{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MMP3D26XU7ODK6HGXTX6QCNMXU","short_pith_number":"pith:MMP3D26X","canonical_record":{"source":{"id":"2508.16974","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-23T09:57:52Z","cross_cats_sorted":[],"title_canon_sha256":"a6c938f49a0f075ac5ca7f0b324874b6e1b925a67aa2071b6de0975a72edae94","abstract_canon_sha256":"83a473363c2ec8dcfead6a5bec29034ecde835ba8b66f057da2e30c04dca438c"},"schema_version":"1.0"},"canonical_sha256":"631fb1ebd7a7dc3578e6bcefe809acbd2df0ef9c34c98dd0af6c19c96cf1c271","source":{"kind":"arxiv","id":"2508.16974","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.16974","created_at":"2026-07-05T11:58:07Z"},{"alias_kind":"arxiv_version","alias_value":"2508.16974v1","created_at":"2026-07-05T11:58:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16974","created_at":"2026-07-05T11:58:07Z"},{"alias_kind":"pith_short_12","alias_value":"MMP3D26XU7OD","created_at":"2026-07-05T11:58:07Z"},{"alias_kind":"pith_short_16","alias_value":"MMP3D26XU7ODK6HG","created_at":"2026-07-05T11:58:07Z"},{"alias_kind":"pith_short_8","alias_value":"MMP3D26X","created_at":"2026-07-05T11:58:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MMP3D26XU7ODK6HGXTX6QCNMXU","target":"record","payload":{"canonical_record":{"source":{"id":"2508.16974","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-23T09:57:52Z","cross_cats_sorted":[],"title_canon_sha256":"a6c938f49a0f075ac5ca7f0b324874b6e1b925a67aa2071b6de0975a72edae94","abstract_canon_sha256":"83a473363c2ec8dcfead6a5bec29034ecde835ba8b66f057da2e30c04dca438c"},"schema_version":"1.0"},"canonical_sha256":"631fb1ebd7a7dc3578e6bcefe809acbd2df0ef9c34c98dd0af6c19c96cf1c271","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:07.548747Z","signature_b64":"WX73eUMvnMd6EZqGGaRq3NVXsRgsrP03L9Cljqhvfhaq7IGMsDFwjQSGNYj/DN93S77FQGliMsNE77vpyFFLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"631fb1ebd7a7dc3578e6bcefe809acbd2df0ef9c34c98dd0af6c19c96cf1c271","last_reissued_at":"2026-07-05T11:58:07.548160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:07.548160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.16974","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":"2026-07-05T11:58:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LUzG/PIoQmi9RVbJzvRXdVqZXK6b/PDvVB1YK1Z/xfbylQTeKbHNE0Q0JogQjhnb4UbZiLnTBXePcDtGI6LoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:07:38.111434Z"},"content_sha256":"eb8bc68352cb982762d713ae27778b6dd1d33233be8c720ef6c9b5421bef6237","schema_version":"1.0","event_id":"sha256:eb8bc68352cb982762d713ae27778b6dd1d33233be8c720ef6c9b5421bef6237"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MMP3D26XU7ODK6HGXTX6QCNMXU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Contextual Grounding LVLM: Enhancing Fine-Grained Visual-Language Understanding with Robust Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonio Carlos Rivera, Haoxuan Ren, Leilei Guo, Peiyu Tang, Zheyu Song","submitted_at":"2025-08-23T09:57:52Z","abstract_excerpt":"Large Language Models (LLMs) and Vision-Language Large Models (LVLMs) have achieved remarkable progress in natural language processing and multimodal understanding. Despite their impressive generalization capabilities, current LVLMs often exhibit insufficient robustness, proneness to hallucination, and reasoning errors in complex real-world scenarios, particularly when precise image region localization and fine-grained visual reasoning are required. To address these limitations, we propose the Hierarchical Contextual Grounding LVLM (HCG-LVLM), a novel architecture that mimics human coarse-to-f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16974","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/2508.16974/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":"2026-07-05T11:58:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4VDdoWQrz7t3PCT2cXRlieuvLQbM9+FPUv++XC9ApR6dHQ/uHZYMWWKCXlEvcfUcoBOXWxqh+U6zngfwBrEsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:07:38.111807Z"},"content_sha256":"738ae0bac2f8be53a5b14d20261bbbc59fc194d7f1a0f7374a29446ab33ccca8","schema_version":"1.0","event_id":"sha256:738ae0bac2f8be53a5b14d20261bbbc59fc194d7f1a0f7374a29446ab33ccca8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MMP3D26XU7ODK6HGXTX6QCNMXU/bundle.json","state_url":"https