{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CDV5YM6SNNXTJ2QNC7RCV662BG","short_pith_number":"pith:CDV5YM6S","canonical_record":{"source":{"id":"2410.06777","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T11:14:07Z","cross_cats_sorted":[],"title_canon_sha256":"de435feecc08c3fa98ad406bd5ec5076b8bbf72cbad0cb1864a4d25e0b97f5c5","abstract_canon_sha256":"0a686946893a12c8eaae502acea0f96cee67bf892475ca9ed920919b306cc7b4"},"schema_version":"1.0"},"canonical_sha256":"10ebdc33d26b6f34ea0d17e22afbda098554f79db44bba62f8ab2a63d6458fc2","source":{"kind":"arxiv","id":"2410.06777","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06777","created_at":"2026-07-05T09:18:06Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06777v1","created_at":"2026-07-05T09:18:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06777","created_at":"2026-07-05T09:18:06Z"},{"alias_kind":"pith_short_12","alias_value":"CDV5YM6SNNXT","created_at":"2026-07-05T09:18:06Z"},{"alias_kind":"pith_short_16","alias_value":"CDV5YM6SNNXTJ2QN","created_at":"2026-07-05T09:18:06Z"},{"alias_kind":"pith_short_8","alias_value":"CDV5YM6S","created_at":"2026-07-05T09:18:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CDV5YM6SNNXTJ2QNC7RCV662BG","target":"record","payload":{"canonical_record":{"source":{"id":"2410.06777","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T11:14:07Z","cross_cats_sorted":[],"title_canon_sha256":"de435feecc08c3fa98ad406bd5ec5076b8bbf72cbad0cb1864a4d25e0b97f5c5","abstract_canon_sha256":"0a686946893a12c8eaae502acea0f96cee67bf892475ca9ed920919b306cc7b4"},"schema_version":"1.0"},"canonical_sha256":"10ebdc33d26b6f34ea0d17e22afbda098554f79db44bba62f8ab2a63d6458fc2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:06.851029Z","signature_b64":"lYeCaXpcUmwwgXlLVSBRF6ljN+bgj2Ip9nD9LGpC6kr7F24syHPQE/+TKVXnjKXyWuvI212yVJ4PKeipAwxtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10ebdc33d26b6f34ea0d17e22afbda098554f79db44bba62f8ab2a63d6458fc2","last_reissued_at":"2026-07-05T09:18:06.850561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:06.850561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.06777","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:18:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KujLUTcZ52UOXHAZoCLQ0k2+Th/XAgnhOYfutj19Cjtbs8q4xmexPQD1tirCkPfGbgW0JLlywcdVQL5Th8SlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:30:10.570731Z"},"content_sha256":"15d61bd164cad12bcbe8f350f81ef25b1b64485fec8d7c8c417ece56ef7f2f2a","schema_version":"1.0","event_id":"sha256:15d61bd164cad12bcbe8f350f81ef25b1b64485fec8d7c8c417ece56ef7f2f2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CDV5YM6SNNXTJ2QNC7RCV662BG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Chang, Hongze Shen, Jiahe Zhao, Keliang Li, Ruibing Hou, Shiguang Shan, Xilin Chen, Zaifei Yang","submitted_at":"2024-10-09T11:14:07Z","abstract_excerpt":"The significant advancements in visual understanding and instruction following from Multimodal Large Language Models (MLLMs) have opened up more possibilities for broader applications in diverse and universal human-centric scenarios. However, existing image-text data may not support the precise modality alignment and integration of multi-grained information, which is crucial for human-centric visual understanding. In this paper, we introduce HERM-Bench, a benchmark for evaluating the human-centric understanding capabilities of MLLMs. Our work reveals the limitations of existing MLLMs in unders"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06777","kind":"arxiv","version":1},"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/2410.06777/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":"2026-07-05T09:18:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Tpqn79KDFk24+mAzwzmrEPUVL+xGj7likfM/sKYPgAjVtPNTZdWVTsgTQ5YZqQ75HAv2Clzyb62AcLEITojAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:30:10.571218Z"},"content_sha256":"9aaa04f056aa42240e51d925a17a2d64d80e3cecf1692120a8e954542e6199b5","schema_version":"1.0","event_id":"sha256:9aaa04f056aa42240e51d925a17a2d64d80e3cecf1692120a8e954542e6199b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CDV5YM6SNNXTJ2QNC7RCV662BG/bundle.json","state_url":"https://pith.science/pith/CDV5YM6SNNXTJ2QNC7RCV662