{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZRSF2RFCPVI22ENZH4QFTSRAZS","short_pith_number":"pith:ZRSF2RFC","schema_version":"1.0","canonical_sha256":"cc645d44a27d51ad11b93f2059ca20ccb498b4bdfa7adcf57798da12d2e2f33c","source":{"kind":"arxiv","id":"2606.29850","version":1},"attestation_state":"computed","paper":{"title":"Efficient Visual Pointing for Embodied AI:Agent-Driven Data Synthesis, Cross-Block Attention, and Iterative Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianming Xing, Liqiang Nie, Qi Lv, Weili Guan, Xiang Deng, Yuxiang Xie, Zijian Hong","submitted_at":"2026-06-29T06:39:03Z","abstract_excerpt":"Visual pointing maps a language instruction to pixel co ordinates, a core skill for embodied AI. We describe our PointArena 2026 solution, which achieves 77.2% overall accuracy and ranks second on the benchmark. The ap proach targets three failure modes. First, agent-driven syn thesis builds large semantic and anchor-relative candidate pools; the server inventory contains 55,372 processed out puts, 53,772 de-duplicated sample IDs, and 37,574 train able completed or accepted rows. Second, a determinis tic steerable-data pipeline creates a verified 10,000-sample main set, plus reserve samples, u"},"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":"2606.29850","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T06:39:03Z","cross_cats_sorted":[],"title_canon_sha256":"34fb035516c4ac1732da456e0f4865bb43bafd64cbdd6bfa4fba03b689c27bcb","abstract_canon_sha256":"481bebab569bc284f1233c2b445effb18951b7b0e0d10f20f58249f99126751d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:38.075271Z","signature_b64":"6UEuTWTDot4yn5QRfSMdwO2DJVKkZJ24sqTcWpArQ66dU8Ii5nyEmCUg+q3vKj9AeomcDtVCEDlnJHPuBScIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc645d44a27d51ad11b93f2059ca20ccb498b4bdfa7adcf57798da12d2e2f33c","last_reissued_at":"2026-06-30T02:17:38.074681Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:38.074681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Visual Pointing for Embodied AI:Agent-Driven Data Synthesis, Cross-Block Attention, and Iterative Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianming Xing, Liqiang Nie, Qi Lv, Weili Guan, Xiang Deng, Yuxiang Xie, Zijian Hong","submitted_at":"2026-06-29T06:39:03Z","abstract_excerpt":"Visual pointing maps a language instruction to pixel co ordinates, a core skill for embodied AI. We describe our PointArena 2026 solution, which achieves 77.2% overall accuracy and ranks second on the benchmark. The ap proach targets three failure modes. First, agent-driven syn thesis builds large semantic and anchor-relative candidate pools; the server inventory contains 55,372 processed out puts, 53,772 de-duplicated sample IDs, and 37,574 train able completed or accepted rows. Second, a determinis tic steerable-data pipeline creates a verified 10,000-sample main set, plus reserve samples, u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29850","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/2606.29850/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":"2606.29850","created_at":"2026-06-30T02:17:38.074780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29850v1","created_at":"2026-06-30T02:17:38.074780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29850","created_at":"2026-06-30T02:17:38.074780+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRSF2RFCPVI2","created_at":"2026-06-30T02:17:38.074780+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRSF2RFCPVI22ENZ","created_at":"2026-06-30T02:17:38.074780+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRSF2RFC","created_at":"2026-06-30T02:17:38.074780+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/ZRSF2RFCPVI22ENZH4QFTSRAZS","json":"https://pith.science/pith/ZRSF2RFCPVI22ENZH4QFTSRAZS.json","graph_json":"https://pith.science/api/pith-number/ZRSF2RFCPVI22ENZH4QFTSRAZS/graph.json","events_json":"https://pith.science/api/pith-number/ZRSF2RFCPVI22ENZH4QFTSRAZS/events.json","paper":"https://pith.science/paper/ZRSF2RFC"},"agent_actions":{"view_html":"https://pith.science/pith/ZRSF2RFCPVI22ENZH4QFTSRAZS","download_json":"https://pith.science/pith/ZRSF2RFCPVI22ENZH4QFTSRAZS.json","view_paper":"https://pith.science/paper/ZRSF2RFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29850&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRSF2RFCPVI22ENZH4QFTSRAZS/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRSF2RFCPVI22ENZH4QFTSRAZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRSF2RFCPVI22ENZH4QFTSRAZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRSF2RFCPVI22ENZH4QFTSRAZS/action/storage_attestation","attest_author":"https://pith.science/pith/ZRSF2RFCPVI22ENZH4QFTSRAZS/action/author_attestation","sign_citation":"https://pith.science/pith/ZRSF2RFCPVI22ENZH4QFTSRAZS/action/citation_signature","submit_replication":"https://pith.science/pith/ZRSF2RFCPVI22ENZH4QFTSRAZS/action/replication_record"}},"created_at":"2026-06-30T02:17:38.074780+00:00","updated_at":"2026-06-30T02:17:38.074780+00:00"}