{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EYTEARKZJG57IFPHB5UGLSVLYL","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":"4e99126b1636c3cd1e918d92681015288be02fcdad3a1553bb8c2fa59196d55c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-12T15:09:33Z","title_canon_sha256":"5de1a8eb8a824f7d493c4b0a629030c1b674b79b05e0786d55bec4c0e788e34c"},"schema_version":"1.0","source":{"id":"2607.10797","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10797","created_at":"2026-07-14T01:21:40Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10797v1","created_at":"2026-07-14T01:21:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10797","created_at":"2026-07-14T01:21:40Z"},{"alias_kind":"pith_short_12","alias_value":"EYTEARKZJG57","created_at":"2026-07-14T01:21:40Z"},{"alias_kind":"pith_short_16","alias_value":"EYTEARKZJG57IFPH","created_at":"2026-07-14T01:21:40Z"},{"alias_kind":"pith_short_8","alias_value":"EYTEARKZ","created_at":"2026-07-14T01:21:40Z"}],"graph_snapshots":[{"event_id":"sha256:1afa9d1c2c32ae5fd7a52a88f6597dc33de3f0f7ecfb94c5c71d234c1b1eb649","target":"graph","created_at":"2026-07-14T01:21:40Z","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/2607.10797/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Assembly action understanding is a key enabler for effective human-robot collaborative assembly, yet it remains challenging due to subtle motions and fine-grained hand-object interactions. We adapt vision-language models (VLMs) to this challenging domain with Compositional Context Fine-Tuning (CCFT), a method that decomposes assembly actions into semantic elements (Verb, Object, Tool) and fine-tunes VLMs to recognize each action element using templated question-answering pairs. This approach ensures near-deterministic outputs. To enable efficient and effective multi-task learning under limited","authors_text":"Hao Zheng, Jinyi Huang, Tiantian Zheng, Tuka Alhanai, Xun Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-12T15:09:33Z","title":"Compositional Context Fine-Tuning Vision-Language Model for Complex Assembly Action Understanding from Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10797","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":"sha256:439af636beb42f347cbb8d1c7f259122b68570feaa9d9e0e6eacbae63d940185","target":"record","created_at":"2026-07-14T01:21:40Z","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":"4e99126b1636c3cd1e918d92681015288be02fcdad3a1553bb8c2fa59196d55c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-12T15:09:33Z","title_canon_sha256":"5de1a8eb8a824f7d493c4b0a629030c1b674b79b05e0786d55bec4c0e788e34c"},"schema_version":"1.0","source":{"id":"2607.10797","kind":"arxiv","version":1}},"canonical_sha256":"262640455949bbf415e70f6865caabc2cb466994e1c90d32a034f1571d9e4cb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"262640455949bbf415e70f6865caabc2cb466994e1c90d32a034f1571d9e4cb0","first_computed_at":"2026-07-14T01:21:40.601967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:21:40.601967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kMUeLDHeWP7eAkY2n6Rnadm6l+dV7eTqTQ0NI4uC8gJiINnzK2foPMuUAbjUZkjTOKcsbQzqr4ugl62DYiwmBQ==","signature_status":"signed_v1","signed_at":"2026-07-14T01:21:40.602788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.10797","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:439af636beb42f347cbb8d1c7f259122b68570feaa9d9e0e6eacbae63d940185","sha256:1afa9d1c2c32ae5fd7a52a88f6597dc33de3f0f7ecfb94c5c71d234c1b1eb649"],"state_sha256":"485bc2f4ddae5dcfff8521cabfbd23496a23291960a84cf312e6762f7148731d"}