{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z2KZ3NSHMZUPDPELSU6F2OZHMX","short_pith_number":"pith:Z2KZ3NSH","schema_version":"1.0","canonical_sha256":"ce959db6476668f1bc8b953c5d3b2765eb1583f3102518b86b0e41cbead4ed4d","source":{"kind":"arxiv","id":"2507.09139","version":1},"attestation_state":"computed","paper":{"title":"PoseLLM: Enhancing Language-Guided Human Pose Estimation with MLP Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dewen Zhang, Hayaru Shouno, Tahir Hussain, Wangpeng An","submitted_at":"2025-07-12T04:53:39Z","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"},"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":"2507.09139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-12T04:53:39Z","cross_cats_sorted":[],"title_canon_sha256":"25d8bfa4032d1e5703472dca9671d5c1d783ada16ba79a651e1c3dddf9d99970","abstract_canon_sha256":"b160ea68d5ddbfafe4297b22e63df13feab5546b967a5ed12c06e355f594b1e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:04.371322Z","signature_b64":"7L3RPvXJmdL6TW2bjrQAK0w5s9KS7UpEvgxbbOeQ/KGwz4XUokEdhaXT6cLxqCbofGO/KNzYmRaX2b6+zIUVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce959db6476668f1bc8b953c5d3b2765eb1583f3102518b86b0e41cbead4ed4d","last_reissued_at":"2026-07-05T11:36:04.370861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:04.370861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PoseLLM: Enhancing Language-Guided Human Pose Estimation with MLP Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dewen Zhang, Hayaru Shouno, Tahir Hussain, Wangpeng An","submitted_at":"2025-07-12T04:53:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09139","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/2507.09139/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":"2507.09139","created_at":"2026-07-05T11:36:04.370919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09139v1","created_at":"2026-07-05T11:36:04.370919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09139","created_at":"2026-07-05T11:36:04.370919+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2KZ3NSHMZUP","created_at":"2026-07-05T11:36:04.370919+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2KZ3NSHMZUPDPEL","created_at":"2026-07-05T11:36:04.370919+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2KZ3NSH","created_at":"2026-07-05T11:36:04.370919+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/Z2KZ3NSHMZUPDPELSU6F2OZHMX","json":"https://pith.science/pith/Z2KZ3NSHMZUPDPELSU6F2OZHMX.json","graph_json":"https://pith.science/api/pith-number/Z2KZ3NSHMZUPDPELSU6F2OZHMX/graph.json","events_json":"https://pith.science/api/pith-number/Z2KZ3NSHMZUPDPELSU6F2OZHMX/events.json","paper":"https://pith.science/paper/Z2KZ3NSH"},"agent_actions":{"view_html":"https://pith.science/pith/Z2KZ3NSHMZUPDPELSU6F2OZHMX","download_json":"https://pith.science/pith/Z2KZ3NSHMZUPDPELSU6F2OZHMX.json","view_paper":"https://pith.science/paper/Z2KZ3NSH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09139&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2KZ3NSHMZUPDPELSU6F2OZHMX/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2KZ3NSHMZUPDPELSU6F2OZHMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2KZ3NSHMZUPDPELSU6F2OZHMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2KZ3NSHMZUPDPELSU6F2OZHMX/action/storage_attestation","attest_author":"https://pith.science/pith/Z2KZ3NSHMZUPDPELSU6F2OZHMX/action/author_attestation","sign_citation":"https://pith.science/pith/Z2KZ3NSHMZUPDPELSU6F2OZHMX/action/citation_signature","submit_replication":"https://pith.science/pith/Z2KZ3NSHMZUPDPELSU6F2OZHMX/action/replication_record"}},"created_at":"2026-07-05T11:36:04.370919+00:00","updated_at":"2026-07-05T11:36:04.370919+00:00"}