{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PL65KRY2D3DR25UVGBRCIQH6WY","short_pith_number":"pith:PL65KRY2","canonical_record":{"source":{"id":"2308.13382","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-25T13:52:05Z","cross_cats_sorted":[],"title_canon_sha256":"1ebb71ecf79a0b5439730daa026ab7451885f3cf149d1332b77ae4ecf099f73d","abstract_canon_sha256":"d28322a4096481219625950ac123828b297fa4e5b0f6bb2a6b9660206aaed1c7"},"schema_version":"1.0"},"canonical_sha256":"7afdd5471a1ec71d769530622440feb635ba827e84ef7018362fc1b1a7c81ed6","source":{"kind":"arxiv","id":"2308.13382","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13382","created_at":"2026-07-05T09:40:36Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13382v3","created_at":"2026-07-05T09:40:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13382","created_at":"2026-07-05T09:40:36Z"},{"alias_kind":"pith_short_12","alias_value":"PL65KRY2D3DR","created_at":"2026-07-05T09:40:36Z"},{"alias_kind":"pith_short_16","alias_value":"PL65KRY2D3DR25UV","created_at":"2026-07-05T09:40:36Z"},{"alias_kind":"pith_short_8","alias_value":"PL65KRY2","created_at":"2026-07-05T09:40:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PL65KRY2D3DR25UVGBRCIQH6WY","target":"record","payload":{"canonical_record":{"source":{"id":"2308.13382","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-25T13:52:05Z","cross_cats_sorted":[],"title_canon_sha256":"1ebb71ecf79a0b5439730daa026ab7451885f3cf149d1332b77ae4ecf099f73d","abstract_canon_sha256":"d28322a4096481219625950ac123828b297fa4e5b0f6bb2a6b9660206aaed1c7"},"schema_version":"1.0"},"canonical_sha256":"7afdd5471a1ec71d769530622440feb635ba827e84ef7018362fc1b1a7c81ed6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:36.823167Z","signature_b64":"OsDVn54nG6Z+GtcO4CsY4nYgrji2b1Lf57N89dJeLJJQZmwRR7rnDb8U3D8M6OGNyqFrmfUs3roaAZAshdxkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7afdd5471a1ec71d769530622440feb635ba827e84ef7018362fc1b1a7c81ed6","last_reissued_at":"2026-07-05T09:40:36.822683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:36.822683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.13382","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":"2026-07-05T09:40:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NbAprzLSa9AAcenPLqF8/DAyygkHuYteSXIjVaf5PH5rqf09ku51l68XBtcwHI+ku6eSWqrVH+q2cMkC7tqODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:55:34.764146Z"},"content_sha256":"ebbf16ef3fc7ede058cefc56f46865d7b9b975346832b3fc0dd79c6b7c157ad9","schema_version":"1.0","event_id":"sha256:ebbf16ef3fc7ede058cefc56f46865d7b9b975346832b3fc0dd79c6b7c157ad9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PL65KRY2D3DR25UVGBRCIQH6WY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prompting Visual-Language Models for Dynamic Facial Expression Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ioannis Patras, Zengqun Zhao","submitted_at":"2023-08-25T13:52:05Z","abstract_excerpt":"This paper presents a novel visual-language model called DFER-CLIP, which is based on the CLIP model and designed for in-the-wild Dynamic Facial Expression Recognition (DFER). Specifically, the proposed DFER-CLIP consists of a visual part and a textual part. For the visual part, based on the CLIP image encoder, a temporal model consisting of several Transformer encoders is introduced for extracting temporal facial expression features, and the final feature embedding is obtained as a learnable \"class\" token. For the textual part, we use as inputs textual descriptions of the facial behaviour tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13382","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/2308.13382/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":"2026-07-05T09:40:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Df10of0N7f2IkD8tCmQmbYTE405dEbF6zBrgYQHutCDCrVSMejqutyM5EN6cMs2CeFkGjdXgR3vsiuMOUxcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:55:34.765060Z"},"content_sha256":"e5dbc3be9b9d3e924fd0c19ad7629442ec84fc17966be58806c3dbef17f5bf0c","schema_version":"1.0","event_id":"sha256:e5dbc3be9b9d3e924fd0c19ad7629442ec84fc17966be58806c3dbef17f5bf0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PL65KRY2D3DR25UVGBRCIQH6WY/bundle.json","state_url":