{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WFLSQ2VLCUTDJHEMJTS6OCOSLE","short_pith_number":"pith:WFLSQ2VL","canonical_record":{"source":{"id":"2509.00692","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T04:18:12Z","cross_cats_sorted":[],"title_canon_sha256":"cc5ec9fac0c83f667667dae9858a521b59ff51ca5b0c316a23825f0c4acf2af4","abstract_canon_sha256":"33e860a4788ba08d84385a97372c1065caa09837d2376b9bcb06b0247621c00e"},"schema_version":"1.0"},"canonical_sha256":"b157286aab1526349c8c4ce5e709d25927381dde7a5f29606f7d7bbec3fde4d3","source":{"kind":"arxiv","id":"2509.00692","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00692","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00692v1","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00692","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"WFLSQ2VLCUTD","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"WFLSQ2VLCUTDJHEM","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"WFLSQ2VL","created_at":"2026-07-05T12:02:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WFLSQ2VLCUTDJHEMJTS6OCOSLE","target":"record","payload":{"canonical_record":{"source":{"id":"2509.00692","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T04:18:12Z","cross_cats_sorted":[],"title_canon_sha256":"cc5ec9fac0c83f667667dae9858a521b59ff51ca5b0c316a23825f0c4acf2af4","abstract_canon_sha256":"33e860a4788ba08d84385a97372c1065caa09837d2376b9bcb06b0247621c00e"},"schema_version":"1.0"},"canonical_sha256":"b157286aab1526349c8c4ce5e709d25927381dde7a5f29606f7d7bbec3fde4d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:21.238353Z","signature_b64":"CUshbktZzcz10W9+3vDSZfrX07fuanhcMJIVChWdvnG8+7GTf1hd7Zp6lMIVwCZeMU+klQJ0HMOfnBDupXkyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b157286aab1526349c8c4ce5e709d25927381dde7a5f29606f7d7bbec3fde4d3","last_reissued_at":"2026-07-05T12:02:21.237930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:21.237930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.00692","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:02:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ga0t/f/QFa4PvNaA+4bxCYAoFGfWPUIc35fat6JR9jJMCUn1POqUmF/K6kbXNqYgS/nuhpcf18H87FOkxduoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:48:15.511765Z"},"content_sha256":"25becc09c929d7de2618f65682251eef091d0f542a6d1cb3df9fac7b79adf47b","schema_version":"1.0","event_id":"sha256:25becc09c929d7de2618f65682251eef091d0f542a6d1cb3df9fac7b79adf47b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WFLSQ2VLCUTDJHEMJTS6OCOSLE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CascadeFormer: A Family of Two-stage Cascading Transformers for Skeleton-based Human Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alper Yilmaz, Yusen Peng","submitted_at":"2025-08-31T04:18:12Z","abstract_excerpt":"Skeleton-based human action recognition leverages sequences of human joint coordinates to identify actions performed in videos. Owing to the intrinsic spatiotemporal structure of skeleton data, Graph Convolutional Networks (GCNs) have been the dominant architecture in this field. However, recent advances in transformer models and masked pretraining frameworks open new avenues for representation learning. In this work, we propose CascadeFormer, a family of two-stage cascading transformers for skeleton-based human action recognition. Our framework consists of a masked pretraining stage to learn "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00692","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/2509.00692/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:02:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nJVnGD70ekjpYhIbk26joUq2lYahU8erToaak3hZko8WiswmdrMBDDKdnAagA0qM7tOwd3NwydLwV1PoG5O4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:48:15.512569Z"},"content_sha256":"cdedfb294f10ac2dae2b75391e55b17ec5308108c9685543ff9b86050c0ab3a1","schema_version":"1.0","event_id":"sha256:cdedfb294f10ac2dae2b75391e55b17ec5308108c9685543ff9b86050c0ab3a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WFLSQ2VLCUTDJHEMJTS6OCOSLE/bundle.json","state_url":"https://pith.science/pith/WFLSQ2VLCUTDJHEMJTS6OCOSLE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WFLSQ2VLCUTDJHEMJTS6OCOSLE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T00:48:15Z","links":{"resolver":"https://pith.science/pith/WFLSQ2VLCUTDJHEMJTS6OCOSLE","bundle":"https://pith.science/pith/WFLSQ2VLCUTDJHEMJTS6OCOSLE/bundle.json","state":"https://pith.science/pith/WFLSQ2VLCUTDJHEMJTS6OCOSLE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WFLSQ2VLCUTDJHEMJTS6OCOSLE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WFLSQ2VLCUTDJHEMJTS6OCOSLE","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":"33e860a4788ba08d84385a97372c1065caa09837d2376b9bcb06b0247621c00e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T04:18:12Z","title_canon_sha256":"cc5ec9fac0c83f667667dae9858a521b59ff51ca5b0c316a23825f0c4acf2af4"},"schema_version":"1.0","source":{"id":"2509.00692","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00692","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00692v1","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00692","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"WFLSQ2VLCUTD","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"WFLSQ2VLCUTDJHEM","created_at":"2026-07-05T12:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"WFLSQ2VL","created_at":"2026-07-05T12:02:21Z"}],"graph_snapshots":[{"event_id":"sha256:cdedfb294f10ac2dae2b75391e55b17ec5308108c9685543ff9b86050c0ab3a1","target":"graph","created_at":"2026-07-05T12:02:21Z","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/2509.00692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Skeleton-based human action recognition leverages sequences of human joint coordinates to identify actions performed in videos. Owing to the intrinsic spatiotemporal structure of skeleton data, Graph Convolutional Networks (GCNs) have been the dominant architecture in this field. However, recent advances in transformer models and masked pretraining frameworks open new avenues for representation learning. In this work, we propose CascadeFormer, a family of two-stage cascading transformers for skeleton-based human action recognition. Our framework consists of a masked pretraining stage to learn ","authors_text":"Alper Yilmaz, Yusen Peng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T04:18:12Z","title":"CascadeFormer: A Family of Two-stage Cascading Transformers for Skeleton-based Human Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00692","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":"sha256:25becc09c929d7de2618f65682251eef091d0f542a6d1cb3df9fac7b79adf47b","target":"record","created_at":"2026-07-05T12:02:21Z","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":"33e860a4788ba08d84385a97372c1065caa09837d2376b9bcb06b0247621c00e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T04:18:12Z","title_canon_sha256":"cc5ec9fac0c83f667667dae9858a521b59ff51ca5b0c316a23825f0c4acf2af4"},"schema_version":"1.0","source":{"id":"2509.00692","kind":"arxiv","version":1}},"canonical_sha256":"b157286aab1526349c8c4ce5e709d25927381dde7a5f29606f7d7bbec3fde4d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b157286aab1526349c8c4ce5e709d25927381dde7a5f29606f7d7bbec3fde4d3","first_computed_at":"2026-07-05T12:02:21.237930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:21.237930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CUshbktZzcz10W9+3vDSZfrX07fuanhcMJIVChWdvnG8+7GTf1hd7Zp6lMIVwCZeMU+klQJ0HMOfnBDupXkyBg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:21.238353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00692","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25becc09c929d7de2618f65682251eef091d0f542a6d1cb3df9fac7b79adf47b","sha256:cdedfb294f10ac2dae2b75391e55b17ec5308108c9685543ff9b86050c0ab3a1"],"state_sha256":"2aa49385db517d2d269ed1d26d5c3fd9f741c6c5bcc314bd8f3fed69908590f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w3sA+rs8ILzgY7rpqWE8wpxvxOuax71gpehPuqYxDLv6ox3HyRhs2uWCoqmJDJErT5/i8RBV5PdN0l6ND3oXBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:48:15.519685Z","bundle_sha256":"17a67cb59bc5faa67e4d48f1442476d371c9ab0592d3ccc0c94a5e76797d8561"}}