{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:R22TTCKVK47S5JA66YSJR3RP2A","short_pith_number":"pith:R22TTCKV","canonical_record":{"source":{"id":"2505.06685","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-10T16:15:26Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d3314c8d88063b65179345f16d73779b48c1dd1526daba6e2f07bc8cf0f4e600","abstract_canon_sha256":"c244c185ab341faec0405dca4912f6dca52afcfe8aa10084acf547aae136e8cb"},"schema_version":"1.0"},"canonical_sha256":"8eb5398955573f2ea41ef62498ee2fd02cf6361360e99dd2fbf22b8a216dc2a9","source":{"kind":"arxiv","id":"2505.06685","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06685","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06685v3","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06685","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"pith_short_12","alias_value":"R22TTCKVK47S","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"pith_short_16","alias_value":"R22TTCKVK47S5JA6","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"pith_short_8","alias_value":"R22TTCKV","created_at":"2026-07-05T11:53:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:R22TTCKVK47S5JA66YSJR3RP2A","target":"record","payload":{"canonical_record":{"source":{"id":"2505.06685","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-10T16:15:26Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d3314c8d88063b65179345f16d73779b48c1dd1526daba6e2f07bc8cf0f4e600","abstract_canon_sha256":"c244c185ab341faec0405dca4912f6dca52afcfe8aa10084acf547aae136e8cb"},"schema_version":"1.0"},"canonical_sha256":"8eb5398955573f2ea41ef62498ee2fd02cf6361360e99dd2fbf22b8a216dc2a9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:02.836535Z","signature_b64":"yNU5BppBlRKDqkYaCn1d3V1UGafusSDxoiuM/LYnZzOj4aM+Z5feyfQNItZ7Fs3Au3DWxYZTPhIpw184D8+DAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8eb5398955573f2ea41ef62498ee2fd02cf6361360e99dd2fbf22b8a216dc2a9","last_reissued_at":"2026-07-05T11:53:02.836073Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:02.836073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.06685","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":"2026-07-05T11:53:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PYZsfcBzrEaV7YuSmoxyarbiXar5U/nh+r08Lpmm4B6gKRpM/iwZK4gc0wnXW/CWtBAsbQZlkCt9ENH061ShAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T03:05:32.888396Z"},"content_sha256":"589e30a89b95b6762f56943a90a730603e576598af1c24a4dd31b8eea16ce391","schema_version":"1.0","event_id":"sha256:589e30a89b95b6762f56943a90a730603e576598af1c24a4dd31b8eea16ce391"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:R22TTCKVK47S5JA66YSJR3RP2A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Emotion-Qwen: A Unified Framework for Emotion and Vision Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.MM","authors_text":"Bin Li, Chuan Yan, Dawei Huang, Qing Li, Xiang Li, Xiaohui Wang, Xiaojiang Peng, Yurong Huang, Zebang Cheng, Zheng Lian, Zhi-Qi Cheng, Zihao Han","submitted_at":"2025-05-10T16:15:26Z","abstract_excerpt":"Accurate emotion understanding in videos necessitates effectively recognizing and interpreting emotional states by integrating visual, textual, auditory, and contextual cues. Although recent Large Multimodal Models (LMMs) have exhibited significant progress in general vision-language (VL) tasks, their performance often deteriorates in emotion-specific scenarios, exhibiting catastrophic forgetting when fine-tuned on emotion-centric tasks. To overcome these limitations, we propose Emotion-Qwen, a unified multimodal framework designed to simultaneously enable robust emotion understanding and pres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06685","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/2505.06685/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":"2026-07-05T11:53:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i1dns++SWbxGKYbY88+Ni4ony5DNtghzybI3iItjb3EZSgTcSTSCRKcEKhUS0l/n1QpjUtzAIxCjHveFTok/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T03:05:32.889291Z"},"content_sha256":"a7789d8e6c34e5265a0c1b4302cb8016974d9d93aafa98eaeb3baa034cd6060d","schema_version":"1.0","event_id":"sha256:a7789d8e6c34e5265a0c1b4302cb8016974d9d93aafa98eaeb3baa034cd6060d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R22TTCKVK47S5JA66YSJR3RP2A/bundle.json","state_url