BG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CDV5YM6SNNXTJ2QNC7RCV662BG/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":"2026-08-18T06:30:10Z","links":{"resolver":"https://pith.science/pith/CDV5YM6SNNXTJ2QNC7RCV662BG","bundle":"https://pith.science/pith/CDV5YM6SNNXTJ2QNC7RCV662BG/bundle.json","state":"https://pith.science/pith/CDV5YM6SNNXTJ2QNC7RCV662BG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CDV5YM6SNNXTJ2QNC7RCV662BG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CDV5YM6SNNXTJ2QNC7RCV662BG","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":"0a686946893a12c8eaae502acea0f96cee67bf892475ca9ed920919b306cc7b4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T11:14:07Z","title_canon_sha256":"de435feecc08c3fa98ad406bd5ec5076b8bbf72cbad0cb1864a4d25e0b97f5c5"},"schema_version":"1.0","source":{"id":"2410.06777","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06777","created_at":"2026-07-05T09:18:06Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06777v1","created_at":"2026-07-05T09:18:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06777","created_at":"2026-07-05T09:18:06Z"},{"alias_kind":"pith_short_12","alias_value":"CDV5YM6SNNXT","created_at":"2026-07-05T09:18:06Z"},{"alias_kind":"pith_short_16","alias_value":"CDV5YM6SNNXTJ2QN","created_at":"2026-07-05T09:18:06Z"},{"alias_kind":"pith_short_8","alias_value":"CDV5YM6S","created_at":"2026-07-05T09:18:06Z"}],"graph_snapshots":[{"event_id":"sha256:9aaa04f056aa42240e51d925a17a2d64d80e3cecf1692120a8e954542e6199b5","target":"graph","created_at":"2026-07-05T09:18:06Z","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/2410.06777/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The significant advancements in visual understanding and instruction following from Multimodal Large Language Models (MLLMs) have opened up more possibilities for broader applications in diverse and universal human-centric scenarios. However, existing image-text data may not support the precise modality alignment and integration of multi-grained information, which is crucial for human-centric visual understanding. In this paper, we introduce HERM-Bench, a benchmark for evaluating the human-centric understanding capabilities of MLLMs. Our work reveals the limitations of existing MLLMs in unders","authors_text":"Hong Chang, Hongze Shen, Jiahe Zhao, Keliang Li, Ruibing Hou, Shiguang Shan, Xilin Chen, Zaifei Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T11:14:07Z","title":"HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06777","kind":"arxiv","version":1},"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":"sha256:15d61bd164cad12bcbe8f350f81ef25b1b64485fec8d7c8c417ece56ef7f2f2a","target":"record","created_at":"2026-07-05T09:18:06Z","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":"0a686946893a12c8eaae502acea0f96cee67bf892475ca9ed920919b306cc7b4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T11:14:07Z","title_canon_sha256":"de435feecc08c3fa98ad406bd5ec5076b8bbf72cbad0cb1864a4d25e0b97f5c5"},"schema_version":"1.0","source":{"id":"2410.06777","kind":"arxiv","version":1}},"canonical_sha256":"10ebdc33d26b6f34ea0d17e22afbda098554f79db44bba62f8ab2a63d6458fc2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10ebdc33d26b6f34ea0d17e22afbda098554f79db44bba62f8ab2a63d6458fc2","first_computed_at":"2026-07-05T09:18:06.850561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:06.850561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lYeCaXpcUmwwgXlLVSBRF6ljN+bgj2Ip9nD9LGpC6kr7F24syHPQE/+TKVXnjKXyWuvI212yVJ4PKeipAwxtCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:06.851029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06777","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15d61bd164cad12bcbe8f350f81ef25b1b64485fec8d7c8c417ece56ef7f2f2a","sha256:9aaa04f056aa42240e51d925a17a2d64d80e3cecf1692120a8e954542e6199b5"],"state_sha256":"73e989ad8d7f2eb1d3c15f057c632195056cedf36e3fd593b79dc903e5062e8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wrCkF0YgwrbciCXl6RhfA663Cmwa6jRCMQEIFi80PcA7ufjAlT9qqS11I4GdVA1h4OcbshHrSsJuSSalMiA5Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T06:30:10.575826Z","bundle_sha256":"0efb40c3ddfd7e352a7bdca737047cdca7e7daa790f0c6055428fd06b0d2cb82"}}