{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YZTAU6MQTOE22HVWCY5VMEAQCL","short_pith_number":"pith:YZTAU6MQ","schema_version":"1.0","canonical_sha256":"c6660a79909b89ad1eb6163b56101012db12cf0207a33f539c677d7f8532dc50","source":{"kind":"arxiv","id":"2507.08022","version":1},"attestation_state":"computed","paper":{"title":"CuriosAI Submission to the EgoExo4D Proficiency Estimation Challenge 2025","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aiswariya Manojkumar, Daichi Yamaga, Fumika Beppu, Hayato Tanoue, Hiroki Nishihara, Hiroki Takushima, Mitsuru Takeda, Takayuki Hori, Yuki Shibata, Yuma Suzuki, Yuto Kanda, Zhao Hengwei","submitted_at":"2025-07-08T12:33:02Z","abstract_excerpt":"This report presents the CuriosAI team's submission to the EgoExo4D Proficiency Estimation Challenge at CVPR 2025. We propose two methods for multi-view skill assessment: (1) a multi-task learning framework using Sapiens-2B that jointly predicts proficiency and scenario labels (43.6 % accuracy), and (2) a two-stage pipeline combining zero-shot scenario recognition with view-specific VideoMAE classifiers (47.8 % accuracy). The superior performance of the two-stage approach demonstrates the effectiveness of scenario-conditioned modeling for proficiency estimation."},"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":"2507.08022","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T12:33:02Z","cross_cats_sorted":[],"title_canon_sha256":"ca1fbaae16a82785916d837546e31dd0e17cdb9e5cb9f16df4f6eb309ed026b1","abstract_canon_sha256":"3abac18afe46291f43f6b103dec83d14b03a9727962804040476c9e24c61fdce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:15.876839Z","signature_b64":"jpm0n9AilI5lFwrUtjuVL7ggz2hmQ2Rnb1SM8lIjbGJ5mXiIMhIcCLpE0eE01TUmqX4myl49lwnbs6SeIAWBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6660a79909b89ad1eb6163b56101012db12cf0207a33f539c677d7f8532dc50","last_reissued_at":"2026-07-05T11:35:15.876375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:15.876375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CuriosAI Submission to the EgoExo4D Proficiency Estimation Challenge 2025","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aiswariya Manojkumar, Daichi Yamaga, Fumika Beppu, Hayato Tanoue, Hiroki Nishihara, Hiroki Takushima, Mitsuru Takeda, Takayuki Hori, Yuki Shibata, Yuma Suzuki, Yuto Kanda, Zhao Hengwei","submitted_at":"2025-07-08T12:33:02Z","abstract_excerpt":"This report presents the CuriosAI team's submission to the EgoExo4D Proficiency Estimation Challenge at CVPR 2025. We propose two methods for multi-view skill assessment: (1) a multi-task learning framework using Sapiens-2B that jointly predicts proficiency and scenario labels (43.6 % accuracy), and (2) a two-stage pipeline combining zero-shot scenario recognition with view-specific VideoMAE classifiers (47.8 % accuracy). The superior performance of the two-stage approach demonstrates the effectiveness of scenario-conditioned modeling for proficiency estimation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08022","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/2507.08022/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":"2507.08022","created_at":"2026-07-05T11:35:15.876431+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.08022v1","created_at":"2026-07-05T11:35:15.876431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08022","created_at":"2026-07-05T11:35:15.876431+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZTAU6MQTOE2","created_at":"2026-07-05T11:35:15.876431+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZTAU6MQTOE22HVW","created_at":"2026-07-05T11:35:15.876431+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZTAU6MQ","created_at":"2026-07-05T11:35:15.876431+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/YZTAU6MQTOE22HVWCY5VMEAQCL","json":"https://pith.science/pith/YZTAU6MQTOE22HVWCY5VMEAQCL.json","graph_json":"https://pith.science/api/pith-number/YZTAU6MQTOE22HVWCY5VMEAQCL/graph.json","events_json":"https://pith.science/api/pith-number/YZTAU6MQTOE22HVWCY5VMEAQCL/events.json","paper":"https://pith.science/paper/YZTAU6MQ"},"agent_actions":{"view_html":"https://pith.science/pith/YZTAU6MQTOE22HVWCY5VMEAQCL","download_json":"https://pith.science/pith/YZTAU6MQTOE22HVWCY5VMEAQCL.json","view_paper":"https://pith.science/paper/YZTAU6MQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.08022&json=true","fetch_graph":"https://pith.science/api/pith-number/YZTAU6MQTOE22HVWCY5VMEAQCL/graph.json","fetch_events":"https://pith.science/api/pith-number/YZTAU6MQTOE22HVWCY5VMEAQCL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZTAU6MQTOE22HVWCY5VMEAQCL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZTAU6MQTOE22HVWCY5VMEAQCL/action/storage_attestation","attest_author":"https://pith.science/pith/YZTAU6MQTOE22HVWCY5VMEAQCL/action/author_attestation","sign_citation":"https://pith.science/pith/YZTAU6MQTOE22HVWCY5VMEAQCL/action/citation_signature","submit_replication":"https://pith.science/pith/YZTAU6MQTOE22HVWCY5VMEAQCL/action/replication_record"}},"created_at":"2026-07-05T11:35:15.876431+00:00","updated_at":"2026-07-05T11:35:15.876431+00:00"}