":"https://pith.science/pith/R22TTCKVK47S5JA66YSJR3RP2A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R22TTCKVK47S5JA66YSJR3RP2A/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":"2026-08-14T03:05:32Z","links":{"resolver":"https://pith.science/pith/R22TTCKVK47S5JA66YSJR3RP2A","bundle":"https://pith.science/pith/R22TTCKVK47S5JA66YSJR3RP2A/bundle.json","state":"https://pith.science/pith/R22TTCKVK47S5JA66YSJR3RP2A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R22TTCKVK47S5JA66YSJR3RP2A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R22TTCKVK47S5JA66YSJR3RP2A","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":"c244c185ab341faec0405dca4912f6dca52afcfe8aa10084acf547aae136e8cb","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-10T16:15:26Z","title_canon_sha256":"d3314c8d88063b65179345f16d73779b48c1dd1526daba6e2f07bc8cf0f4e600"},"schema_version":"1.0","source":{"id":"2505.06685","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06685","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06685v3","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06685","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"pith_short_12","alias_value":"R22TTCKVK47S","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"pith_short_16","alias_value":"R22TTCKVK47S5JA6","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"pith_short_8","alias_value":"R22TTCKV","created_at":"2026-07-05T11:53:02Z"}],"graph_snapshots":[{"event_id":"sha256:a7789d8e6c34e5265a0c1b4302cb8016974d9d93aafa98eaeb3baa034cd6060d","target":"graph","created_at":"2026-07-05T11:53:02Z","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/2505.06685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate emotion understanding in videos necessitates effectively recognizing and interpreting emotional states by integrating visual, textual, auditory, and contextual cues. Although recent Large Multimodal Models (LMMs) have exhibited significant progress in general vision-language (VL) tasks, their performance often deteriorates in emotion-specific scenarios, exhibiting catastrophic forgetting when fine-tuned on emotion-centric tasks. To overcome these limitations, we propose Emotion-Qwen, a unified multimodal framework designed to simultaneously enable robust emotion understanding and pres","authors_text":"Bin Li, Chuan Yan, Dawei Huang, Qing Li, Xiang Li, Xiaohui Wang, Xiaojiang Peng, Yurong Huang, Zebang Cheng, Zheng Lian, Zhi-Qi Cheng, Zihao Han","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-10T16:15:26Z","title":"Emotion-Qwen: A Unified Framework for Emotion and Vision Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06685","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":"sha256:589e30a89b95b6762f56943a90a730603e576598af1c24a4dd31b8eea16ce391","target":"record","created_at":"2026-07-05T11:53:02Z","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":"c244c185ab341faec0405dca4912f6dca52afcfe8aa10084acf547aae136e8cb","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-10T16:15:26Z","title_canon_sha256":"d3314c8d88063b65179345f16d73779b48c1dd1526daba6e2f07bc8cf0f4e600"},"schema_version":"1.0","source":{"id":"2505.06685","kind":"arxiv","version":3}},"canonical_sha256":"8eb5398955573f2ea41ef62498ee2fd02cf6361360e99dd2fbf22b8a216dc2a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8eb5398955573f2ea41ef62498ee2fd02cf6361360e99dd2fbf22b8a216dc2a9","first_computed_at":"2026-07-05T11:53:02.836073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:02.836073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yNU5BppBlRKDqkYaCn1d3V1UGafusSDxoiuM/LYnZzOj4aM+Z5feyfQNItZ7Fs3Au3DWxYZTPhIpw184D8+DAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:02.836535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06685","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:589e30a89b95b6762f56943a90a730603e576598af1c24a4dd31b8eea16ce391","sha256:a7789d8e6c34e5265a0c1b4302cb8016974d9d93aafa98eaeb3baa034cd6060d"],"state_sha256":"c9168e6cfb1163cf1f614fc93347ab0a3864c39265da6aa0fe3b9f698f7e6a9d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YQJ1MPvN8FSkwKbtzqESmgyPfPKShRQw0opfwTbnDX9zlwCIeT3GVlqXWD78j7qeysxhc66nEXlEgiBRrp0YBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T03:05:32.969574Z","bundle_sha256":"0200e2f9abc0890659eda0bb5eb19b79978fdadd10b013cf24f85ad9f35eaf71"}}