{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BPGOVHPH6CCNAUZTB3P6SH53AS","short_pith_number":"pith:BPGOVHPH","canonical_record":{"source":{"id":"2412.08614","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T18:37:42Z","cross_cats_sorted":[],"title_canon_sha256":"2b8398c5bb93a5eef1fb4dffb8cc07c38266bfd5f53993fa983cbf2c23cc6de4","abstract_canon_sha256":"bec190ff8387bdce70b14dfafc474bb60e75ea6103faf749470774fd57fdff87"},"schema_version":"1.0"},"canonical_sha256":"0bccea9de7f084d053330edfe91fbb0491316fb0f3cf1b100576f5302859a283","source":{"kind":"arxiv","id":"2412.08614","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08614","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08614v3","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08614","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"pith_short_12","alias_value":"BPGOVHPH6CCN","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"pith_short_16","alias_value":"BPGOVHPH6CCNAUZT","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"pith_short_8","alias_value":"BPGOVHPH","created_at":"2026-07-05T10:39:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BPGOVHPH6CCNAUZTB3P6SH53AS","target":"record","payload":{"canonical_record":{"source":{"id":"2412.08614","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T18:37:42Z","cross_cats_sorted":[],"title_canon_sha256":"2b8398c5bb93a5eef1fb4dffb8cc07c38266bfd5f53993fa983cbf2c23cc6de4","abstract_canon_sha256":"bec190ff8387bdce70b14dfafc474bb60e75ea6103faf749470774fd57fdff87"},"schema_version":"1.0"},"canonical_sha256":"0bccea9de7f084d053330edfe91fbb0491316fb0f3cf1b100576f5302859a283","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:24.427183Z","signature_b64":"ZYvlrfSCluKTdC7Qp6iWZcq4RvAyPY3UJNX6kGjrILFnjxUcgZafW/eCm3R2CpxsP7+eBvUX8Y1l5cmBI7YTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bccea9de7f084d053330edfe91fbb0491316fb0f3cf1b100576f5302859a283","last_reissued_at":"2026-07-05T10:39:24.426683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:24.426683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.08614","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":"2026-07-05T10:39:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F+dqNJSVeo5ctTbOxpIw5ApWNX3gx0D0/e7reVRVFWe6NHtTxkckEJ/eJOPpVJ8sLux9ERpfiNzkiep45wQQDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:47:31.460426Z"},"content_sha256":"ba9adf86c44e31e6fb0b2f9f5c9139cf947bd2992982a195a60a67941b9493ee","schema_version":"1.0","event_id":"sha256:ba9adf86c44e31e6fb0b2f9f5c9139cf947bd2992982a195a60a67941b9493ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BPGOVHPH6CCNAUZTB3P6SH53AS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Gong, Fan Lu, Jiawei Liu, Kecheng Zheng, Shuailei Ma, Wei Wu, Wei Zhai, Yang Cao, Yujun Shen, Zheng-Jun Zha","submitted_at":"2024-12-11T18:37:42Z","abstract_excerpt":"Generating detailed captions comprehending text-rich visual content in images has received growing attention for Large Vision-Language Models (LVLMs). However, few studies have developed benchmarks specifically tailored for detailed captions to measure their accuracy and comprehensiveness. In this paper, we introduce a detailed caption benchmark, termed as CompreCap, to evaluate the visual context from a directed scene graph view. Concretely, we first manually segment the image into semantically meaningful regions (i.e., semantic segmentation mask) according to common-object vocabulary, while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08614","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/2412.08614/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":"2026-07-05T10:39:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"La+7kn4LEeT6zlQCCnIvmqg2NhgK3NbSN8o18il4DpNV+2wlmZ+8Ggg80MEGMyOCmFsPzsEMO047JGBb18MVBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:47:31.461347Z"},"content_sha256":"798575b77e8e84daef39248a05d18bc1f6ad89d915e7f429b78f7142aac1d639","schema_version":"1.0","event_id":"sha256:798575b77e8e84daef39248a05d18bc1f6ad89d915e7f429b78f7142aac1d639"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BPGOVHPH6CCNAUZTB3P6SH53AS/bundle.json","state_url":"https://pith.science/pith/BPGOVHPH6