{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JIEI74CRKNPJSRUXSENLOMUVLV","short_pith_number":"pith:JIEI74CR","canonical_record":{"source":{"id":"2506.21317","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-26T14:32:56Z","cross_cats_sorted":[],"title_canon_sha256":"28c95d3c359ee77709d55a979f4762f21d623e5d1ab8dfae8ea8eb2c686d23b8","abstract_canon_sha256":"0ebbb55183c10c49ab7f87c316301b19753e94160eb2f8979a471c63ce6a3a5a"},"schema_version":"1.0"},"canonical_sha256":"4a088ff051535e994697911ab732955d698443805f144bca64a0e46e7d1cd13e","source":{"kind":"arxiv","id":"2506.21317","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21317","created_at":"2026-07-05T11:27:43Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21317v1","created_at":"2026-07-05T11:27:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21317","created_at":"2026-07-05T11:27:43Z"},{"alias_kind":"pith_short_12","alias_value":"JIEI74CRKNPJ","created_at":"2026-07-05T11:27:43Z"},{"alias_kind":"pith_short_16","alias_value":"JIEI74CRKNPJSRUX","created_at":"2026-07-05T11:27:43Z"},{"alias_kind":"pith_short_8","alias_value":"JIEI74CR","created_at":"2026-07-05T11:27:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JIEI74CRKNPJSRUXSENLOMUVLV","target":"record","payload":{"canonical_record":{"source":{"id":"2506.21317","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-26T14:32:56Z","cross_cats_sorted":[],"title_canon_sha256":"28c95d3c359ee77709d55a979f4762f21d623e5d1ab8dfae8ea8eb2c686d23b8","abstract_canon_sha256":"0ebbb55183c10c49ab7f87c316301b19753e94160eb2f8979a471c63ce6a3a5a"},"schema_version":"1.0"},"canonical_sha256":"4a088ff051535e994697911ab732955d698443805f144bca64a0e46e7d1cd13e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:43.425045Z","signature_b64":"T6K6oudRBup0dZQvIVVADAIa7b821yrWieBibKwu7k1THaeE8gqi2VliBxChfXyO/zQK8ooMIesJ6ONi0ncdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a088ff051535e994697911ab732955d698443805f144bca64a0e46e7d1cd13e","last_reissued_at":"2026-07-05T11:27:43.424508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:43.424508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.21317","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:27:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XnTAqS6dQmYnzGk318rsmcY+FrjRlNt3mdsbsRGh13vXFB0SEr//GDP2KQn7yeEXqcxF2Rni/XofvGaUoCZJBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T02:53:12.922842Z"},"content_sha256":"84c5de4c5d3ab8c102778835569232dee90c7cd91feb200cbf392cd34832e0be","schema_version":"1.0","event_id":"sha256:84c5de4c5d3ab8c102778835569232dee90c7cd91feb200cbf392cd34832e0be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JIEI74CRKNPJSRUXSENLOMUVLV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaVA-Pose: Enhancing Human Pose and Action Understanding via Keypoint-Integrated Instruction Tuning","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":"2025-06-26T14:32:56Z","abstract_excerpt":"Current vision-language models (VLMs) 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 tasks, f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21317","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/2506.21317/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:27:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mLuqtFMPf8PM8FbPefktyQ3+hW9VTnlehsPGgbQvUXugT9XXKM+2/ZG7F9OrVMh496lBH2PaoV3hxzJbR/bMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T02:53:12.923377Z"},"content_sha256":"20108ce0565ce0bbe09c16c28a022fff522a9f914a69f4a885e972cf8e0b94c3","schema_version":"1.0","event_id":"sha256:20108ce0565ce0bbe09c16c28a022fff522a9f914a69f4a885e972cf8e0b94c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JIEI74CRKNPJSRUXSENLOMUVLV/bundle.json","state_url":"https://pith.science/pith/JIEI74CRKNPJSRUXSENLOMUVLV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JIEI74CRKNPJSRUXSENLOMUVLV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T02:53:12Z","links":{"resolver":"https://pith.science/pith/JIEI74CRKNPJSRUXSENLOMUVLV","bundle":"https://pith.science/pith/JIEI74CRKNPJSRUXSENLOMUVLV/bundle.json","state":"https://pith.science/pith/JIEI74CRKNPJSRUXSENLOMUVLV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JIEI74CRKNPJSRUXSENLOMUVLV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JIEI74CRKNPJSRUXSENLOMUVLV","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":"0ebbb55183c10c49ab7f87c316301b19753e94160eb2f8979a471c63ce6a3a5a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-26T14:32:56Z","title_canon_sha256":"28c95d3c359ee77709d55a979f4762f21d623e5d1ab8dfae8ea8eb2c686d23b8"},"schema_version":"1.0","source":{"id":"2506.21317","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21317","created_at":"2026-07-05T11:27:43Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21317v1","created_at":"2026-07-05T11:27:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21317","created_at":"2026-07-05T11:27:43Z"},{"alias_kind":"pith_short_12","alias_value":"JIEI74CRKNPJ","created_at":"2026-07-05T11:27:43Z"},{"alias_kind":"pith_short_16","alias_value":"JIEI74CRKNPJSRUX","created_at":"2026-07-05T11:27:43Z"},{"alias_kind":"pith_short_8","alias_value":"JIEI74CR","created_at":"2026-07-05T11:27:43Z"}],"graph_snapshots":[{"event_id":"sha256:20108ce0565ce0bbe09c16c28a022fff522a9f914a69f4a885e972cf8e0b94c3","target":"graph","created_at":"2026-07-05T11:27:43Z","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/2506.21317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current vision-language models (VLMs) 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 tasks, f","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":"2025-06-26T14:32:56Z","title":"LLaVA-Pose: Enhancing Human Pose and Action Understanding via Keypoint-Integrated Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21317","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":"sha256:84c5de4c5d3ab8c102778835569232dee90c7cd91feb200cbf392cd34832e0be","target":"record","created_at":"2026-07-05T11:27:43Z","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":"0ebbb55183c10c49ab7f87c316301b19753e94160eb2f8979a471c63ce6a3a5a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-26T14:32:56Z","title_canon_sha256":"28c95d3c359ee77709d55a979f4762f21d623e5d1ab8dfae8ea8eb2c686d23b8"},"schema_version":"1.0","source":{"id":"2506.21317","kind":"arxiv","version":1}},"canonical_sha256":"4a088ff051535e994697911ab732955d698443805f144bca64a0e46e7d1cd13e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a088ff051535e994697911ab732955d698443805f144bca64a0e46e7d1cd13e","first_computed_at":"2026-07-05T11:27:43.424508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:43.424508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T6K6oudRBup0dZQvIVVADAIa7b821yrWieBibKwu7k1THaeE8gqi2VliBxChfXyO/zQK8ooMIesJ6ONi0ncdDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:43.425045Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21317","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84c5de4c5d3ab8c102778835569232dee90c7cd91feb200cbf392cd34832e0be","sha256:20108ce0565ce0bbe09c16c28a022fff522a9f914a69f4a885e972cf8e0b94c3"],"state_sha256":"fe8ab83537a7c9ba79b155cdea70941f7833efbb4d5cb0ddef51d6a8c7496efd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ujRz+dbBvOvwPDIYtitoUcjmvOgaWDb5tjpki1mkD2pihguWzFPvK7hy4RBSZHpf5z9ePrDhyxJN9XHELtmaBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T02:53:12.929215Z","bundle_sha256":"574afb46fad4b5115f1aa268182ba62bc3ef86e9f563c1d3aab6252d3bfb41ac"}}