{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z2KZ3NSHMZUPDPELSU6F2OZHMX","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":"b160ea68d5ddbfafe4297b22e63df13feab5546b967a5ed12c06e355f594b1e7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-12T04:53:39Z","title_canon_sha256":"25d8bfa4032d1e5703472dca9671d5c1d783ada16ba79a651e1c3dddf9d99970"},"schema_version":"1.0","source":{"id":"2507.09139","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09139","created_at":"2026-07-05T11:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09139v1","created_at":"2026-07-05T11:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09139","created_at":"2026-07-05T11:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"Z2KZ3NSHMZUP","created_at":"2026-07-05T11:36:04Z"},{"alias_kind":"pith_short_16","alias_value":"Z2KZ3NSHMZUPDPEL","created_at":"2026-07-05T11:36:04Z"},{"alias_kind":"pith_short_8","alias_value":"Z2KZ3NSH","created_at":"2026-07-05T11:36:04Z"}],"graph_snapshots":[{"event_id":"sha256:dbbc20b410821e8843bd8ae4bc4ef91b370c38daabf4f4e12078a7bf8bc5dc9c","target":"graph","created_at":"2026-07-05T11:36:04Z","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/2507.09139/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human pose estimation traditionally relies on architectures that encode keypoint priors, limiting their generalization to novel poses or unseen keypoints. Recent language-guided approaches like LocLLM reformulate keypoint localization as a vision-language task, enabling zero-shot generalization through textual descriptions. However, LocLLM's linear projector fails to capture complex spatial-textual interactions critical for high-precision localization. To address this, we propose PoseLLM, the first Large Language Model (LLM)-based pose estimation framework that replaces the linear projector wi","authors_text":"Dewen Zhang, Hayaru Shouno, Tahir Hussain, Wangpeng An","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-12T04:53:39Z","title":"PoseLLM: Enhancing Language-Guided Human Pose Estimation with MLP Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09139","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:bd79e067b552a34508ddfb32f80fc6f99de6aeecf850dbac08c8590b6bf70e11","target":"record","created_at":"2026-07-05T11:36:04Z","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":"b160ea68d5ddbfafe4297b22e63df13feab5546b967a5ed12c06e355f594b1e7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-12T04:53:39Z","title_canon_sha256":"25d8bfa4032d1e5703472dca9671d5c1d783ada16ba79a651e1c3dddf9d99970"},"schema_version":"1.0","source":{"id":"2507.09139","kind":"arxiv","version":1}},"canonical_sha256":"ce959db6476668f1bc8b953c5d3b2765eb1583f3102518b86b0e41cbead4ed4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce959db6476668f1bc8b953c5d3b2765eb1583f3102518b86b0e41cbead4ed4d","first_computed_at":"2026-07-05T11:36:04.370861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:04.370861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7L3RPvXJmdL6TW2bjrQAK0w5s9KS7UpEvgxbbOeQ/KGwz4XUokEdhaXT6cLxqCbofGO/KNzYmRaX2b6+zIUVCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:04.371322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09139","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd79e067b552a34508ddfb32f80fc6f99de6aeecf850dbac08c8590b6bf70e11","sha256:dbbc20b410821e8843bd8ae4bc4ef91b370c38daabf4f4e12078a7bf8bc5dc9c"],"state_sha256":"7f2f24c9f43a6e4477dea9fc819fcc4452e0aec7beec59183b6442b93f4baae0"}