{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DJGYFBNF7HXVQN4SZLPEWJFZ3P","short_pith_number":"pith:DJGYFBNF","canonical_record":{"source":{"id":"2408.01532","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-02T18:45:01Z","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"b9e877a4db8f4c07df49ef4958133e2f4127141d20d03fea9bc8b535ce092ef5","abstract_canon_sha256":"c69d148337d958b74946e1a32bd40a45f10ffe449f2863559f221e37a50e3f39"},"schema_version":"1.0"},"canonical_sha256":"1a4d8285a5f9ef583792cade4b24b9dbff7752d39a15bce80edeb5eacacff988","source":{"kind":"arxiv","id":"2408.01532","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01532","created_at":"2026-07-05T08:52:56Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01532v2","created_at":"2026-07-05T08:52:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01532","created_at":"2026-07-05T08:52:56Z"},{"alias_kind":"pith_short_12","alias_value":"DJGYFBNF7HXV","created_at":"2026-07-05T08:52:56Z"},{"alias_kind":"pith_short_16","alias_value":"DJGYFBNF7HXVQN4S","created_at":"2026-07-05T08:52:56Z"},{"alias_kind":"pith_short_8","alias_value":"DJGYFBNF","created_at":"2026-07-05T08:52:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DJGYFBNF7HXVQN4SZLPEWJFZ3P","target":"record","payload":{"canonical_record":{"source":{"id":"2408.01532","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-02T18:45:01Z","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"b9e877a4db8f4c07df49ef4958133e2f4127141d20d03fea9bc8b535ce092ef5","abstract_canon_sha256":"c69d148337d958b74946e1a32bd40a45f10ffe449f2863559f221e37a50e3f39"},"schema_version":"1.0"},"canonical_sha256":"1a4d8285a5f9ef583792cade4b24b9dbff7752d39a15bce80edeb5eacacff988","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:56.193107Z","signature_b64":"nqvi2wJR2bXV+fFeW3He2cYQ/MOenncNylp4FN8cVdnvPGVYzWnET2kZjHB6yZPMh7ZMjlX/Be9E2Eblvtv0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a4d8285a5f9ef583792cade4b24b9dbff7752d39a15bce80edeb5eacacff988","last_reissued_at":"2026-07-05T08:52:56.192688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:56.192688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.01532","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":"2026-07-05T08:52:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xue+6z+ouOh3nJK9Ux0MBuFFf0xIVq98uA+j3lvC/t5YpMEmHLKMoWf5+BhaqbZFzonnuI3fjcyWshSEgQw8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:55:18.255482Z"},"content_sha256":"65865419a1bf8d7467410d9867f83eb21b365d950f72bec697ac1d803fcf7dea","schema_version":"1.0","event_id":"sha256:65865419a1bf8d7467410d9867f83eb21b365d950f72bec697ac1d803fcf7dea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DJGYFBNF7HXVQN4SZLPEWJFZ3P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ajita Rattani, Vinaya Sree Katamneni","submitted_at":"2024-08-02T18:45:01Z","abstract_excerpt":"In the digital age, the emergence of deepfakes and synthetic media presents a significant threat to societal and political integrity. Deepfakes based on multi-modal manipulation, such as audio-visual, are more realistic and pose a greater threat. Current multi-modal deepfake detectors are often based on the attention-based fusion of heterogeneous data streams from multiple modalities. However, the heterogeneous nature of the data (such as audio and visual signals) creates a distributional modality gap and poses a significant challenge in effective fusion and hence multi-modal deepfake detectio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01532","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/2408.01532/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":"2026-07-05T08:52:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ey4L5+2/xh2Z6jGGg/cQnJVMHJLoft/SexhPB0J3wlvKh88lglKX5Rad/YqzHORySwtgnVdeU3HFlk9JhLUSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:55:18.256095Z"},"content_sha256":"78c7dd61de89d5f880294694213480f7066a8dc54f8362835f0ae2fbae0a3a7f","schema_version":"1.0","event_id":"sha256:78c7dd61de89d5f880294694213480f7066a8dc54f8362835f0ae2fbae0a3a7f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P/bundle.json","state_url":"https