{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KFDSXV5JN7H2OYR2HWE7BEF32N","short_pith_number":"pith:KFDSXV5J","canonical_record":{"source":{"id":"2406.16384","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T07:53:46Z","cross_cats_sorted":[],"title_canon_sha256":"b497a7bc9b87f3dc05a1ea9232c3e19d5b4299d331e3024351bd6390ae3877b6","abstract_canon_sha256":"98e366232c97a38029b36a203ace279ff67aa1936f9c45288ba71f58f552c042"},"schema_version":"1.0"},"canonical_sha256":"51472bd7a96fcfa7623a3d89f090bbd3564bd8458d3c05d2a5103367d666848c","source":{"kind":"arxiv","id":"2406.16384","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KFDSXV5JN7H2OYR2HWE7BEF32N","target":"record","payload":{"canonical_record":{"source":{"id":"2406.16384","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T07:53:46Z","cross_cats_sorted":[],"title_canon_sha256":"b497a7bc9b87f3dc05a1ea9232c3e19d5b4299d331e3024351bd6390ae3877b6","abstract_canon_sha256":"98e366232c97a38029b36a203ace279ff67aa1936f9c45288ba71f58f552c042"},"schema_version":"1.0"},"canonical_sha256":"51472bd7a96fcfa7623a3d89f090bbd3564bd8458d3c05d2a5103367d666848c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:37.453187Z","signature_b64":"kUP0ZV69HSnbhr/ct+C06m4Ln7CD4ocLTwzDbrUSgPeQ6NorSvMDmpwNU19WTzs845gm0DFVmuAXE2+HGXyNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51472bd7a96fcfa7623a3d89f090bbd3564bd8458d3c05d2a5103367d666848c","last_reissued_at":"2026-07-05T08:42:37.452682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:37.452682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.16384","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:42:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CSyBvsbFIuWmRTG79x8eT54nDjeqsU1sZ+V7OAh2lTMEDCEQKESnxOS/EVA+dyHxP3+XyiWnV+vUEUzy9e1XCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:59:34.738199Z"},"content_sha256":"a6eb6673cdb078e15f7de5765101c10b0fac007f8e064d24858e84192779085e","schema_version":"1.0","event_id":"sha256:a6eb6673cdb078e15f7de5765101c10b0fac007f8e064d24858e84192779085e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KFDSXV5JN7H2OYR2HWE7BEF32N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"High-resolution open-vocabulary object 6D pose estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Cavallaro, Changjae Oh, Davide Boscaini, Fabio Poiesi, Francesco Giuliari, Jaime Corsetti","submitted_at":"2024-06-24T07:53:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16384","kind":"arxiv","version":2},"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/2406.16384/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":"2026-07-05T08:42:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZoRITgO954gdU4CL0yLM4Fk/CMwS5Rdr7Zz5oEtUfvicMEZvgLSsnPB5kz0HRYSzF4v5rE/5KgRVvulRG1gJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:59:34.738692Z"},"content_sha256":"76ce17e0fd777a9a39067f68f844d62a90264de1addf69e66f6e37a605cd4776","schema_version":"1.0","event_id":"sha256:76ce17e0fd777a9a39067f68f844d62a90264de1addf69e66f6e37a605cd4776"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KFDSXV5JN7H2OYR2HWE7BEF32N/bundle.json","state_url":"https://pith.science/pith/KFDSXV5JN7H2OYR2HWE7BEF32N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KFDSXV5JN7H2OYR2HWE7BEF32N/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":"2026-08-08T12:59:34Z","links":{"resolver":"https://pith.science/pith/KFDSXV5JN7H2OYR2HWE7BEF32N","bundle":"https://pith.science/pith/KFDSXV5JN7H2OYR2HWE7BEF32N/bundle.json","state":"https://pith.science/pith/KFDSXV5JN7H2OYR2HWE7BEF32N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KFDSXV5JN7H2OYR2HWE7BEF32N/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4/dWXqmByKdbwPci+cvXQEnCMCFkrUXQjPFtKvaAKRh7WEAwNp86LiwDJ5EaaAjEUwOLsOzFwukp9jMxGqNDBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:59:34.743572Z","bundle_sha256":"9fc90cb0ddcc0a025afb437c0468ee1f6dce249b9e1dfdda8932894b267e87f9"}}