{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RLY7BCHNCNKTXSI6CJFQSIK477","short_pith_number":"pith:RLY7BCHN","schema_version":"1.0","canonical_sha256":"8af1f088ed13553bc91e124b09215cffef588e63a4773f55fb7c526534318668","source":{"kind":"arxiv","id":"2606.00662","version":1},"attestation_state":"computed","paper":{"title":"TAP-JEPA: Frozen Future-Latent Probing and Two-Stage Score Fusion for EPIC-KITCHENS-100 Action Anticipation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoyang Wang, Lexuan Xu","submitted_at":"2026-05-30T10:23:12Z","abstract_excerpt":"This report presents TAP-JEPA, our runner-up submission to the EPIC-KITCHENS-100 (EK-100) Action Anticipation Challenge at EgoVis 2026. The task is to anticipate the next verb, noun, and verb-noun action from an egocentric clip that ends before the target action begins. Instead of fine-tuning a large video backbone, TAP-JEPA builds a compact anticipation model on frozen V-JEPA 2.1 features: a ViT-G/384 encoder extracts visible pre-action tokens, the pre-trained latent predictor estimates near-future tokens from the observed context, and both token groups are fused by attentive probes with task"},"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":"2606.00662","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T10:23:12Z","cross_cats_sorted":[],"title_canon_sha256":"f82e23a397834b8ecd84842102b34f1e428c78d8f71c8778fe2f7aed1e04f292","abstract_canon_sha256":"c1978d80ef1ff31abf2e87f4a4fc4699cda7f2f039dcc4b38289acd30be6bdc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:01.430313Z","signature_b64":"dw5c6o9CKXjH9R/f7yQiMKExk72LxJcm5ED++xZS9RY3bJUfAjmyDgg9StgZ076V67yXBKDkv7ICksp2XPwfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8af1f088ed13553bc91e124b09215cffef588e63a4773f55fb7c526534318668","last_reissued_at":"2026-06-02T01:04:01.429823Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:01.429823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TAP-JEPA: Frozen Future-Latent Probing and Two-Stage Score Fusion for EPIC-KITCHENS-100 Action Anticipation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoyang Wang, Lexuan Xu","submitted_at":"2026-05-30T10:23:12Z","abstract_excerpt":"This report presents TAP-JEPA, our runner-up submission to the EPIC-KITCHENS-100 (EK-100) Action Anticipation Challenge at EgoVis 2026. The task is to anticipate the next verb, noun, and verb-noun action from an egocentric clip that ends before the target action begins. Instead of fine-tuning a large video backbone, TAP-JEPA builds a compact anticipation model on frozen V-JEPA 2.1 features: a ViT-G/384 encoder extracts visible pre-action tokens, the pre-trained latent predictor estimates near-future tokens from the observed context, and both token groups are fused by attentive probes with task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00662","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/2606.00662/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":"2606.00662","created_at":"2026-06-02T01:04:01.429906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00662v1","created_at":"2026-06-02T01:04:01.429906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00662","created_at":"2026-06-02T01:04:01.429906+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLY7BCHNCNKT","created_at":"2026-06-02T01:04:01.429906+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLY7BCHNCNKTXSI6","created_at":"2026-06-02T01:04:01.429906+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLY7BCHN","created_at":"2026-06-02T01:04:01.429906+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/RLY7BCHNCNKTXSI6CJFQSIK477","json":"https://pith.science/pith/RLY7BCHNCNKTXSI6CJFQSIK477.json","graph_json":"https://pith.science/api/pith-number/RLY7BCHNCNKTXSI6CJFQSIK477/graph.json","events_json":"https://pith.science/api/pith-number/RLY7BCHNCNKTXSI6CJFQSIK477/events.json","paper":"https://pith.science/paper/RLY7BCHN"},"agent_actions":{"view_html":"https://pith.science/pith/RLY7BCHNCNKTXSI6CJFQSIK477","download_json":"https://pith.science/pith/RLY7BCHNCNKTXSI6CJFQSIK477.json","view_paper":"https://pith.science/paper/RLY7BCHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00662&json=true","fetch_graph":"https://pith.science/api/pith-number/RLY7BCHNCNKTXSI6CJFQSIK477/graph.json","fetch_events":"https://pith.science/api/pith-number/RLY7BCHNCNKTXSI6CJFQSIK477/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLY7BCHNCNKTXSI6CJFQSIK477/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLY7BCHNCNKTXSI6CJFQSIK477/action/storage_attestation","attest_author":"https://pith.science/pith/RLY7BCHNCNKTXSI6CJFQSIK477/action/author_attestation","sign_citation":"https://pith.science/pith/RLY7BCHNCNKTXSI6CJFQSIK477/action/citation_signature","submit_replication":"https://pith.science/pith/RLY7BCHNCNKTXSI6CJFQSIK477/action/replication_record"}},"created_at":"2026-06-02T01:04:01.429906+00:00","updated_at":"2026-06-02T01:04:01.429906+00:00"}