{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M2326VRZ3WH4BCPKX2UZEVEKK7","short_pith_number":"pith:M2326VRZ","schema_version":"1.0","canonical_sha256":"66b7af5639dd8fc089eabea992548a57e921c2ce3b87c509da5610e5e1d1ffb1","source":{"kind":"arxiv","id":"2506.03709","version":1},"attestation_state":"computed","paper":{"title":"AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Gandhamal, Aniruddh Sikdar, Suresh Sundaram","submitted_at":"2025-06-04T08:41:19Z","abstract_excerpt":"Open-vocabulary semantic segmentation (OVSS) involves assigning labels to each pixel in an image based on textual descriptions, leveraging world models like CLIP. However, they encounter significant challenges in cross-domain generalization, hindering their practical efficacy in real-world applications. Embodied AI systems are transforming autonomous navigation for ground vehicles and drones by enhancing their perception abilities, and in this study, we present AetherVision-Bench, a benchmark for multi-angle segmentation across aerial, and ground perspectives, which facilitates an extensive ev"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.03709","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T08:41:19Z","cross_cats_sorted":[],"title_canon_sha256":"26dee655003c3f2bae673bee92f1dc5c8069776a764ed173fba03f869988587e","abstract_canon_sha256":"e74d7bfc68404a331ebe4377b4a460d6def6295db753de47ded5082c69b1fb2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:50.350463Z","signature_b64":"AVkVGAZGq9AXnArj46qctWkIHGsRBUXDpE8HETULMQahNDKiFAVlFHtbaUExIUyB7WV7RKNKHTm23a2IrNhOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66b7af5639dd8fc089eabea992548a57e921c2ce3b87c509da5610e5e1d1ffb1","last_reissued_at":"2026-07-05T11:15:50.349993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:50.349993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Gandhamal, Aniruddh Sikdar, Suresh Sundaram","submitted_at":"2025-06-04T08:41:19Z","abstract_excerpt":"Open-vocabulary semantic segmentation (OVSS) involves assigning labels to each pixel in an image based on textual descriptions, leveraging world models like CLIP. However, they encounter significant challenges in cross-domain generalization, hindering their practical efficacy in real-world applications. Embodied AI systems are transforming autonomous navigation for ground vehicles and drones by enhancing their perception abilities, and in this study, we present AetherVision-Bench, a benchmark for multi-angle segmentation across aerial, and ground perspectives, which facilitates an extensive ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03709","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/2506.03709/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.03709","created_at":"2026-07-05T11:15:50.350049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03709v1","created_at":"2026-07-05T11:15:50.350049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03709","created_at":"2026-07-05T11:15:50.350049+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2326VRZ3WH4","created_at":"2026-07-05T11:15:50.350049+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2326VRZ3WH4BCPK","created_at":"2026-07-05T11:15:50.350049+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2326VRZ","created_at":"2026-07-05T11:15:50.350049+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2326VRZ3WH4BCPKX2UZEVEKK7","json":"https://pith.science/pith/M2326VRZ3WH4BCPKX2UZEVEKK7.json","graph_json":"https://pith.science/api/pith-number/M2326VRZ3WH4BCPKX2UZEVEKK7/graph.json","events_json":"https://pith.science/api/pith-number/M2326VRZ3WH4BCPKX2UZEVEKK7/events.json","paper":"https://pith.science/paper/M2326VRZ"},"agent_actions":{"view_html":"https://pith.science/pith/M2326VRZ3WH4BCPKX2UZEVEKK7","download_json":"https://pith.science/pith/M2326VRZ3WH4BCPKX2UZEVEKK7.json","view_paper":"https://pith.science/paper/M2326VRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03709&json=true","fetch_graph":"https://pith.science/api/pith-number/M2326VRZ3WH4BCPKX2UZEVEKK7/graph.json","fetch_events":"https://pith.science/api/pith-number/M2326VRZ3WH4BCPKX2UZEVEKK7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2326VRZ3WH4BCPKX2UZEVEKK7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2326VRZ3WH4BCPKX2UZEVEKK7/action/storage_attestation","attest_author":"https://pith.science/pith/M2326VRZ3WH4BCPKX2UZEVEKK7/action/author_attestation","sign_citation":"https://pith.science/pith/M2326VRZ3WH4BCPKX2UZEVEKK7/action/citation_signature","submit_replication":"https://pith.science/pith/M2326VRZ3WH4BCPKX2UZEVEKK7/action/replication_record"}},"created_at":"2026-07-05T11:15:50.350049+00:00","updated_at":"2026-07-05T11:15:50.350049+00:00"}