3WZCMLEGWT","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":"471080c501c70243106f46245eaac03365ef8290e77b38af2eb02249d2a2299d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T17:33:47Z","title_canon_sha256":"3c2bcc7466e9733185554a520c96e5ec55bc81ca3f29157804ad56ff8cf2cacc"},"schema_version":"1.0","source":{"id":"2408.14441","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14441","created_at":"2026-07-05T08:59:20Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14441v1","created_at":"2026-07-05T08:59:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14441","created_at":"2026-07-05T08:59:20Z"},{"alias_kind":"pith_short_12","alias_value":"2V7ZMBUTP6XL","created_at":"2026-07-05T08:59:20Z"},{"alias_kind":"pith_short_16","alias_value":"2V7ZMBUTP6XLMG6W","created_at":"2026-07-05T08:59:20Z"},{"alias_kind":"pith_short_8","alias_value":"2V7ZMBUT","created_at":"2026-07-05T08:59:20Z"}],"graph_snapshots":[{"event_id":"sha256:51c8afab0542bc138b8569da501d5d10caa2de95c984f63b67e5cf05daec8df9","target":"graph","created_at":"2026-07-05T08:59:20Z","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/2408.14441/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploiting both audio and visual modalities for video classification is a challenging task, as the existing methods require large model architectures, leading to high computational complexity and resource requirements. Smaller architectures, on the other hand, struggle to achieve optimal performance. In this paper, we propose Attend-Fusion, an audio-visual (AV) fusion approach that introduces a compact model architecture specifically designed to capture intricate audio-visual relationships in video data. Through extensive experiments on the challenging YouTube-8M dataset, we demonstrate that A","authors_text":"Armin Mustafa, Asmar Nadeem, Mahrukh Awan, Muhammad Junaid Awan, Syed Sameed Husain","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T17:33:47Z","title":"Attend-Fusion: Efficient Audio-Visual Fusion for Video Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14441","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":"sha256:9a553eb66f6dfe9ebdf6eb02cfc9dd4467c340d5322d0c02cf7247e463c6dfc8","target":"record","created_at":"2026-07-05T08:59:20Z","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":"471080c501c70243106f46245eaac03365ef8290e77b38af2eb02249d2a2299d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T17:33:47Z","title_canon_sha256":"3c2bcc7466e9733185554a520c96e5ec55bc81ca3f29157804ad56ff8cf2cacc"},"schema_version":"1.0","source":{"id":"2408.14441","kind":"arxiv","version":1}},"canonical_sha256":"d57f9606937faeb61bd6ddb2262c86b4d6b1af008553560af85e50e69fea664f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d57f9606937faeb61bd6ddb2262c86b4d6b1af008553560af85e50e69fea664f","first_computed_at":"2026-07-05T08:59:20.885300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:20.885300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HJwemMv59mFGWh/L7JWiuhIMIqIttorAo+DRcqly8+nFax59RmHNjEUvxzgzbXi3PmopXuJA4ZVfn+F0AC2ZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:20.885789Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.14441","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a553eb66f6dfe9ebdf6eb02cfc9dd4467c340d5322d0c02cf7247e463c6dfc8","sha256:51c8afab0542bc138b8569da501d5d10caa2de95c984f63b67e5cf05daec8df9"],"state_sha256":"bf5c49b6b8c15f2a02ce99a7d44b3980cd5089a441cdc864ad3aa72e8a4387ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1fTkvGoX9CjrDG5glxYzjy1LAb5e64/3uHtEXiFrJsp7VAP4mx7yTfHRP8+3dJeUrMuzIvCRDK7mAnze+YbCDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T07:15:13.963075Z","bundle_sha256":"365341b5636ae417338446ab51002c219431a4c72814decd6096e775d9add2e3"}}