{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3R4N67BHPGX4RTCVDXDRBCZOEA","short_pith_number":"pith:3R4N67BH","schema_version":"1.0","canonical_sha256":"dc78df7c2779afc8cc551dc7108b2e203d0709b8a1bfbcfa241a903482985e88","source":{"kind":"arxiv","id":"2409.09306","version":2},"attestation_state":"computed","paper":{"title":"Keypoint-Integrated Instruction-Following Data Generation for Enhanced Human Pose and Action Understanding in Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dewen Zhang, Hayaru Shouno, Wangpeng An","submitted_at":"2024-09-14T05:07:57Z","abstract_excerpt":"Current vision-language multimodal models are well-adapted for general visual understanding tasks. However, they perform inadequately when handling complex visual tasks related to human poses and actions due to the lack of specialized vision-language instruction-following data. We introduce a method for generating such data by integrating human keypoints with traditional visual features such as captions and bounding boxes, enabling more precise understanding of human-centric scenes. Our approach constructs a dataset comprising 200,328 samples tailored to fine-tune models for human-centric task"},"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":"2409.09306","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-14T05:07:57Z","cross_cats_sorted":[],"title_canon_sha256":"683952ce0ef1d430bd5a15ceb6664ed6f7ee72cf11ed073192aff5af9e4afbd5","abstract_canon_sha256":"8c2b114a72a9477da068e39a742ee1d65c9499d2845f0b4d91178b6704b27d10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:57.888641Z","signature_b64":"PdlCTs4HdnU0SDJCkBrXGmDlzLmekZ4rSJoVMGty6Caz3Mv1x3zMywkr4MNWQ9Ppwtpwn9f9RHLI4ChtuMwGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc78df7c2779afc8cc551dc7108b2e203d0709b8a1bfbcfa241a903482985e88","last_reissued_at":"2026-07-05T11:13:57.888180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:57.888180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Keypoint-Integrated Instruction-Following Data Generation for Enhanced Human Pose and Action Understanding in Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dewen Zhang, Hayaru Shouno, Wangpeng An","submitted_at":"2024-09-14T05:07:57Z","abstract_excerpt":"Current vision-language multimodal models are well-adapted for general visual understanding tasks. However, they perform inadequately when handling complex visual tasks related to human poses and actions due to the lack of specialized vision-language instruction-following data. We introduce a method for generating such data by integrating human keypoints with traditional visual features such as captions and bounding boxes, enabling more precise understanding of human-centric scenes. Our approach constructs a dataset comprising 200,328 samples tailored to fine-tune models for human-centric task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09306","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/2409.09306/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":"2409.09306","created_at":"2026-07-05T11:13:57.888234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09306v2","created_at":"2026-07-05T11:13:57.888234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09306","created_at":"2026-07-05T11:13:57.888234+00:00"},{"alias_kind":"pith_short_12","alias_value":"3R4N67BHPGX4","created_at":"2026-07-05T11:13:57.888234+00:00"},{"alias_kind":"pith_short_16","alias_value":"3R4N67BHPGX4RTCV","created_at":"2026-07-05T11:13:57.888234+00:00"},{"alias_kind":"pith_short_8","alias_value":"3R4N67BH","created_at":"2026-07-05T11:13:57.888234+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09139","citing_title":"PoseLLM: Enhancing Language-Guided Human Pose Estimation with MLP Alignment","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3R4N67BHPGX4RTCVDXDRBCZOEA","json":"https://pith.science/pith/3R4N67BHPGX4RTCVDXDRBCZOEA.json","graph_json":"https://pith.science/api/pith-number/3R4N67BHPGX4RTCVDXDRBCZOEA/graph.json","events_json":"https://pith.science/api/pith-number/3R4N67BHPGX4RTCVDXDRBCZOEA/events.json","paper":"https://pith.science/paper/3R4N67BH"},"agent_actions":{"view_html":"https://pith.science/pith/3R4N67BHPGX4RTCVDXDRBCZOEA","download_json":"https://pith.science/pith/3R4N67BHPGX4RTCVDXDRBCZOEA.json","view_paper":"https://pith.science/paper/3R4N67BH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09306&json=true","fetch_graph":"https://pith.science/api/pith-number/3R4N67BHPGX4RTCVDXDRBCZOEA/graph.json","fetch_events":"https://pith.science/api/pith-number/3R4N67BHPGX4RTCVDXDRBCZOEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3R4N67BHPGX4RTCVDXDRBCZOEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3R4N67BHPGX4RTCVDXDRBCZOEA/action/storage_attestation","attest_author":"https://pith.science/pith/3R4N67BHPGX4RTCVDXDRBCZOEA/action/author_attestation","sign_citation":"https://pith.science/pith/3R4N67BHPGX4RTCVDXDRBCZOEA/action/citation_signature","submit_replication":"https://pith.science/pith/3R4N67BHPGX4RTCVDXDRBCZOEA/action/replication_record"}},"created_at":"2026-07-05T11:13:57.888234+00:00","updated_at":"2026-07-05T11:13:57.888234+00:00"}