{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QAKSDVE7IDVUUCJWZICQEGYTJ2","short_pith_number":"pith:QAKSDVE7","canonical_record":{"source":{"id":"2405.08992","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-14T23:24:12Z","cross_cats_sorted":[],"title_canon_sha256":"8912e5b813554505b958aae90ff2ecb7809c26adbe50c4503b4a5b60e686f9dd","abstract_canon_sha256":"2094c332e9b3b6368a21a5aaf89d183a0b6e9a60f7890e92d2ff5673b07be6a2"},"schema_version":"1.0"},"canonical_sha256":"801521d49f40eb4a0936ca05021b134e819763f641a15805507f00126c064cf0","source":{"kind":"arxiv","id":"2405.08992","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.08992","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.08992v2","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08992","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_12","alias_value":"QAKSDVE7IDVU","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_16","alias_value":"QAKSDVE7IDVUUCJW","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_8","alias_value":"QAKSDVE7","created_at":"2026-07-05T10:07:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QAKSDVE7IDVUUCJWZICQEGYTJ2","target":"record","payload":{"canonical_record":{"source":{"id":"2405.08992","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-14T23:24:12Z","cross_cats_sorted":[],"title_canon_sha256":"8912e5b813554505b958aae90ff2ecb7809c26adbe50c4503b4a5b60e686f9dd","abstract_canon_sha256":"2094c332e9b3b6368a21a5aaf89d183a0b6e9a60f7890e92d2ff5673b07be6a2"},"schema_version":"1.0"},"canonical_sha256":"801521d49f40eb4a0936ca05021b134e819763f641a15805507f00126c064cf0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:41.361969Z","signature_b64":"hU/TZxG8UsmHIe8VPV5va7F2/9PEgF8foZiXk1IWwqS+c5VNwyAzufkWGcpfEx15HB0x9Or0gn0HmMaqVSHgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"801521d49f40eb4a0936ca05021b134e819763f641a15805507f00126c064cf0","last_reissued_at":"2026-07-05T10:07:41.361478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:41.361478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.08992","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":"2026-07-05T10:07:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aIDjSTYt4oeI8Y3fUtnSg/andl6XKpDoYLASdhmbXof5yKoadJM04epfWTYM5rigVqtqa98IiYtp9ags1Tt5Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:12:34.375966Z"},"content_sha256":"d47a73bd3c24d43e95c240e4efd0366f52650b9af86d4ccfd6cb42ca891f49ff","schema_version":"1.0","event_id":"sha256:d47a73bd3c24d43e95c240e4efd0366f52650b9af86d4ccfd6cb42ca891f49ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QAKSDVE7IDVUUCJWZICQEGYTJ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contextual Emotion Recognition using Large Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angelica Lim, Chuxuan Zhang, \\\"Ozge Nilay Yal\\c{c}{\\i}n, Yasaman Etesam","submitted_at":"2024-05-14T23:24:12Z","abstract_excerpt":"\"How does the person in the bounding box feel?\" Achieving human-level recognition of the apparent emotion of a person in real world situations remains an unsolved task in computer vision. Facial expressions are not enough: body pose, contextual knowledge, and commonsense reasoning all contribute to how humans perform this emotional theory of mind task. In this paper, we examine two major approaches enabled by recent large vision language models: 1) image captioning followed by a language-only LLM, and 2) vision language models, under zero-shot and fine-tuned setups. We evaluate the methods on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08992","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/2405.08992/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":"2026-07-05T10:07:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pvUU5GYV/DuZLa3goTVcsbu8RSpvzbc0U0EWuXyp6IscKyhBKU4amEocodVB+3RC8fH7vAtf3AXDidOsaJI8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:12:34.377309Z"},"content_sha256":"24b76cf5da82defbe1b870b6060e91cc997a6230608ec7c5beea6b69d6898d19","schema_version":"1.0","event_id":"sha256:24b76cf5da82defbe1b870b6060e91cc997a6230608ec7c5beea6b69d6898d19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QAKSDVE7IDVUUCJWZICQEGYTJ2/bundle.json","state_url":"https://pith.science