{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZAL5AMIPHKRCLA5OHBUZMDIUSX","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":"dd2710288235a49c40c2a22a67460ee46371b80e4b19587a16516f535245a664","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-15T08:52:28Z","title_canon_sha256":"5bd377600d7be0b6759c04c741da62fbac6d63f5c5a37665abf9ed6f32d4fcda"},"schema_version":"1.0","source":{"id":"2507.11102","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.11102","created_at":"2026-07-05T11:37:31Z"},{"alias_kind":"arxiv_version","alias_value":"2507.11102v1","created_at":"2026-07-05T11:37:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11102","created_at":"2026-07-05T11:37:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZAL5AMIPHKRC","created_at":"2026-07-05T11:37:31Z"},{"alias_kind":"pith_short_16","alias_value":"ZAL5AMIPHKRCLA5O","created_at":"2026-07-05T11:37:31Z"},{"alias_kind":"pith_short_8","alias_value":"ZAL5AMIP","created_at":"2026-07-05T11:37:31Z"}],"graph_snapshots":[{"event_id":"sha256:19c3befdf7bdd0a9b6a7e8ba631233012079b6340e16ee01e3c5dff0a6523039","target":"graph","created_at":"2026-07-05T11:37:31Z","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/2507.11102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergence of Multimodal Large Language Models (MLLMs) has revolutionized image understanding by bridging textual and visual modalities. However, these models often struggle with capturing fine-grained semantic information, such as the precise identification and analysis of object keypoints. Keypoints, as structure-aware, pixel-level, and compact representations of objects, particularly articulated ones, play a crucial role in applications such as fine-grained image analysis, object retrieval, and behavior recognition. In this paper, we propose KptLLM++, a novel multimodal large language mo","authors_text":"Chen Qian, Jie Yang, Lumin Xu, Ruimao Zhang, Sheng Jin, Wang Zeng, Wentao Liu, Zhen Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-15T08:52:28Z","title":"KptLLM++: Towards Generic Keypoint Comprehension with Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11102","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:e890172f452de30338ef9a7d593f60361eaa5b09c02900c2ec061501bd3cfadf","target":"record","created_at":"2026-07-05T11:37:31Z","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":"dd2710288235a49c40c2a22a67460ee46371b80e4b19587a16516f535245a664","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-15T08:52:28Z","title_canon_sha256":"5bd377600d7be0b6759c04c741da62fbac6d63f5c5a37665abf9ed6f32d4fcda"},"schema_version":"1.0","source":{"id":"2507.11102","kind":"arxiv","version":1}},"canonical_sha256":"c817d0310f3aa22583ae3869960d1495fdeb0ce94ba4af2e8ec3d692b85e7a04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c817d0310f3aa22583ae3869960d1495fdeb0ce94ba4af2e8ec3d692b85e7a04","first_computed_at":"2026-07-05T11:37:31.985450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:31.985450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tFNjCM1nJRxInFsWDOHGS+xCK+Gs8mCenGlQY3dPsKeaQ+riITagHe2tDUj/1KEl3uvR81ewb4dFq2Kf4IFbBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:31.986025Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.11102","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e890172f452de30338ef9a7d593f60361eaa5b09c02900c2ec061501bd3cfadf","sha256:19c3befdf7bdd0a9b6a7e8ba631233012079b6340e16ee01e3c5dff0a6523039"],"state_sha256":"9307df39acedf8ae45e18a16bfe235344175076be5ee33d9c2214838034bc89e"}