{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AAEEK22KM35EB6KBJNRKYCD4HC","short_pith_number":"pith:AAEEK22K","canonical_record":{"source":{"id":"2404.10904","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T20:51:36Z","cross_cats_sorted":[],"title_canon_sha256":"f4a122aa5b5ac80299a9f2cf04c2d693ba26b4054d17df467e423f12a8d420e1","abstract_canon_sha256":"212330373490dc01af8beed672cb994607f0eee7708cfd32599b1b5392e8cf29"},"schema_version":"1.0"},"canonical_sha256":"0008456b4a66fa40f9414b62ac087c3894c0afb789b52b4b848d8475cb211ddc","source":{"kind":"arxiv","id":"2404.10904","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10904","created_at":"2026-07-05T09:02:57Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10904v2","created_at":"2026-07-05T09:02:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10904","created_at":"2026-07-05T09:02:57Z"},{"alias_kind":"pith_short_12","alias_value":"AAEEK22KM35E","created_at":"2026-07-05T09:02:57Z"},{"alias_kind":"pith_short_16","alias_value":"AAEEK22KM35EB6KB","created_at":"2026-07-05T09:02:57Z"},{"alias_kind":"pith_short_8","alias_value":"AAEEK22K","created_at":"2026-07-05T09:02:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AAEEK22KM35EB6KBJNRKYCD4HC","target":"record","payload":{"canonical_record":{"source":{"id":"2404.10904","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T20:51:36Z","cross_cats_sorted":[],"title_canon_sha256":"f4a122aa5b5ac80299a9f2cf04c2d693ba26b4054d17df467e423f12a8d420e1","abstract_canon_sha256":"212330373490dc01af8beed672cb994607f0eee7708cfd32599b1b5392e8cf29"},"schema_version":"1.0"},"canonical_sha256":"0008456b4a66fa40f9414b62ac087c3894c0afb789b52b4b848d8475cb211ddc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:57.772870Z","signature_b64":"Wwlx9wcMlG7isj5mDGWc+YbX4ZNxrCXuzeCTjZewxtuh0wKsGuuk4mpJ+s7hZOJnzy48ZFgZt5NlpNsmSz/YAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0008456b4a66fa40f9414b62ac087c3894c0afb789b52b4b848d8475cb211ddc","last_reissued_at":"2026-07-05T09:02:57.772361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:57.772361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.10904","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":"2026-07-05T09:02:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ce7Z6Q2rySZQ6Bo0u5i9KaMbs6Ol7q+dNO97fpdMxFT4lohHxn34hEB7Lr4IEKJ/bni4jWKRGeOayxlgSJWDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:39:44.890809Z"},"content_sha256":"34b9609aa047cf6709ef411fb893c32f981d642069d5512a6d6533eacdbc7b4b","schema_version":"1.0","event_id":"sha256:34b9609aa047cf6709ef411fb893c32f981d642069d5512a6d6533eacdbc7b4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AAEEK22KM35EB6KBJNRKYCD4HC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Florian Blume, Marah Halawa, Martin Maier, Olaf Hellwich, Pia Bideau, Rasha Abdel Rahman","submitted_at":"2024-04-16T20:51:36Z","abstract_excerpt":"Human communication is multi-modal; e.g., face-to-face interaction involves auditory signals (speech) and visual signals (face movements and hand gestures). Hence, it is essential to exploit multiple modalities when designing machine learning-based facial expression recognition systems. In addition, given the ever-growing quantities of video data that capture human facial expressions, such systems should utilize raw unlabeled videos without requiring expensive annotations. Therefore, in this work, we employ a multitask multi-modal self-supervised learning method for facial expression recogniti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10904","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/2404.10904/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":"2026-07-05T09:02:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wqRObVmjjgm7D5OfgmZb85iYTiqy2Td0V19jxMxeQMsWxsYz9yuciIJ6gzATpoYbNvF7J44c2tlcbYCb1IbhDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:39:44.891328Z"},"content_sha256":"0128e03dd1f8eb217abcca2d56e9f650edd7b00e2cbfd747a71b3b33a7c28e97","schema_version":"1.0","event_id":"sha256:0128e03dd1f8eb217abcca2d56e9f650edd7b00e2cbfd747a71b3b33a7c28e97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AAEEK22KM35EB6KBJNRKYCD4HC/bundle.json","state_url":"https://pith.science/pith/AAEEK22KM35EB6KBJNRKYCD4HC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AAEEK22KM35EB6KBJNRKYCD4HC/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":"2026-08-21T18:39:44Z","links":{"resolver":"https://pith.science/pith/AAEEK22KM35EB6KBJNRKYCD4HC","bundle":"https://pith.science/pith/AAEEK22KM35EB6KBJNRKYCD4HC/bundle.json","state":"https://pith.science/pith/AAEEK22KM35EB6KBJNRKYCD4HC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AAEEK22KM35EB6KBJNRKYCD4HC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AAEEK22KM35EB6KBJNRKYCD4HC","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":"212330373490dc01af8beed672cb994607f0eee7708cfd32599b1b5392e8cf29","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T20:51:36Z","title_canon_sha256":"f4a122aa5b5ac80299a9f2cf04c2d693ba26b4054d17df467e423f12a8d420e1"},"schema_version":"1.0","source":{"id":"2404.10904","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10904","created_at":"2026-07-05T09:02:57Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10904v2","created_at":"2026-07-05T09:02:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10904","created_at":"2026-07-05T09:02:57Z"},{"alias_kind":"pith_short_12","alias_value":"AAEEK22KM35E","created_at":"2026-07-05T09:02:57Z"},{"alias_kind":"pith_short_16","alias_value":"AAEEK22KM35EB6KB","created_at":"2026-07-05T09:02:57Z"},{"alias_kind":"pith_short_8","alias_value":"AAEEK22K","created_at":"2026-07-05T09:02:57Z"}],"graph_snapshots":[{"event_id":"sha256:0128e03dd1f8eb217abcca2d56e9f650edd7b00e2cbfd747a71b3b33a7c28e97","target":"graph","created_at":"2026-07-05T09:02:57Z","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/2404.10904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human communication is multi-modal; e.g., face-to-face interaction involves auditory signals (speech) and visual signals (face movements and hand gestures). Hence, it is essential to exploit multiple modalities when designing machine learning-based facial expression recognition systems. In addition, given the ever-growing quantities of video data that capture human facial expressions, such systems should utilize raw unlabeled videos without requiring expensive annotations. Therefore, in this work, we employ a multitask multi-modal self-supervised learning method for facial expression recogniti","authors_text":"Florian Blume, Marah Halawa, Martin Maier, Olaf Hellwich, Pia Bideau, Rasha Abdel Rahman","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T20:51:36Z","title":"Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10904","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":"sha256:34b9609aa047cf6709ef411fb893c32f981d642069d5512a6d6533eacdbc7b4b","target":"record","created_at":"2026-07-05T09:02:57Z","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":"212330373490dc01af8beed672cb994607f0eee7708cfd32599b1b5392e8cf29","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T20:51:36Z","title_canon_sha256":"f4a122aa5b5ac80299a9f2cf04c2d693ba26b4054d17df467e423f12a8d420e1"},"schema_version":"1.0","source":{"id":"2404.10904","kind":"arxiv","version":2}},"canonical_sha256":"0008456b4a66fa40f9414b62ac087c3894c0afb789b52b4b848d8475cb211ddc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0008456b4a66fa40f9414b62ac087c3894c0afb789b52b4b848d8475cb211ddc","first_computed_at":"2026-07-05T09:02:57.772361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:02:57.772361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wwlx9wcMlG7isj5mDGWc+YbX4ZNxrCXuzeCTjZewxtuh0wKsGuuk4mpJ+s7hZOJnzy48ZFgZt5NlpNsmSz/YAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:02:57.772870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10904","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34b9609aa047cf6709ef411fb893c32f981d642069d5512a6d6533eacdbc7b4b","sha256:0128e03dd1f8eb217abcca2d56e9f650edd7b00e2cbfd747a71b3b33a7c28e97"],"state_sha256":"4f8c473a9ea67c391be3e17d336b74931decab2504cc8fa1e44c7f2c467bd086"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DfCVmCOJaGiSb9bifMAmFLw32Rhf3/aOZtsgWkjO7Y5y6f50BSayh4YxwmxNHnk1x91PzybsksU70W6wN2ltAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T18:39:44.898463Z","bundle_sha256":"26fcc6335c27954adfe47af6b0b9a9e716f1caf2e776dca062d2e8ba6d086d4c"}}