{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HI4YBZLQBR2Z23AW7D76MNFLAM","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":"fae4c5f276c2bff90fef776cedccd8bd2fc135d9dc35d1065963d37d3a128fea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T08:55:18Z","title_canon_sha256":"715c5c33e06ea7f7f1c33f7dbadecd57192ea76306f263ff560db83edf28b2e4"},"schema_version":"1.0","source":{"id":"2411.10745","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10745","created_at":"2026-07-05T11:38:01Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10745v4","created_at":"2026-07-05T11:38:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10745","created_at":"2026-07-05T11:38:01Z"},{"alias_kind":"pith_short_12","alias_value":"HI4YBZLQBR2Z","created_at":"2026-07-05T11:38:01Z"},{"alias_kind":"pith_short_16","alias_value":"HI4YBZLQBR2Z23AW","created_at":"2026-07-05T11:38:01Z"},{"alias_kind":"pith_short_8","alias_value":"HI4YBZLQ","created_at":"2026-07-05T11:38:01Z"}],"graph_snapshots":[{"event_id":"sha256:9b3494558f1946fed2e7cdf2b7dcafea7658d65cd74be93ad286d52bf471ec21","target":"graph","created_at":"2026-07-05T11:38:01Z","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/2411.10745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In zero-shot skeleton-based action recognition (ZSAR), aligning skeleton features with the text features of action labels is essential for accurately predicting unseen actions. ZSAR faces a fundamental challenge in bridging the modality gap between the two-kind features, which severely limits generalization to unseen actions. Previous methods focus on direct alignment between skeleton and text latent spaces, but the modality gaps between these spaces hinder robust generalization learning. Motivated by the success of diffusion models in multi-modal alignment (e.g., text-to-image, text-to-video)","authors_text":"Jeonghyeok Do, Munchurl Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T08:55:18Z","title":"Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10745","kind":"arxiv","version":4},"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:e613c9bf375e3e0bc3a731f04ad91519f5474380e663d383c1dc0a0f78760986","target":"record","created_at":"2026-07-05T11:38:01Z","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":"fae4c5f276c2bff90fef776cedccd8bd2fc135d9dc35d1065963d37d3a128fea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T08:55:18Z","title_canon_sha256":"715c5c33e06ea7f7f1c33f7dbadecd57192ea76306f263ff560db83edf28b2e4"},"schema_version":"1.0","source":{"id":"2411.10745","kind":"arxiv","version":4}},"canonical_sha256":"3a3980e5700c759d6c16f8ffe634ab031af3b0e666020908a7a225fcc8dfb933","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a3980e5700c759d6c16f8ffe634ab031af3b0e666020908a7a225fcc8dfb933","first_computed_at":"2026-07-05T11:38:01.924622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:01.924622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z8fDsBYHQNCrbxD4Ig+fDUChYhRFTnatuBQujka/8G1nqn5v/vLkiYBO75Hi3SDzuKf6BIKk1fl8gzw7vNd3Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:01.925113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10745","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e613c9bf375e3e0bc3a731f04ad91519f5474380e663d383c1dc0a0f78760986","sha256:9b3494558f1946fed2e7cdf2b7dcafea7658d65cd74be93ad286d52bf471ec21"],"state_sha256":"482f9923caec05655a760c9dc11a54d3b594f50f895bd6923a5480544b9f09c6"}