://pith.science/pith/MMP3D26XU7ODK6HGXTX6QCNMXU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MMP3D26XU7ODK6HGXTX6QCNMXU/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":"2026-08-18T01:07:38Z","links":{"resolver":"https://pith.science/pith/MMP3D26XU7ODK6HGXTX6QCNMXU","bundle":"https://pith.science/pith/MMP3D26XU7ODK6HGXTX6QCNMXU/bundle.json","state":"https://pith.science/pith/MMP3D26XU7ODK6HGXTX6QCNMXU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MMP3D26XU7ODK6HGXTX6QCNMXU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MMP3D26XU7ODK6HGXTX6QCNMXU","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":"83a473363c2ec8dcfead6a5bec29034ecde835ba8b66f057da2e30c04dca438c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-23T09:57:52Z","title_canon_sha256":"a6c938f49a0f075ac5ca7f0b324874b6e1b925a67aa2071b6de0975a72edae94"},"schema_version":"1.0","source":{"id":"2508.16974","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.16974","created_at":"2026-07-05T11:58:07Z"},{"alias_kind":"arxiv_version","alias_value":"2508.16974v1","created_at":"2026-07-05T11:58:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16974","created_at":"2026-07-05T11:58:07Z"},{"alias_kind":"pith_short_12","alias_value":"MMP3D26XU7OD","created_at":"2026-07-05T11:58:07Z"},{"alias_kind":"pith_short_16","alias_value":"MMP3D26XU7ODK6HG","created_at":"2026-07-05T11:58:07Z"},{"alias_kind":"pith_short_8","alias_value":"MMP3D26X","created_at":"2026-07-05T11:58:07Z"}],"graph_snapshots":[{"event_id":"sha256:738ae0bac2f8be53a5b14d20261bbbc59fc194d7f1a0f7374a29446ab33ccca8","target":"graph","created_at":"2026-07-05T11:58:07Z","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/2508.16974/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) and Vision-Language Large Models (LVLMs) have achieved remarkable progress in natural language processing and multimodal understanding. Despite their impressive generalization capabilities, current LVLMs often exhibit insufficient robustness, proneness to hallucination, and reasoning errors in complex real-world scenarios, particularly when precise image region localization and fine-grained visual reasoning are required. To address these limitations, we propose the Hierarchical Contextual Grounding LVLM (HCG-LVLM), a novel architecture that mimics human coarse-to-f","authors_text":"Antonio Carlos Rivera, Haoxuan Ren, Leilei Guo, Peiyu Tang, Zheyu Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-23T09:57:52Z","title":"Hierarchical Contextual Grounding LVLM: Enhancing Fine-Grained Visual-Language Understanding with Robust Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16974","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:eb8bc68352cb982762d713ae27778b6dd1d33233be8c720ef6c9b5421bef6237","target":"record","created_at":"2026-07-05T11:58:07Z","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":"83a473363c2ec8dcfead6a5bec29034ecde835ba8b66f057da2e30c04dca438c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-23T09:57:52Z","title_canon_sha256":"a6c938f49a0f075ac5ca7f0b324874b6e1b925a67aa2071b6de0975a72edae94"},"schema_version":"1.0","source":{"id":"2508.16974","kind":"arxiv","version":1}},"canonical_sha256":"631fb1ebd7a7dc3578e6bcefe809acbd2df0ef9c34c98dd0af6c19c96cf1c271","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"631fb1ebd7a7dc3578e6bcefe809acbd2df0ef9c34c98dd0af6c19c96cf1c271","first_computed_at":"2026-07-05T11:58:07.548160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:07.548160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WX73eUMvnMd6EZqGGaRq3NVXsRgsrP03L9Cljqhvfhaq7IGMsDFwjQSGNYj/DN93S77FQGliMsNE77vpyFFLCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:07.548747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.16974","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb8bc68352cb982762d713ae27778b6dd1d33233be8c720ef6c9b5421bef6237","sha256:738ae0bac2f8be53a5b14d20261bbbc59fc194d7f1a0f7374a29446ab33ccca8"],"state_sha256":"b5fca631c6b0498524382fb72efab99e7a00568d040c287ccdd46ef1d912d559"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ikVyJaPD16IQ9Y1MEKJnHu3N7dgzaH9+TibecB/2B8KDeXF5lAQ5gemoZYPsqLS17/bbhrCKem3jZwyw3vFWAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T01:07:38.114394Z","bundle_sha256":"fba0b65e36def4ad1620c6c0dd125dce1b4b9f6ab2bd55586f471fd532c87918"}}