{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XPPNOANDGFJQLF6LHXYXBC7TDT","short_pith_number":"pith:XPPNOAND","schema_version":"1.0","canonical_sha256":"bbded701a331530597cb3df1708bf31cfa2c12b0c85caab8aa09b46666e9ff4e","source":{"kind":"arxiv","id":"2501.00432","version":1},"attestation_state":"computed","paper":{"title":"OV-HHIR: Open Vocabulary Human Interaction Recognition Using Cross-modal Integration of Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Zhou, Lala Shakti Swarup Ray, Paul Lukowicz, Sungho Suh","submitted_at":"2024-12-31T13:22:00Z","abstract_excerpt":"Understanding human-to-human interactions, especially in contexts like public security surveillance, is critical for monitoring and maintaining safety. Traditional activity recognition systems are limited by fixed vocabularies, predefined labels, and rigid interaction categories that often rely on choreographed videos and overlook concurrent interactive groups. These limitations make such systems less adaptable to real-world scenarios, where interactions are diverse and unpredictable. In this paper, we propose an open vocabulary human-to-human interaction recognition (OV-HHIR) framework that l"},"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":"2501.00432","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T13:22:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9d1a48072f0be0acc03563cf32f71871ce33c968ed1f5bfddb3262c5fc0ddbb1","abstract_canon_sha256":"2f02f67272062658f15ff65d4b0cb48c44fa5d6b2969dac282639093cd645096"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:05.802295Z","signature_b64":"uxGMEfeZDWM8T4+zF5t41fv48F0lCxfgzeG4Z5SdkEmyVrU3aHvCQEk0rGNdiBSy9NCjk1yDo6AZkfajdBg+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbded701a331530597cb3df1708bf31cfa2c12b0c85caab8aa09b46666e9ff4e","last_reissued_at":"2026-07-05T09:56:05.801831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:05.801831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OV-HHIR: Open Vocabulary Human Interaction Recognition Using Cross-modal Integration of Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Zhou, Lala Shakti Swarup Ray, Paul Lukowicz, Sungho Suh","submitted_at":"2024-12-31T13:22:00Z","abstract_excerpt":"Understanding human-to-human interactions, especially in contexts like public security surveillance, is critical for monitoring and maintaining safety. Traditional activity recognition systems are limited by fixed vocabularies, predefined labels, and rigid interaction categories that often rely on choreographed videos and overlook concurrent interactive groups. These limitations make such systems less adaptable to real-world scenarios, where interactions are diverse and unpredictable. In this paper, we propose an open vocabulary human-to-human interaction recognition (OV-HHIR) framework that l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00432","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/2501.00432/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":"2501.00432","created_at":"2026-07-05T09:56:05.801884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00432v1","created_at":"2026-07-05T09:56:05.801884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00432","created_at":"2026-07-05T09:56:05.801884+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPPNOANDGFJQ","created_at":"2026-07-05T09:56:05.801884+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPPNOANDGFJQLF6L","created_at":"2026-07-05T09:56:05.801884+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPPNOAND","created_at":"2026-07-05T09:56:05.801884+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/XPPNOANDGFJQLF6LHXYXBC7TDT","json":"https://pith.science/pith/XPPNOANDGFJQLF6LHXYXBC7TDT.json","graph_json":"https://pith.science/api/pith-number/XPPNOANDGFJQLF6LHXYXBC7TDT/graph.json","events_json":"https://pith.science/api/pith-number/XPPNOANDGFJQLF6LHXYXBC7TDT/events.json","paper":"https://pith.science/paper/XPPNOAND"},"agent_actions":{"view_html":"https://pith.science/pith/XPPNOANDGFJQLF6LHXYXBC7TDT","download_json":"https://pith.science/pith/XPPNOANDGFJQLF6LHXYXBC7TDT.json","view_paper":"https://pith.science/paper/XPPNOAND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00432&json=true","fetch_graph":"https://pith.science/api/pith-number/XPPNOANDGFJQLF6LHXYXBC7TDT/graph.json","fetch_events":"https://pith.science/api/pith-number/XPPNOANDGFJQLF6LHXYXBC7TDT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPPNOANDGFJQLF6LHXYXBC7TDT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPPNOANDGFJQLF6LHXYXBC7TDT/action/storage_attestation","attest_author":"https://pith.science/pith/XPPNOANDGFJQLF6LHXYXBC7TDT/action/author_attestation","sign_citation":"https://pith.science/pith/XPPNOANDGFJQLF6LHXYXBC7TDT/action/citation_signature","submit_replication":"https://pith.science/pith/XPPNOANDGFJQLF6LHXYXBC7TDT/action/replication_record"}},"created_at":"2026-07-05T09:56:05.801884+00:00","updated_at":"2026-07-05T09:56:05.801884+00:00"}