{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZAL5AMIPHKRCLA5OHBUZMDIUSX","short_pith_number":"pith:ZAL5AMIP","schema_version":"1.0","canonical_sha256":"c817d0310f3aa22583ae3869960d1495fdeb0ce94ba4af2e8ec3d692b85e7a04","source":{"kind":"arxiv","id":"2507.11102","version":1},"attestation_state":"computed","paper":{"title":"KptLLM++: Towards Generic Keypoint Comprehension with Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Qian, Jie Yang, Lumin Xu, Ruimao Zhang, Sheng Jin, Wang Zeng, Wentao Liu, Zhen Li","submitted_at":"2025-07-15T08:52:28Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.11102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-15T08:52:28Z","cross_cats_sorted":[],"title_canon_sha256":"5bd377600d7be0b6759c04c741da62fbac6d63f5c5a37665abf9ed6f32d4fcda","abstract_canon_sha256":"dd2710288235a49c40c2a22a67460ee46371b80e4b19587a16516f535245a664"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:31.986025Z","signature_b64":"tFNjCM1nJRxInFsWDOHGS+xCK+Gs8mCenGlQY3dPsKeaQ+riITagHe2tDUj/1KEl3uvR81ewb4dFq2Kf4IFbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c817d0310f3aa22583ae3869960d1495fdeb0ce94ba4af2e8ec3d692b85e7a04","last_reissued_at":"2026-07-05T11:37:31.985450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:31.985450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KptLLM++: Towards Generic Keypoint Comprehension with Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Qian, Jie Yang, Lumin Xu, Ruimao Zhang, Sheng Jin, Wang Zeng, Wentao Liu, Zhen Li","submitted_at":"2025-07-15T08:52:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11102","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/2507.11102/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.11102","created_at":"2026-07-05T11:37:31.985545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.11102v1","created_at":"2026-07-05T11:37:31.985545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11102","created_at":"2026-07-05T11:37:31.985545+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZAL5AMIPHKRC","created_at":"2026-07-05T11:37:31.985545+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZAL5AMIPHKRCLA5O","created_at":"2026-07-05T11:37:31.985545+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZAL5AMIP","created_at":"2026-07-05T11:37:31.985545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZAL5AMIPHKRCLA5OHBUZMDIUSX","json":"https://pith.science/pith/ZAL5AMIPHKRCLA5OHBUZMDIUSX.json","graph_json":"https://pith.science/api/pith-number/ZAL5AMIPHKRCLA5OHBUZMDIUSX/graph.json","events_json":"https://pith.science/api/pith-number/ZAL5AMIPHKRCLA5OHBUZMDIUSX/events.json","paper":"https://pith.science/paper/ZAL5AMIP"},"agent_actions":{"view_html":"https://pith.science/pith/ZAL5AMIPHKRCLA5OHBUZMDIUSX","download_json":"https://pith.science/pith/ZAL5AMIPHKRCLA5OHBUZMDIUSX.json","view_paper":"https://pith.science/paper/ZAL5AMIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.11102&json=true","fetch_graph":"https://pith.science/api/pith-number/ZAL5AMIPHKRCLA5OHBUZMDIUSX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZAL5AMIPHKRCLA5OHBUZMDIUSX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZAL5AMIPHKRCLA5OHBUZMDIUSX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZAL5AMIPHKRCLA5OHBUZMDIUSX/action/storage_attestation","attest_author":"https://pith.science/pith/ZAL5AMIPHKRCLA5OHBUZMDIUSX/action/author_attestation","sign_citation":"https://pith.science/pith/ZAL5AMIPHKRCLA5OHBUZMDIUSX/action/citation_signature","submit_replication":"https://pith.science/pith/ZAL5AMIPHKRCLA5OHBUZMDIUSX/action/replication_record"}},"created_at":"2026-07-05T11:37:31.985545+00:00","updated_at":"2026-07-05T11:37:31.985545+00:00"}