://pith.science/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P/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":"2026-08-08T12:55:18Z","links":{"resolver":"https://pith.science/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P","bundle":"https://pith.science/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P/bundle.json","state":"https://pith.science/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DJGYFBNF7HXVQN4SZLPEWJFZ3P","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":"c69d148337d958b74946e1a32bd40a45f10ffe449f2863559f221e37a50e3f39","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-02T18:45:01Z","title_canon_sha256":"b9e877a4db8f4c07df49ef4958133e2f4127141d20d03fea9bc8b535ce092ef5"},"schema_version":"1.0","source":{"id":"2408.01532","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01532","created_at":"2026-07-05T08:52:56Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01532v2","created_at":"2026-07-05T08:52:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01532","created_at":"2026-07-05T08:52:56Z"},{"alias_kind":"pith_short_12","alias_value":"DJGYFBNF7HXV","created_at":"2026-07-05T08:52:56Z"},{"alias_kind":"pith_short_16","alias_value":"DJGYFBNF7HXVQN4S","created_at":"2026-07-05T08:52:56Z"},{"alias_kind":"pith_short_8","alias_value":"DJGYFBNF","created_at":"2026-07-05T08:52:56Z"}],"graph_snapshots":[{"event_id":"sha256:78c7dd61de89d5f880294694213480f7066a8dc54f8362835f0ae2fbae0a3a7f","target":"graph","created_at":"2026-07-05T08:52:56Z","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/2408.01532/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the digital age, the emergence of deepfakes and synthetic media presents a significant threat to societal and political integrity. Deepfakes based on multi-modal manipulation, such as audio-visual, are more realistic and pose a greater threat. Current multi-modal deepfake detectors are often based on the attention-based fusion of heterogeneous data streams from multiple modalities. However, the heterogeneous nature of the data (such as audio and visual signals) creates a distributional modality gap and poses a significant challenge in effective fusion and hence multi-modal deepfake detectio","authors_text":"Ajita Rattani, Vinaya Sree Katamneni","cross_cats":["cs.AI","cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-02T18:45:01Z","title":"Contextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01532","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":"sha256:65865419a1bf8d7467410d9867f83eb21b365d950f72bec697ac1d803fcf7dea","target":"record","created_at":"2026-07-05T08:52:56Z","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":"c69d148337d958b74946e1a32bd40a45f10ffe449f2863559f221e37a50e3f39","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-02T18:45:01Z","title_canon_sha256":"b9e877a4db8f4c07df49ef4958133e2f4127141d20d03fea9bc8b535ce092ef5"},"schema_version":"1.0","source":{"id":"2408.01532","kind":"arxiv","version":2}},"canonical_sha256":"1a4d8285a5f9ef583792cade4b24b9dbff7752d39a15bce80edeb5eacacff988","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a4d8285a5f9ef583792cade4b24b9dbff7752d39a15bce80edeb5eacacff988","first_computed_at":"2026-07-05T08:52:56.192688Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:56.192688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nqvi2wJR2bXV+fFeW3He2cYQ/MOenncNylp4FN8cVdnvPGVYzWnET2kZjHB6yZPMh7ZMjlX/Be9E2Eblvtv0AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:56.193107Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.01532","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65865419a1bf8d7467410d9867f83eb21b365d950f72bec697ac1d803fcf7dea","sha256:78c7dd61de89d5f880294694213480f7066a8dc54f8362835f0ae2fbae0a3a7f"],"state_sha256":"043fe2e7666a1ceea253345684de6f1456321fa3a48dfd40ce82ba745fe7d6c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUdBtuttN0fcc2pyGUU2/dtKWecIF6v2M/d1gT2xZsZINMa1Qpr3TuGFPIaFhrZAM0SoXdphrP+LfsNOSflBBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:55:18.261351Z","bundle_sha256":"6034b4dce5d5c1c14ba362700cc40b3fb43d2b647796fe52008d5ca4100c1297"}}