{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KFDSXV5JN7H2OYR2HWE7BEF32N","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":"98e366232c97a38029b36a203ace279ff67aa1936f9c45288ba71f58f552c042","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T07:53:46Z","title_canon_sha256":"b497a7bc9b87f3dc05a1ea9232c3e19d5b4299d331e3024351bd6390ae3877b6"},"schema_version":"1.0","source":{"id":"2406.16384","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16384","created_at":"2026-07-05T08:42:37Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16384v2","created_at":"2026-07-05T08:42:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16384","created_at":"2026-07-05T08:42:37Z"},{"alias_kind":"pith_short_12","alias_value":"KFDSXV5JN7H2","created_at":"2026-07-05T08:42:37Z"},{"alias_kind":"pith_short_16","alias_value":"KFDSXV5JN7H2OYR2","created_at":"2026-07-05T08:42:37Z"},{"alias_kind":"pith_short_8","alias_value":"KFDSXV5J","created_at":"2026-07-05T08:42:37Z"}],"graph_snapshots":[{"event_id":"sha256:76ce17e0fd777a9a39067f68f844d62a90264de1addf69e66f6e37a605cd4776","target":"graph","created_at":"2026-07-05T08:42:37Z","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/2406.16384/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The generalisation to unseen objects in the 6D pose estimation task is very challenging. While Vision-Language Models (VLMs) enable using natural language descriptions to support 6D pose estimation of unseen objects, these solutions underperform compared to model-based methods. In this work we present Horyon, an open-vocabulary VLM-based architecture that addresses relative pose estimation between two scenes of an unseen object, described by a textual prompt only. We use the textual prompt to identify the unseen object in the scenes and then obtain high-resolution multi-scale features. These f","authors_text":"Andrea Cavallaro, Changjae Oh, Davide Boscaini, Fabio Poiesi, Francesco Giuliari, Jaime Corsetti","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T07:53:46Z","title":"High-resolution open-vocabulary object 6D pose estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16384","kind":"arxiv","version":2},"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:a6eb6673cdb078e15f7de5765101c10b0fac007f8e064d24858e84192779085e","target":"record","created_at":"2026-07-05T08:42:37Z","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":"98e366232c97a38029b36a203ace279ff67aa1936f9c45288ba71f58f552c042","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T07:53:46Z","title_canon_sha256":"b497a7bc9b87f3dc05a1ea9232c3e19d5b4299d331e3024351bd6390ae3877b6"},"schema_version":"1.0","source":{"id":"2406.16384","kind":"arxiv","version":2}},"canonical_sha256":"51472bd7a96fcfa7623a3d89f090bbd3564bd8458d3c05d2a5103367d666848c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51472bd7a96fcfa7623a3d89f090bbd3564bd8458d3c05d2a5103367d666848c","first_computed_at":"2026-07-05T08:42:37.452682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:37.452682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kUP0ZV69HSnbhr/ct+C06m4Ln7CD4ocLTwzDbrUSgPeQ6NorSvMDmpwNU19WTzs845gm0DFVmuAXE2+HGXyNDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:37.453187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.16384","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6eb6673cdb078e15f7de5765101c10b0fac007f8e064d24858e84192779085e","sha256:76ce17e0fd777a9a39067f68f844d62a90264de1addf69e66f6e37a605cd4776"],"state_sha256":"3ad0f273419161049a73f80b63bd9dd6ea8a9cbc51feb09a1b75a3d124dcb898"}