{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:23YL5AMYDUWLBMQ7OXLQBYKBUW","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":"11d19028afcbb0ed801beb7fbec1c507057cccc8e0e838f5347c2449c0a66469","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T12:38:36Z","title_canon_sha256":"61a4010b97212c33abade29c0c061dbaa3b349deca0564d1484b8cdf023ed98d"},"schema_version":"1.0","source":{"id":"2606.23256","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23256","created_at":"2026-06-23T03:14:15Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23256v1","created_at":"2026-06-23T03:14:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23256","created_at":"2026-06-23T03:14:15Z"},{"alias_kind":"pith_short_12","alias_value":"23YL5AMYDUWL","created_at":"2026-06-23T03:14:15Z"},{"alias_kind":"pith_short_16","alias_value":"23YL5AMYDUWLBMQ7","created_at":"2026-06-23T03:14:15Z"},{"alias_kind":"pith_short_8","alias_value":"23YL5AMY","created_at":"2026-06-23T03:14:15Z"}],"graph_snapshots":[{"event_id":"sha256:49f5653a0b661dc2f38212964e3ab69546c01221d356b2c474940b6403021c64","target":"graph","created_at":"2026-06-23T03:14:15Z","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/2606.23256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing maturity of embodied AI platforms has driven a growing interest in procedural video representation learning to support intelligent assistance systems for complex, multi-step tasks. Leveraging large-scale latent predictive training, video foundation models capture video dynamics, enabling downstream tasks such as activity understanding, spatiotemporal localization, and predictive control. However, procedural videos include actions with long-range dependencies that these models do not support, due to the quadratic complexity of self-attention. Distinct actions, for example, may be","authors_text":"Benjamin Killeen, Christian Benz, Felix Tristram, Ghazal Ghazaei, Marcel Walch, Nassir Navab, Stefano Gasperini","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T12:38:36Z","title":"P-JEPA: Procedural Video Representation Learning via Joint Embedding Predictive Architecture"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23256","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":"sha256:0ac0ad963941dbcf8570ee060628cd76edc66114feeaece92beed0dcd5871538","target":"record","created_at":"2026-06-23T03:14:15Z","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":"11d19028afcbb0ed801beb7fbec1c507057cccc8e0e838f5347c2449c0a66469","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T12:38:36Z","title_canon_sha256":"61a4010b97212c33abade29c0c061dbaa3b349deca0564d1484b8cdf023ed98d"},"schema_version":"1.0","source":{"id":"2606.23256","kind":"arxiv","version":1}},"canonical_sha256":"d6f0be81981d2cb0b21f75d700e141a587af93e7a132301c4ab1d7422f9b4e43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6f0be81981d2cb0b21f75d700e141a587af93e7a132301c4ab1d7422f9b4e43","first_computed_at":"2026-06-23T03:14:15.050780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:15.050780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O67/8RwqG1lxvyt3fNZetOiskpQ4Wvht9o8AR8Wb6LOydFywbGgH2vTdvB8V0XCtuplNwOKa8hAeWhviFmUJDg==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:15.051175Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23256","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ac0ad963941dbcf8570ee060628cd76edc66114feeaece92beed0dcd5871538","sha256:49f5653a0b661dc2f38212964e3ab69546c01221d356b2c474940b6403021c64"],"state_sha256":"ace6173082f76df6efce80aeda78472a215a47c1cd4372107e70524d37beb873"}