{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZPRZORQIB257HE4EJS36R4ADU5","short_pith_number":"pith:ZPRZORQI","schema_version":"1.0","canonical_sha256":"cbe39746080ebbf393844cb7e8f003a7754622558929914507b019d37b8584c8","source":{"kind":"arxiv","id":"2606.31585","version":1},"attestation_state":"computed","paper":{"title":"DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Shun Kenney, Teppei Suzuki","submitted_at":"2026-06-30T12:38:58Z","abstract_excerpt":"The remarkable scalability of Transformers has expanded their application to 3D computer vision, where camera-aware positional encoding is crucial for providing spatial cues in multi-view geometry. Recent advancements have established the practice of using camera parameters -- such as extrinsics or projection matrices -- as relative positional encoding into the query, key, and value vectors of the attention mechanism. However, when scaling up the training recipe of novel view synthesis (NVS) models with the camera-based positional encoding, we observe a significant issue: model performance sta"},"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":"2606.31585","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T12:38:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6387e5ab51fa9ccbfa18fdfc73726ae0d24ce8722bbb37a47bdec4809cc69ae0","abstract_canon_sha256":"5779b8270279aee83c03ece8d41e644c596f1cf7123697946bbaa511be32802d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:08.387424Z","signature_b64":"jeEn1ghKkwwCnGf1QzETMVPKK0MyvSiDAsg+o5ldNPBLZYo8UNzrscOxgrMUJ2p76byvF77FDpmebCIvIYVaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbe39746080ebbf393844cb7e8f003a7754622558929914507b019d37b8584c8","last_reissued_at":"2026-07-01T01:18:08.387044Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:08.387044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Shun Kenney, Teppei Suzuki","submitted_at":"2026-06-30T12:38:58Z","abstract_excerpt":"The remarkable scalability of Transformers has expanded their application to 3D computer vision, where camera-aware positional encoding is crucial for providing spatial cues in multi-view geometry. Recent advancements have established the practice of using camera parameters -- such as extrinsics or projection matrices -- as relative positional encoding into the query, key, and value vectors of the attention mechanism. However, when scaling up the training recipe of novel view synthesis (NVS) models with the camera-based positional encoding, we observe a significant issue: model performance sta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31585","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/2606.31585/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":"2606.31585","created_at":"2026-07-01T01:18:08.387098+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31585v1","created_at":"2026-07-01T01:18:08.387098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31585","created_at":"2026-07-01T01:18:08.387098+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPRZORQIB257","created_at":"2026-07-01T01:18:08.387098+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPRZORQIB257HE4E","created_at":"2026-07-01T01:18:08.387098+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPRZORQI","created_at":"2026-07-01T01:18:08.387098+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/ZPRZORQIB257HE4EJS36R4ADU5","json":"https://pith.science/pith/ZPRZORQIB257HE4EJS36R4ADU5.json","graph_json":"https://pith.science/api/pith-number/ZPRZORQIB257HE4EJS36R4ADU5/graph.json","events_json":"https://pith.science/api/pith-number/ZPRZORQIB257HE4EJS36R4ADU5/events.json","paper":"https://pith.science/paper/ZPRZORQI"},"agent_actions":{"view_html":"https://pith.science/pith/ZPRZORQIB257HE4EJS36R4ADU5","download_json":"https://pith.science/pith/ZPRZORQIB257HE4EJS36R4ADU5.json","view_paper":"https://pith.science/paper/ZPRZORQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31585&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPRZORQIB257HE4EJS36R4ADU5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPRZORQIB257HE4EJS36R4ADU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPRZORQIB257HE4EJS36R4ADU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPRZORQIB257HE4EJS36R4ADU5/action/storage_attestation","attest_author":"https://pith.science/pith/ZPRZORQIB257HE4EJS36R4ADU5/action/author_attestation","sign_citation":"https://pith.science/pith/ZPRZORQIB257HE4EJS36R4ADU5/action/citation_signature","submit_replication":"https://pith.science/pith/ZPRZORQIB257HE4EJS36R4ADU5/action/replication_record"}},"created_at":"2026-07-01T01:18:08.387098+00:00","updated_at":"2026-07-01T01:18:08.387098+00:00"}