{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ORPTBQR5HECWKPMSVVUMMZ2ASF","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":"e6314d38c9e0e952f037352a9f55ed5f7075d669632a4d743ca8573ae936838e","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-08T18:05:21Z","title_canon_sha256":"e15639d7d75665be1cf9a8ac12b387870f114de6965a630cb98696a6ead5f18b"},"schema_version":"1.0","source":{"id":"2608.08273","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08273","created_at":"2026-08-11T01:22:11Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08273v1","created_at":"2026-08-11T01:22:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08273","created_at":"2026-08-11T01:22:11Z"},{"alias_kind":"pith_short_12","alias_value":"ORPTBQR5HECW","created_at":"2026-08-11T01:22:11Z"},{"alias_kind":"pith_short_16","alias_value":"ORPTBQR5HECWKPMS","created_at":"2026-08-11T01:22:11Z"},{"alias_kind":"pith_short_8","alias_value":"ORPTBQR5","created_at":"2026-08-11T01:22:11Z"}],"graph_snapshots":[{"event_id":"sha256:5bd8c159644dcc84f1db26b0d07dc2b38f8f81ee198c079fa240646be56cefe7","target":"graph","created_at":"2026-08-11T01:22:11Z","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/2608.08273/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-based embodied agents executing multi-step natural language instructions require feedback mechanisms that assess task progress over complete trajectories. Conventional approaches based on final-frame matching or continuous embedding similarity may overlook intermediate transitions that are necessary for determining whether an instruction has been completed. We propose ALVA (Action- and Language-Conditioned Video Assessment), a trajectory evaluator that conditions its assessment on visual observations, the executed action sequence, and the natural language instruction. The method uses a ","authors_text":"Chang D. Yoo, Donghoon Lee, Hwanhee Kim, Hyeonseo Yun, Jaehyun Jang, Seungmin Cha","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-08T18:05:21Z","title":"Action- and Language-Conditioned Video Assessment for Embodied Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08273","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":"sha256:5488bb0fcb67d67f909fd9b9379487525357ec504a9024c7d35adce330da47dd","target":"record","created_at":"2026-08-11T01:22:11Z","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":"e6314d38c9e0e952f037352a9f55ed5f7075d669632a4d743ca8573ae936838e","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-08T18:05:21Z","title_canon_sha256":"e15639d7d75665be1cf9a8ac12b387870f114de6965a630cb98696a6ead5f18b"},"schema_version":"1.0","source":{"id":"2608.08273","kind":"arxiv","version":1}},"canonical_sha256":"745f30c23d3905653d92ad68c66740917c4b020df573420e983bb82f90462876","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"745f30c23d3905653d92ad68c66740917c4b020df573420e983bb82f90462876","first_computed_at":"2026-08-11T01:22:11.074242Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:22:11.074242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R7rqB8fmsv/gXrKmVsZI1cCRZW2Bd1Usdck3tcXknbloIFay+NWTqOvnqUIe4dZ5dbmwwpIlMQlRJwAdLXZYCg==","signature_status":"signed_v1","signed_at":"2026-08-11T01:22:11.076754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08273","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5488bb0fcb67d67f909fd9b9379487525357ec504a9024c7d35adce330da47dd","sha256:5bd8c159644dcc84f1db26b0d07dc2b38f8f81ee198c079fa240646be56cefe7"],"state_sha256":"b04e28bdfff06a83b49416d3bb1276f9382b3761285581395485d2e907ced59c"}