{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OPPN4AK6U5HKXGBBHXXFPLN76F","short_pith_number":"pith:OPPN4AK6","schema_version":"1.0","canonical_sha256":"73dede015ea74eab98213dee57adbff16e328b9bec48fb2e8fae432674cc86d4","source":{"kind":"arxiv","id":"2606.05031","version":1},"attestation_state":"computed","paper":{"title":"MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dewei Zhou, Ji Xie, Kunchang Li, Liang Li, Xinyu Huang, Xun Wang, Yabo Zhang, Yi Yang, Zongxin Yang","submitted_at":"2026-06-03T15:58:56Z","abstract_excerpt":"Generative visual models fundamentally struggle with precise spatial control. This arises from a core disconnect: models can process textual descriptions of space but cannot directly map numerical coordinates onto the 2D image canvas. We introduce MetaPoint, a method that bridges this gap by representing a continuous 2D coordinate as a single, special token. Crucially, MetaPoint requires no new architectural components; it directly leverages the model's inherent positional encoding schemes to interpret these coordinates, treating our token as a virtual point on the canvas. This lightweight app"},"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":"2606.05031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T15:58:56Z","cross_cats_sorted":[],"title_canon_sha256":"8e872a6c8e2dad402f5858c87d068b26b2ab23f93f6cc40c14079619ad18aa8b","abstract_canon_sha256":"97a666c3a565c3db97461e83f436ce351785681ab96e5822474e6cf644aa5af9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:10:03.080731Z","signature_b64":"cb1yEdTvoT/SZ43L7uleYUXDpPAiq+JqAwMCamRMUAkH3+DpRGjTBnqamCGVhE/2WSPLuPfPzQYN6rMJQ5/cBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73dede015ea74eab98213dee57adbff16e328b9bec48fb2e8fae432674cc86d4","last_reissued_at":"2026-06-04T01:10:03.080025Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:10:03.080025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dewei Zhou, Ji Xie, Kunchang Li, Liang Li, Xinyu Huang, Xun Wang, Yabo Zhang, Yi Yang, Zongxin Yang","submitted_at":"2026-06-03T15:58:56Z","abstract_excerpt":"Generative visual models fundamentally struggle with precise spatial control. This arises from a core disconnect: models can process textual descriptions of space but cannot directly map numerical coordinates onto the 2D image canvas. We introduce MetaPoint, a method that bridges this gap by representing a continuous 2D coordinate as a single, special token. Crucially, MetaPoint requires no new architectural components; it directly leverages the model's inherent positional encoding schemes to interpret these coordinates, treating our token as a virtual point on the canvas. This lightweight app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05031","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/2606.05031/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":"2606.05031","created_at":"2026-06-04T01:10:03.080122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05031v1","created_at":"2026-06-04T01:10:03.080122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05031","created_at":"2026-06-04T01:10:03.080122+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPPN4AK6U5HK","created_at":"2026-06-04T01:10:03.080122+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPPN4AK6U5HKXGBB","created_at":"2026-06-04T01:10:03.080122+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPPN4AK6","created_at":"2026-06-04T01:10:03.080122+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.01667","citing_title":"Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning","ref_index":90,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OPPN4AK6U5HKXGBBHXXFPLN76F","json":"https://pith.science/pith/OPPN4AK6U5HKXGBBHXXFPLN76F.json","graph_json":"https://pith.science/api/pith-number/OPPN4AK6U5HKXGBBHXXFPLN76F/graph.json","events_json":"https://pith.science/api/pith-number/OPPN4AK6U5HKXGBBHXXFPLN76F/events.json","paper":"https://pith.science/paper/OPPN4AK6"},"agent_actions":{"view_html":"https://pith.science/pith/OPPN4AK6U5HKXGBBHXXFPLN76F","download_json":"https://pith.science/pith/OPPN4AK6U5HKXGBBHXXFPLN76F.json","view_paper":"https://pith.science/paper/OPPN4AK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05031&json=true","fetch_graph":"https://pith.science/api/pith-number/OPPN4AK6U5HKXGBBHXXFPLN76F/graph.json","fetch_events":"https://pith.science/api/pith-number/OPPN4AK6U5HKXGBBHXXFPLN76F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPPN4AK6U5HKXGBBHXXFPLN76F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPPN4AK6U5HKXGBBHXXFPLN76F/action/storage_attestation","attest_author":"https://pith.science/pith/OPPN4AK6U5HKXGBBHXXFPLN76F/action/author_attestation","sign_citation":"https://pith.science/pith/OPPN4AK6U5HKXGBBHXXFPLN76F/action/citation_signature","submit_replication":"https://pith.science/pith/OPPN4AK6U5HKXGBBHXXFPLN76F/action/replication_record"}},"created_at":"2026-06-04T01:10:03.080122+00:00","updated_at":"2026-06-04T01:10:03.080122+00:00"}