{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VF6AR3IN34SKEOAJT6NSBQWAVI","short_pith_number":"pith:VF6AR3IN","schema_version":"1.0","canonical_sha256":"a97c08ed0ddf24a238099f9b20c2c0aa2acb3a5c1331a8adf5f41cc4c3e2a8af","source":{"kind":"arxiv","id":"2601.02457","version":2},"attestation_state":"computed","paper":{"title":"PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingchen Gong, Emery Pierson, Lei Li, Maks Ovsjanikov, Peter Wonka, Ramana Sundararaman, Souhail Hadgi","submitted_at":"2026-01-05T18:55:45Z","abstract_excerpt":"Current foundation models for 3D shapes excel at global tasks (retrieval, classification) but transfer poorly to local part-level reasoning. Recent approaches leverage vision and language foundation models to directly solve dense tasks through multi-view renderings and text queries. While promising, these pipelines require expensive inference over multiple renderings, depend heavily on large language-model (LLM) prompt engineering for captions, and fail to exploit the inherent 3D geometry of shapes. We address this gap by introducing an encoder-only 3D model that produces language-aligned patc"},"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":"2601.02457","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-05T18:55:45Z","cross_cats_sorted":[],"title_canon_sha256":"f4ed7feeb109727594983b828cbd1a88c240d61a7cad841b39b1ab1cf6e39476","abstract_canon_sha256":"f0d49a75c8797902727196d3b5c8d2ea7c2b78e0fd1c9bd80f0282f25ec34fc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:52:08.027536Z","signature_b64":"UuG+HC1fIisl99AzzMzMSHKKIdu07QwjbNHDNuczGmEBwIGuY2qj0SdIYHuT6+eTN6xEBPoZ08di+5KIXtEWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a97c08ed0ddf24a238099f9b20c2c0aa2acb3a5c1331a8adf5f41cc4c3e2a8af","last_reissued_at":"2026-08-04T01:52:08.025748Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:52:08.025748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingchen Gong, Emery Pierson, Lei Li, Maks Ovsjanikov, Peter Wonka, Ramana Sundararaman, Souhail Hadgi","submitted_at":"2026-01-05T18:55:45Z","abstract_excerpt":"Current foundation models for 3D shapes excel at global tasks (retrieval, classification) but transfer poorly to local part-level reasoning. Recent approaches leverage vision and language foundation models to directly solve dense tasks through multi-view renderings and text queries. While promising, these pipelines require expensive inference over multiple renderings, depend heavily on large language-model (LLM) prompt engineering for captions, and fail to exploit the inherent 3D geometry of shapes. We address this gap by introducing an encoder-only 3D model that produces language-aligned patc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.02457","kind":"arxiv","version":2},"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/2601.02457/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":"2601.02457","created_at":"2026-08-04T01:52:08.027037+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.02457v2","created_at":"2026-08-04T01:52:08.027037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.02457","created_at":"2026-08-04T01:52:08.027037+00:00"},{"alias_kind":"pith_short_12","alias_value":"VF6AR3IN34SK","created_at":"2026-08-04T01:52:08.027037+00:00"},{"alias_kind":"pith_short_16","alias_value":"VF6AR3IN34SKEOAJ","created_at":"2026-08-04T01:52:08.027037+00:00"},{"alias_kind":"pith_short_8","alias_value":"VF6AR3IN","created_at":"2026-08-04T01:52:08.027037+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.31533","citing_title":"MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshes","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04050","citing_title":"TORA: Topological Representation Alignment for 3D Shape Assembly","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VF6AR3IN34SKEOAJT6NSBQWAVI","json":"https://pith.science/pith/VF6AR3IN34SKEOAJT6NSBQWAVI.json","graph_json":"https://pith.science/api/pith-number/VF6AR3IN34SKEOAJT6NSBQWAVI/graph.json","events_json":"https://pith.science/api/pith-number/VF6AR3IN34SKEOAJT6NSBQWAVI/events.json","paper":"https://pith.science/paper/VF6AR3IN"},"agent_actions":{"view_html":"https://pith.science/pith/VF6AR3IN34SKEOAJT6NSBQWAVI","download_json":"https://pith.science/pith/VF6AR3IN34SKEOAJT6NSBQWAVI.json","view_paper":"https://pith.science/paper/VF6AR3IN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.02457&json=true","fetch_graph":"https://pith.science/api/pith-number/VF6AR3IN34SKEOAJT6NSBQWAVI/graph.json","fetch_events":"https://pith.science/api/pith-number/VF6AR3IN34SKEOAJT6NSBQWAVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VF6AR3IN34SKEOAJT6NSBQWAVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VF6AR3IN34SKEOAJT6NSBQWAVI/action/storage_attestation","attest_author":"https://pith.science/pith/VF6AR3IN34SKEOAJT6NSBQWAVI/action/author_attestation","sign_citation":"https://pith.science/pith/VF6AR3IN34SKEOAJT6NSBQWAVI/action/citation_signature","submit_replication":"https://pith.science/pith/VF6AR3IN34SKEOAJT6NSBQWAVI/action/replication_record"}},"created_at":"2026-08-04T01:52:08.027037+00:00","updated_at":"2026-08-04T01:52:08.027037+00:00"}