{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WD2V3CF7PPG2ZKGNKDK5CTB65V","short_pith_number":"pith:WD2V3CF7","canonical_record":{"source":{"id":"2606.00556","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T06:13:42Z","cross_cats_sorted":[],"title_canon_sha256":"9630a514c8f01ba5ad35c1607a73be393196e47f1f7729766b08a8f44b74cf83","abstract_canon_sha256":"f14b483220ae646fd70fe62bb200a7fbee0517ed234cf088503f6e3070ceef95"},"schema_version":"1.0"},"canonical_sha256":"b0f55d88bf7bcdaca8cd50d5d14c3eed59b7412efe184f424f8355eabaee0cdc","source":{"kind":"arxiv","id":"2606.00556","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00556","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00556v1","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00556","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"WD2V3CF7PPG2","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"WD2V3CF7PPG2ZKGN","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"WD2V3CF7","created_at":"2026-06-02T01:03:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WD2V3CF7PPG2ZKGNKDK5CTB65V","target":"record","payload":{"canonical_record":{"source":{"id":"2606.00556","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T06:13:42Z","cross_cats_sorted":[],"title_canon_sha256":"9630a514c8f01ba5ad35c1607a73be393196e47f1f7729766b08a8f44b74cf83","abstract_canon_sha256":"f14b483220ae646fd70fe62bb200a7fbee0517ed234cf088503f6e3070ceef95"},"schema_version":"1.0"},"canonical_sha256":"b0f55d88bf7bcdaca8cd50d5d14c3eed59b7412efe184f424f8355eabaee0cdc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:58.114640Z","signature_b64":"oQb4F2k/u5zTjTYRFMrf3wUFMH7outytdbRhJ3AsxB6MKrL4zSLYe6NgymAwv+0Yk3jRpDpUZK3KET0L8bXEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0f55d88bf7bcdaca8cd50d5d14c3eed59b7412efe184f424f8355eabaee0cdc","last_reissued_at":"2026-06-02T01:03:58.114205Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:58.114205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.00556","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g5uJD25Eu0Iuz1HF/OLknTWYF1/Gl5NdWqz8qDH5XcH/PH87vzuW3O1kkEOLmylOSYG3+Blb4osTYchXi06aAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T22:14:08.125166Z"},"content_sha256":"63e4e8aba6d4de6586d3cab0d4cc0852b912046039d14e91ef8573d58f31dbea","schema_version":"1.0","event_id":"sha256:63e4e8aba6d4de6586d3cab0d4cc0852b912046039d14e91ef8573d58f31dbea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WD2V3CF7PPG2ZKGNKDK5CTB65V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Visual Grounding in Remote Sensing via Cluster-Guided Refinement and Model Ensemble Voting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ashutosh Gandhe, Geet Sethi, Panav Shah","submitted_at":"2026-05-30T06:13:42Z","abstract_excerpt":"Visual grounding aims to locate image regions that correspond to natural language descriptions and is a key component of interpretable vision systems. In remote sensing imagery, grounding is particularly challenging due to complex scenes, small objects, and large variations in scale. Relying on a single model is often insufficient to address these diverse challenges. In this work, we propose two grounding pipelines, Sequential Grounding Refinement (SGR) and Cluster-Aware Grounding Refinement (CGR), that combine the complementary strengths of RemoteSAM, a visual grounding model specialized for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00556","kind":"arxiv","version":1},"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/2606.00556/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":"2026-06-02T01:03:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hhF6ACrr7a24ueYxtKbEuKWQrrtfLwmJbPMthihy2Z5wlFbe//Mwaj3CXc6JBEKOG2ORdvR5fV5WUUL6J6agBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T22:14:08.125566Z"},"content_sha256":"4d83fb677fd3d9549e714dcbc092580fedc53084dc7e80a32d4ace2c0b4c9149","schema_version":"1.0","event_id":"sha256:4d83fb677fd3d9549e714dcbc092580fedc53084dc7e80a32d4ace2c0b4c9149"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WD2V3CF7PPG2ZKGNKDK5CTB65V/bundle.json","state_url":"https://pith.science/pith/WD2V3CF7PPG2ZKGNKDK5CTB65V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WD2V3CF7PPG2ZKGNKDK5CTB65V/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":"2026-06-10T22:14:08Z","links":{"resolver":"https://pith.science/pith/WD2V3CF7PPG2ZKGNKDK5CTB65V","bundle":"https://pith.science/pith/WD2V3CF7PPG2ZKGNKDK5CTB65V/bundle.json","state":"https://pith.science/pith/WD2V3CF7PPG2ZKGNKDK5CTB65V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WD2V3CF7PPG2ZKGNKDK5CTB65V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WD2V3CF7PPG2ZKGNKDK5CTB65V","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":"f14b483220ae646fd70fe62bb200a7fbee0517ed234cf088503f6e3070ceef95","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T06:13:42Z","title_canon_sha256":"9630a514c8f01ba5ad35c1607a73be393196e47f1f7729766b08a8f44b74cf83"},"schema_version":"1.0","source":{"id":"2606.00556","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00556","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00556v1","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00556","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"WD2V3CF7PPG2","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"WD2V3CF7PPG2ZKGN","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"WD2V3CF7","created_at":"2026-06-02T01:03:58Z"}],"graph_snapshots":[{"event_id":"sha256:4d83fb677fd3d9549e714dcbc092580fedc53084dc7e80a32d4ace2c0b4c9149","target":"graph","created_at":"2026-06-02T01:03:58Z","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/2606.00556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual grounding aims to locate image regions that correspond to natural language descriptions and is a key component of interpretable vision systems. In remote sensing imagery, grounding is particularly challenging due to complex scenes, small objects, and large variations in scale. Relying on a single model is often insufficient to address these diverse challenges. In this work, we propose two grounding pipelines, Sequential Grounding Refinement (SGR) and Cluster-Aware Grounding Refinement (CGR), that combine the complementary strengths of RemoteSAM, a visual grounding model specialized for ","authors_text":"Ashutosh Gandhe, Geet Sethi, Panav Shah","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T06:13:42Z","title":"Improving Visual Grounding in Remote Sensing via Cluster-Guided Refinement and Model Ensemble Voting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00556","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":"sha256:63e4e8aba6d4de6586d3cab0d4cc0852b912046039d14e91ef8573d58f31dbea","target":"record","created_at":"2026-06-02T01:03:58Z","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":"f14b483220ae646fd70fe62bb200a7fbee0517ed234cf088503f6e3070ceef95","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T06:13:42Z","title_canon_sha256":"9630a514c8f01ba5ad35c1607a73be393196e47f1f7729766b08a8f44b74cf83"},"schema_version":"1.0","source":{"id":"2606.00556","kind":"arxiv","version":1}},"canonical_sha256":"b0f55d88bf7bcdaca8cd50d5d14c3eed59b7412efe184f424f8355eabaee0cdc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0f55d88bf7bcdaca8cd50d5d14c3eed59b7412efe184f424f8355eabaee0cdc","first_computed_at":"2026-06-02T01:03:58.114205Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:58.114205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oQb4F2k/u5zTjTYRFMrf3wUFMH7outytdbRhJ3AsxB6MKrL4zSLYe6NgymAwv+0Yk3jRpDpUZK3KET0L8bXEAw==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:58.114640Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00556","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63e4e8aba6d4de6586d3cab0d4cc0852b912046039d14e91ef8573d58f31dbea","sha256:4d83fb677fd3d9549e714dcbc092580fedc53084dc7e80a32d4ace2c0b4c9149"],"state_sha256":"1945a1494b19c402a962d928df510279ee4bb0d69f08cd7ea3062ffd0b4d34ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AOgDA3OazvuCRw60MQfK3LBbRrlCHX0YYwkyg5Wqgr90i5VwxpRFvPvEvGv7iMmRG8rGy50QI6aCobOK2ZWdAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T22:14:08.127505Z","bundle_sha256":"0005032132fbf5ebb14df76e94c4e616c53afe31b8ba2cacb4e8360e36aada6e"}}