/pith/QAKSDVE7IDVUUCJWZICQEGYTJ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QAKSDVE7IDVUUCJWZICQEGYTJ2/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":"2026-08-17T22:12:34Z","links":{"resolver":"https://pith.science/pith/QAKSDVE7IDVUUCJWZICQEGYTJ2","bundle":"https://pith.science/pith/QAKSDVE7IDVUUCJWZICQEGYTJ2/bundle.json","state":"https://pith.science/pith/QAKSDVE7IDVUUCJWZICQEGYTJ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QAKSDVE7IDVUUCJWZICQEGYTJ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QAKSDVE7IDVUUCJWZICQEGYTJ2","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":"2094c332e9b3b6368a21a5aaf89d183a0b6e9a60f7890e92d2ff5673b07be6a2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-14T23:24:12Z","title_canon_sha256":"8912e5b813554505b958aae90ff2ecb7809c26adbe50c4503b4a5b60e686f9dd"},"schema_version":"1.0","source":{"id":"2405.08992","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.08992","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.08992v2","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08992","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_12","alias_value":"QAKSDVE7IDVU","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_16","alias_value":"QAKSDVE7IDVUUCJW","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_8","alias_value":"QAKSDVE7","created_at":"2026-07-05T10:07:41Z"}],"graph_snapshots":[{"event_id":"sha256:24b76cf5da82defbe1b870b6060e91cc997a6230608ec7c5beea6b69d6898d19","target":"graph","created_at":"2026-07-05T10:07:41Z","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/2405.08992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"\"How does the person in the bounding box feel?\" Achieving human-level recognition of the apparent emotion of a person in real world situations remains an unsolved task in computer vision. Facial expressions are not enough: body pose, contextual knowledge, and commonsense reasoning all contribute to how humans perform this emotional theory of mind task. In this paper, we examine two major approaches enabled by recent large vision language models: 1) image captioning followed by a language-only LLM, and 2) vision language models, under zero-shot and fine-tuned setups. We evaluate the methods on ","authors_text":"Angelica Lim, Chuxuan Zhang, \\\"Ozge Nilay Yal\\c{c}{\\i}n, Yasaman Etesam","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-14T23:24:12Z","title":"Contextual Emotion Recognition using Large Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08992","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:d47a73bd3c24d43e95c240e4efd0366f52650b9af86d4ccfd6cb42ca891f49ff","target":"record","created_at":"2026-07-05T10:07:41Z","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":"2094c332e9b3b6368a21a5aaf89d183a0b6e9a60f7890e92d2ff5673b07be6a2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-14T23:24:12Z","title_canon_sha256":"8912e5b813554505b958aae90ff2ecb7809c26adbe50c4503b4a5b60e686f9dd"},"schema_version":"1.0","source":{"id":"2405.08992","kind":"arxiv","version":2}},"canonical_sha256":"801521d49f40eb4a0936ca05021b134e819763f641a15805507f00126c064cf0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"801521d49f40eb4a0936ca05021b134e819763f641a15805507f00126c064cf0","first_computed_at":"2026-07-05T10:07:41.361478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:41.361478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hU/TZxG8UsmHIe8VPV5va7F2/9PEgF8foZiXk1IWwqS+c5VNwyAzufkWGcpfEx15HB0x9Or0gn0HmMaqVSHgDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:41.361969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.08992","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d47a73bd3c24d43e95c240e4efd0366f52650b9af86d4ccfd6cb42ca891f49ff","sha256:24b76cf5da82defbe1b870b6060e91cc997a6230608ec7c5beea6b69d6898d19"],"state_sha256":"61fc37eac4c32b92e297f6a8cef79a7f4066a377a0ef25418653a73a958578be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qOc1Vff1wSsa7+/eHJM375Pxq6QV8snfrRhp3I22OTniPB4Ok2LCEkgmvCuzZvOesUgiFYW11eLBEmX1f72BDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T22:12:34.387202Z","bundle_sha256":"2f23127a946b66c27a6c67c6c45f8a38e4d10c456a89709128e7d8842d496327"}}