CCNAUZTB3P6SH53AS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BPGOVHPH6CCNAUZTB3P6SH53AS/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":"2026-08-08T19:47:31Z","links":{"resolver":"https://pith.science/pith/BPGOVHPH6CCNAUZTB3P6SH53AS","bundle":"https://pith.science/pith/BPGOVHPH6CCNAUZTB3P6SH53AS/bundle.json","state":"https://pith.science/pith/BPGOVHPH6CCNAUZTB3P6SH53AS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BPGOVHPH6CCNAUZTB3P6SH53AS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BPGOVHPH6CCNAUZTB3P6SH53AS","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":"bec190ff8387bdce70b14dfafc474bb60e75ea6103faf749470774fd57fdff87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T18:37:42Z","title_canon_sha256":"2b8398c5bb93a5eef1fb4dffb8cc07c38266bfd5f53993fa983cbf2c23cc6de4"},"schema_version":"1.0","source":{"id":"2412.08614","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08614","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08614v3","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08614","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"pith_short_12","alias_value":"BPGOVHPH6CCN","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"pith_short_16","alias_value":"BPGOVHPH6CCNAUZT","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"pith_short_8","alias_value":"BPGOVHPH","created_at":"2026-07-05T10:39:24Z"}],"graph_snapshots":[{"event_id":"sha256:798575b77e8e84daef39248a05d18bc1f6ad89d915e7f429b78f7142aac1d639","target":"graph","created_at":"2026-07-05T10:39:24Z","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/2412.08614/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating detailed captions comprehending text-rich visual content in images has received growing attention for Large Vision-Language Models (LVLMs). However, few studies have developed benchmarks specifically tailored for detailed captions to measure their accuracy and comprehensiveness. In this paper, we introduce a detailed caption benchmark, termed as CompreCap, to evaluate the visual context from a directed scene graph view. Concretely, we first manually segment the image into semantically meaningful regions (i.e., semantic segmentation mask) according to common-object vocabulary, while ","authors_text":"Biao Gong, Fan Lu, Jiawei Liu, Kecheng Zheng, Shuailei Ma, Wei Wu, Wei Zhai, Yang Cao, Yujun Shen, Zheng-Jun Zha","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T18:37:42Z","title":"Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08614","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:ba9adf86c44e31e6fb0b2f9f5c9139cf947bd2992982a195a60a67941b9493ee","target":"record","created_at":"2026-07-05T10:39:24Z","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":"bec190ff8387bdce70b14dfafc474bb60e75ea6103faf749470774fd57fdff87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T18:37:42Z","title_canon_sha256":"2b8398c5bb93a5eef1fb4dffb8cc07c38266bfd5f53993fa983cbf2c23cc6de4"},"schema_version":"1.0","source":{"id":"2412.08614","kind":"arxiv","version":3}},"canonical_sha256":"0bccea9de7f084d053330edfe91fbb0491316fb0f3cf1b100576f5302859a283","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bccea9de7f084d053330edfe91fbb0491316fb0f3cf1b100576f5302859a283","first_computed_at":"2026-07-05T10:39:24.426683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:24.426683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZYvlrfSCluKTdC7Qp6iWZcq4RvAyPY3UJNX6kGjrILFnjxUcgZafW/eCm3R2CpxsP7+eBvUX8Y1l5cmBI7YTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:24.427183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08614","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba9adf86c44e31e6fb0b2f9f5c9139cf947bd2992982a195a60a67941b9493ee","sha256:798575b77e8e84daef39248a05d18bc1f6ad89d915e7f429b78f7142aac1d639"],"state_sha256":"0ec54783518018fd0c9ca43265a9cb29787233ff3660109f7dd12165b0529eb8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Qf8t7Z3rMTs+LTm7yU1zib9e4SEBb3EsVZElcXOwtUghzxJLmuPZ7YTWeTOGoMpp8aRF0awbfOHrj/Mnp/NDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:47:31.467989Z","bundle_sha256":"78e1a02c3fe577096b39cb14b49bebbeebbb29373fd802b8b18ff9e1ac40ea56"}}