{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MAA6EBNC63G6TFVSPVLOSMNJHR","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":"1bd765b87db34f75a2458c541edb87863d65e3902e39316481e14a23d8942e18","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T04:13:23Z","title_canon_sha256":"05c95da96a38f3ddd0144946147e123e6b32ee21b6ef57abe6eb529b38f3aae0"},"schema_version":"1.0","source":{"id":"2411.18038","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18038","created_at":"2026-07-05T09:41:10Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18038v1","created_at":"2026-07-05T09:41:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18038","created_at":"2026-07-05T09:41:10Z"},{"alias_kind":"pith_short_12","alias_value":"MAA6EBNC63G6","created_at":"2026-07-05T09:41:10Z"},{"alias_kind":"pith_short_16","alias_value":"MAA6EBNC63G6TFVS","created_at":"2026-07-05T09:41:10Z"},{"alias_kind":"pith_short_8","alias_value":"MAA6EBNC","created_at":"2026-07-05T09:41:10Z"}],"graph_snapshots":[{"event_id":"sha256:009903930b05e3fcf2eb0eb1d05796a0530f601c825349a13ce4d367151b4b79","target":"graph","created_at":"2026-07-05T09:41:10Z","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/2411.18038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Large Vision Language Model (VLM) has recently addressed remarkable progress in bridging two fundamental modalities. VLM, trained by a sufficiently large dataset, exhibits a comprehensive understanding of both visual and linguistic to perform diverse tasks. To distill this knowledge accurately, in this paper, we introduce a novel approach that explicitly utilizes VLM as an objective function form for the Human-Object Interaction (HOI) detection task (\\textbf{VLM-HOI}). Specifically, we propose a method that quantifies the similarity of the predicted HOI triplet using the Image-Text matchin","authors_text":"Dasol Jeong, Donggoo Kang, Hasil Park, Hyunmin Lee, Joonki Paik, Sangwoo Park, Sunkyu Kwon, Yeongjoon Kim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T04:13:23Z","title":"VLM-HOI: Vision Language Models for Interpretable Human-Object Interaction Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18038","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:d700c03a4073c3bda14b7869b2de0284b44fc60ea745372e5372ef4279fa41ed","target":"record","created_at":"2026-07-05T09:41:10Z","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":"1bd765b87db34f75a2458c541edb87863d65e3902e39316481e14a23d8942e18","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T04:13:23Z","title_canon_sha256":"05c95da96a38f3ddd0144946147e123e6b32ee21b6ef57abe6eb529b38f3aae0"},"schema_version":"1.0","source":{"id":"2411.18038","kind":"arxiv","version":1}},"canonical_sha256":"6001e205a2f6cde996b27d56e931a93c6c0dd85bb791368070671472225901f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6001e205a2f6cde996b27d56e931a93c6c0dd85bb791368070671472225901f5","first_computed_at":"2026-07-05T09:41:10.903743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:10.903743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EW0TuvRdTHBmFDncjnHKh9joyagjCr13qYR3EXo9QrCFYIqNVjNfLpqYxvs0DlpxMhyNz6ZRN+ZVKPQYuczoBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:10.904221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.18038","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d700c03a4073c3bda14b7869b2de0284b44fc60ea745372e5372ef4279fa41ed","sha256:009903930b05e3fcf2eb0eb1d05796a0530f601c825349a13ce4d367151b4b79"],"state_sha256":"0c8f79c424775b4ed0f5826c379b86e194ad894fa1b5743f344e717b799fce44"}