{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TVETRKS2AIABIT4JOUXWTZ25WZ","short_pith_number":"pith:TVETRKS2","schema_version":"1.0","canonical_sha256":"9d4938aa5a0200144f89752f69e75db671655c9c189234d382f0cc7f20e8be11","source":{"kind":"arxiv","id":"2606.02962","version":1},"attestation_state":"computed","paper":{"title":"Hand Trajectory Fusion for Egocentric Natural Language Query Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","eess.IV"],"primary_cat":"cs.CV","authors_text":"Carlos R. del-Blanco, Enmin Zhong, Fernando Jaureguizar, Narciso Garc\\'ia","submitted_at":"2026-06-01T23:46:18Z","abstract_excerpt":"Egocentric Natural Language Query (NLQ) grounding asks a model to localize, in a long first-person video, the temporal interval that answers a free-form text query. Existing methods fuse video appearance with the query but ignore hand motion, despite the fact that roughly 41% of Ego4D NLQ queries are answered at a moment of hand--object manipulation or their immediate outcomes.We propose a hand-trajectory encoder for converting a sequence of hand skeletons into highly-semantic hand kinematic features, which are then aligned and combined with pretrained video--text features through a cross-atte"},"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":"2606.02962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T23:46:18Z","cross_cats_sorted":["cs.AI","cs.HC","eess.IV"],"title_canon_sha256":"f0fed1b18b6f03655c07ccb012b7edb355b326abe57dbc4d7f8bbeeb8e7c9c58","abstract_canon_sha256":"9ced1e6cb8eae0492de74c4e0a5e7ac8ace81c33ce2b9667bee9437b6b1e6735"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:27.776837Z","signature_b64":"i11RbrqX2VMRC2tJjsvQvR0cGz5MxEqnAQdpy8jMIoiPITnF9YTjgU2zdOJhnLErkSYigVhqjUxHxGUrzA2mBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d4938aa5a0200144f89752f69e75db671655c9c189234d382f0cc7f20e8be11","last_reissued_at":"2026-06-03T01:05:27.776424Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:27.776424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hand Trajectory Fusion for Egocentric Natural Language Query Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","eess.IV"],"primary_cat":"cs.CV","authors_text":"Carlos R. del-Blanco, Enmin Zhong, Fernando Jaureguizar, Narciso Garc\\'ia","submitted_at":"2026-06-01T23:46:18Z","abstract_excerpt":"Egocentric Natural Language Query (NLQ) grounding asks a model to localize, in a long first-person video, the temporal interval that answers a free-form text query. Existing methods fuse video appearance with the query but ignore hand motion, despite the fact that roughly 41% of Ego4D NLQ queries are answered at a moment of hand--object manipulation or their immediate outcomes.We propose a hand-trajectory encoder for converting a sequence of hand skeletons into highly-semantic hand kinematic features, which are then aligned and combined with pretrained video--text features through a cross-atte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02962","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/2606.02962/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":"2606.02962","created_at":"2026-06-03T01:05:27.776480+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02962v1","created_at":"2026-06-03T01:05:27.776480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02962","created_at":"2026-06-03T01:05:27.776480+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVETRKS2AIAB","created_at":"2026-06-03T01:05:27.776480+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVETRKS2AIABIT4J","created_at":"2026-06-03T01:05:27.776480+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVETRKS2","created_at":"2026-06-03T01:05:27.776480+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/TVETRKS2AIABIT4JOUXWTZ25WZ","json":"https://pith.science/pith/TVETRKS2AIABIT4JOUXWTZ25WZ.json","graph_json":"https://pith.science/api/pith-number/TVETRKS2AIABIT4JOUXWTZ25WZ/graph.json","events_json":"https://pith.science/api/pith-number/TVETRKS2AIABIT4JOUXWTZ25WZ/events.json","paper":"https://pith.science/paper/TVETRKS2"},"agent_actions":{"view_html":"https://pith.science/pith/TVETRKS2AIABIT4JOUXWTZ25WZ","download_json":"https://pith.science/pith/TVETRKS2AIABIT4JOUXWTZ25WZ.json","view_paper":"https://pith.science/paper/TVETRKS2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02962&json=true","fetch_graph":"https://pith.science/api/pith-number/TVETRKS2AIABIT4JOUXWTZ25WZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TVETRKS2AIABIT4JOUXWTZ25WZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVETRKS2AIABIT4JOUXWTZ25WZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVETRKS2AIABIT4JOUXWTZ25WZ/action/storage_attestation","attest_author":"https://pith.science/pith/TVETRKS2AIABIT4JOUXWTZ25WZ/action/author_attestation","sign_citation":"https://pith.science/pith/TVETRKS2AIABIT4JOUXWTZ25WZ/action/citation_signature","submit_replication":"https://pith.science/pith/TVETRKS2AIABIT4JOUXWTZ25WZ/action/replication_record"}},"created_at":"2026-06-03T01:05:27.776480+00:00","updated_at":"2026-06-03T01:05:27.776480+00:00"}