"https://pith.science/pith/PL65KRY2D3DR25UVGBRCIQH6WY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PL65KRY2D3DR25UVGBRCIQH6WY/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":"2026-08-08T20:55:34Z","links":{"resolver":"https://pith.science/pith/PL65KRY2D3DR25UVGBRCIQH6WY","bundle":"https://pith.science/pith/PL65KRY2D3DR25UVGBRCIQH6WY/bundle.json","state":"https://pith.science/pith/PL65KRY2D3DR25UVGBRCIQH6WY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PL65KRY2D3DR25UVGBRCIQH6WY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PL65KRY2D3DR25UVGBRCIQH6WY","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":"d28322a4096481219625950ac123828b297fa4e5b0f6bb2a6b9660206aaed1c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-25T13:52:05Z","title_canon_sha256":"1ebb71ecf79a0b5439730daa026ab7451885f3cf149d1332b77ae4ecf099f73d"},"schema_version":"1.0","source":{"id":"2308.13382","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13382","created_at":"2026-07-05T09:40:36Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13382v3","created_at":"2026-07-05T09:40:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13382","created_at":"2026-07-05T09:40:36Z"},{"alias_kind":"pith_short_12","alias_value":"PL65KRY2D3DR","created_at":"2026-07-05T09:40:36Z"},{"alias_kind":"pith_short_16","alias_value":"PL65KRY2D3DR25UV","created_at":"2026-07-05T09:40:36Z"},{"alias_kind":"pith_short_8","alias_value":"PL65KRY2","created_at":"2026-07-05T09:40:36Z"}],"graph_snapshots":[{"event_id":"sha256:e5dbc3be9b9d3e924fd0c19ad7629442ec84fc17966be58806c3dbef17f5bf0c","target":"graph","created_at":"2026-07-05T09:40:36Z","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/2308.13382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a novel visual-language model called DFER-CLIP, which is based on the CLIP model and designed for in-the-wild Dynamic Facial Expression Recognition (DFER). Specifically, the proposed DFER-CLIP consists of a visual part and a textual part. For the visual part, based on the CLIP image encoder, a temporal model consisting of several Transformer encoders is introduced for extracting temporal facial expression features, and the final feature embedding is obtained as a learnable \"class\" token. For the textual part, we use as inputs textual descriptions of the facial behaviour tha","authors_text":"Ioannis Patras, Zengqun Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-25T13:52:05Z","title":"Prompting Visual-Language Models for Dynamic Facial Expression Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13382","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:ebbf16ef3fc7ede058cefc56f46865d7b9b975346832b3fc0dd79c6b7c157ad9","target":"record","created_at":"2026-07-05T09:40:36Z","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":"d28322a4096481219625950ac123828b297fa4e5b0f6bb2a6b9660206aaed1c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-25T13:52:05Z","title_canon_sha256":"1ebb71ecf79a0b5439730daa026ab7451885f3cf149d1332b77ae4ecf099f73d"},"schema_version":"1.0","source":{"id":"2308.13382","kind":"arxiv","version":3}},"canonical_sha256":"7afdd5471a1ec71d769530622440feb635ba827e84ef7018362fc1b1a7c81ed6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7afdd5471a1ec71d769530622440feb635ba827e84ef7018362fc1b1a7c81ed6","first_computed_at":"2026-07-05T09:40:36.822683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:36.822683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OsDVn54nG6Z+GtcO4CsY4nYgrji2b1Lf57N89dJeLJJQZmwRR7rnDb8U3D8M6OGNyqFrmfUs3roaAZAshdxkAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:36.823167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.13382","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebbf16ef3fc7ede058cefc56f46865d7b9b975346832b3fc0dd79c6b7c157ad9","sha256:e5dbc3be9b9d3e924fd0c19ad7629442ec84fc17966be58806c3dbef17f5bf0c"],"state_sha256":"a2cef77c179285b3355655213b0a5b4c24d9b810819b8ca13ff5f935d5d57cba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aKsSR4WX7X7GmdIPSevy3wUPqz356j/3oRf0mLa6rNyBw90up8Ay4XqpYUKwM9r/tlTxmEtWBR1vge9ajHGuDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:55:34.770340Z","bundle_sha256":"51cda14f42cb4fe4c45dae4ac4e1a6801eefc73f8ed8047e9a1da9ce702bcd22"}}