{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2EDP6UG4FQOONBWFX3RG6LIRLB","short_pith_number":"pith:2EDP6UG4","schema_version":"1.0","canonical_sha256":"d106ff50dc2c1ce686c5bee26f2d11584bd9c6784c93dedc0a1aab7c67a4a0f0","source":{"kind":"arxiv","id":"2411.06869","version":2},"attestation_state":"computed","paper":{"title":"CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Byung-Hoon Kim, Hyungjin Chung, Junho Kim","submitted_at":"2024-11-11T11:08:26Z","abstract_excerpt":"Category-agnostic pose estimation (CAPE) has traditionally relied on support images with annotated keypoints, a process that is often cumbersome and may fail to fully capture the necessary correspondences across diverse object categories. Recent efforts have explored the use of text queries, leveraging their enhanced stability and generalization capabilities. However, existing approaches often remain constrained by their reliance on support queries, their failure to fully utilize the rich priors embedded in pre-trained large language models, and the limitations imposed by their parametric dist"},"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":"2411.06869","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-11T11:08:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9222315ef6ae4b1c0978a5b497b6b45b6140c9faf1b581797d1cc871c8afdfb7","abstract_canon_sha256":"643dc2fab8fd70981e467a6af01d0427e018f7c793aa60bf3e174f970886ad37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:42.429097Z","signature_b64":"8MA8J12zKK09oA/wm1SSogRpeoSndeUejAGlCmjsYvnLNWVhQPa815EXke7nxTX1WupeIB42sCSpyOCjF4WsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d106ff50dc2c1ce686c5bee26f2d11584bd9c6784c93dedc0a1aab7c67a4a0f0","last_reissued_at":"2026-07-05T11:53:42.428483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:42.428483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Byung-Hoon Kim, Hyungjin Chung, Junho Kim","submitted_at":"2024-11-11T11:08:26Z","abstract_excerpt":"Category-agnostic pose estimation (CAPE) has traditionally relied on support images with annotated keypoints, a process that is often cumbersome and may fail to fully capture the necessary correspondences across diverse object categories. Recent efforts have explored the use of text queries, leveraging their enhanced stability and generalization capabilities. However, existing approaches often remain constrained by their reliance on support queries, their failure to fully utilize the rich priors embedded in pre-trained large language models, and the limitations imposed by their parametric dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06869","kind":"arxiv","version":2},"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/2411.06869/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":"2411.06869","created_at":"2026-07-05T11:53:42.428554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.06869v2","created_at":"2026-07-05T11:53:42.428554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06869","created_at":"2026-07-05T11:53:42.428554+00:00"},{"alias_kind":"pith_short_12","alias_value":"2EDP6UG4FQOO","created_at":"2026-07-05T11:53:42.428554+00:00"},{"alias_kind":"pith_short_16","alias_value":"2EDP6UG4FQOONBWF","created_at":"2026-07-05T11:53:42.428554+00:00"},{"alias_kind":"pith_short_8","alias_value":"2EDP6UG4","created_at":"2026-07-05T11:53:42.428554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13151","citing_title":"GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose Estimation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2EDP6UG4FQOONBWFX3RG6LIRLB","json":"https://pith.science/pith/2EDP6UG4FQOONBWFX3RG6LIRLB.json","graph_json":"https://pith.science/api/pith-number/2EDP6UG4FQOONBWFX3RG6LIRLB/graph.json","events_json":"https://pith.science/api/pith-number/2EDP6UG4FQOONBWFX3RG6LIRLB/events.json","paper":"https://pith.science/paper/2EDP6UG4"},"agent_actions":{"view_html":"https://pith.science/pith/2EDP6UG4FQOONBWFX3RG6LIRLB","download_json":"https://pith.science/pith/2EDP6UG4FQOONBWFX3RG6LIRLB.json","view_paper":"https://pith.science/paper/2EDP6UG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.06869&json=true","fetch_graph":"https://pith.science/api/pith-number/2EDP6UG4FQOONBWFX3RG6LIRLB/graph.json","fetch_events":"https://pith.science/api/pith-number/2EDP6UG4FQOONBWFX3RG6LIRLB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2EDP6UG4FQOONBWFX3RG6LIRLB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2EDP6UG4FQOONBWFX3RG6LIRLB/action/storage_attestation","attest_author":"https://pith.science/pith/2EDP6UG4FQOONBWFX3RG6LIRLB/action/author_attestation","sign_citation":"https://pith.science/pith/2EDP6UG4FQOONBWFX3RG6LIRLB/action/citation_signature","submit_replication":"https://pith.science/pith/2EDP6UG4FQOONBWFX3RG6LIRLB/action/replication_record"}},"created_at":"2026-07-05T11:53:42.428554+00:00","updated_at":"2026-07-05T11:53:42.428554+00:00"}