{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TTBNQCLBHZNOEVVPNOUYCI2FXM","short_pith_number":"pith:TTBNQCLB","schema_version":"1.0","canonical_sha256":"9cc2d809613e5ae256af6ba9812345bb30c2f5e2e30ae569dc833dabfd3cb8bc","source":{"kind":"arxiv","id":"2605.28995","version":1},"attestation_state":"computed","paper":{"title":"GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrii Zadaianchuk, Mohammad Mahdi Derakhshani, Polytimi Anna Gkotsi","submitted_at":"2026-05-27T18:53:09Z","abstract_excerpt":"Recent approaches integrating vision-language models (VLMs) as prompt encoders for generative model conditioning typically rely on expensive end-to-end training or map features to compressed representations, discarding the dense spatial structure required for geometry-aware tasks like 3D asset generation. To address this, we propose GAP3D, a modular, diffusion-based approach that aligns VLM-generated latents directly to the complete, patch-level feature space of a pre-trained image encoder, enabling a frozen downstream generative model to utilize a VLM as prompt encoder while maintaining a spa"},"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":"2605.28995","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T18:53:09Z","cross_cats_sorted":[],"title_canon_sha256":"c69717569a5d7a44e1598dbdcaf5e34afe26e431f2dacc8a9028931a91ff9722","abstract_canon_sha256":"7bfda07397969e9f73a8c8976398620ec3de2727e50e2dd9047e7595e5f506bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:42.966971Z","signature_b64":"aedjftlG9yf6tUG0pnRzjjDKd93obK4VwwMyvHAE0iOZgTXDWZDRFkN9v80ca0dpSlfMpp2QrrfnVHSfUrK1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cc2d809613e5ae256af6ba9812345bb30c2f5e2e30ae569dc833dabfd3cb8bc","last_reissued_at":"2026-05-29T01:04:42.966497Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:42.966497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrii Zadaianchuk, Mohammad Mahdi Derakhshani, Polytimi Anna Gkotsi","submitted_at":"2026-05-27T18:53:09Z","abstract_excerpt":"Recent approaches integrating vision-language models (VLMs) as prompt encoders for generative model conditioning typically rely on expensive end-to-end training or map features to compressed representations, discarding the dense spatial structure required for geometry-aware tasks like 3D asset generation. To address this, we propose GAP3D, a modular, diffusion-based approach that aligns VLM-generated latents directly to the complete, patch-level feature space of a pre-trained image encoder, enabling a frozen downstream generative model to utilize a VLM as prompt encoder while maintaining a spa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28995","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/2605.28995/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":"2605.28995","created_at":"2026-05-29T01:04:42.966566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28995v1","created_at":"2026-05-29T01:04:42.966566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28995","created_at":"2026-05-29T01:04:42.966566+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTBNQCLBHZNO","created_at":"2026-05-29T01:04:42.966566+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTBNQCLBHZNOEVVP","created_at":"2026-05-29T01:04:42.966566+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTBNQCLB","created_at":"2026-05-29T01:04:42.966566+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/TTBNQCLBHZNOEVVPNOUYCI2FXM","json":"https://pith.science/pith/TTBNQCLBHZNOEVVPNOUYCI2FXM.json","graph_json":"https://pith.science/api/pith-number/TTBNQCLBHZNOEVVPNOUYCI2FXM/graph.json","events_json":"https://pith.science/api/pith-number/TTBNQCLBHZNOEVVPNOUYCI2FXM/events.json","paper":"https://pith.science/paper/TTBNQCLB"},"agent_actions":{"view_html":"https://pith.science/pith/TTBNQCLBHZNOEVVPNOUYCI2FXM","download_json":"https://pith.science/pith/TTBNQCLBHZNOEVVPNOUYCI2FXM.json","view_paper":"https://pith.science/paper/TTBNQCLB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28995&json=true","fetch_graph":"https://pith.science/api/pith-number/TTBNQCLBHZNOEVVPNOUYCI2FXM/graph.json","fetch_events":"https://pith.science/api/pith-number/TTBNQCLBHZNOEVVPNOUYCI2FXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTBNQCLBHZNOEVVPNOUYCI2FXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTBNQCLBHZNOEVVPNOUYCI2FXM/action/storage_attestation","attest_author":"https://pith.science/pith/TTBNQCLBHZNOEVVPNOUYCI2FXM/action/author_attestation","sign_citation":"https://pith.science/pith/TTBNQCLBHZNOEVVPNOUYCI2FXM/action/citation_signature","submit_replication":"https://pith.science/pith/TTBNQCLBHZNOEVVPNOUYCI2FXM/action/replication_record"}},"created_at":"2026-05-29T01:04:42.966566+00:00","updated_at":"2026-05-29T01:04:42.966566+00:00"}