{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:F4D4VWPG2TRFVC7RLR3T5IQPAM","short_pith_number":"pith:F4D4VWPG","schema_version":"1.0","canonical_sha256":"2f07cad9e6d4e25a8bf15c773ea20f0324789fe1de59ce5929860b097e202abf","source":{"kind":"arxiv","id":"2009.05147","version":1},"attestation_state":"computed","paper":{"title":"Practical Cross-modal Manifold Alignment for Grounded Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO","stat.ML"],"primary_cat":"cs.CV","authors_text":"Andre T. Nguyen, Cynthia Matuszek, Edward Raff, Frank Ferraro, Gaoussou Youssouf Kebe, Kasra Darvish, Luke E. Richards","submitted_at":"2020-09-01T04:16:48Z","abstract_excerpt":"We propose a cross-modality manifold alignment procedure that leverages triplet loss to jointly learn consistent, multi-modal embeddings of language-based concepts of real-world items. Our approach learns these embeddings by sampling triples of anchor, positive, and negative data points from RGB-depth images and their natural language descriptions. We show that our approach can benefit from, but does not require, post-processing steps such as Procrustes analysis, in contrast to some of our baselines which require it for reasonable performance. We demonstrate the effectiveness of our approach o"},"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":"2009.05147","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-01T04:16:48Z","cross_cats_sorted":["cs.LG","cs.RO","stat.ML"],"title_canon_sha256":"15899628e9425123c1dfb102be87daf8bd547c730b14489c5cdc31af85e59ecd","abstract_canon_sha256":"32a7a2d9c33cce7dd575083344a663630ae797b5a7e4869fd6374a79709c1477"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:34:35.509193Z","signature_b64":"A2sgLasTMXqwiPCmD8FfcPvljeKzp41sEXNNuNQYkndhqc9I45uo5BQQ7lQE8q4Eh3lT0j10AGkjS1svKRqfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f07cad9e6d4e25a8bf15c773ea20f0324789fe1de59ce5929860b097e202abf","last_reissued_at":"2026-07-05T01:34:35.508743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:34:35.508743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Practical Cross-modal Manifold Alignment for Grounded Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO","stat.ML"],"primary_cat":"cs.CV","authors_text":"Andre T. Nguyen, Cynthia Matuszek, Edward Raff, Frank Ferraro, Gaoussou Youssouf Kebe, Kasra Darvish, Luke E. Richards","submitted_at":"2020-09-01T04:16:48Z","abstract_excerpt":"We propose a cross-modality manifold alignment procedure that leverages triplet loss to jointly learn consistent, multi-modal embeddings of language-based concepts of real-world items. Our approach learns these embeddings by sampling triples of anchor, positive, and negative data points from RGB-depth images and their natural language descriptions. We show that our approach can benefit from, but does not require, post-processing steps such as Procrustes analysis, in contrast to some of our baselines which require it for reasonable performance. We demonstrate the effectiveness of our approach o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.05147","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/2009.05147/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":"2009.05147","created_at":"2026-07-05T01:34:35.508806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.05147v1","created_at":"2026-07-05T01:34:35.508806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.05147","created_at":"2026-07-05T01:34:35.508806+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4D4VWPG2TRF","created_at":"2026-07-05T01:34:35.508806+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4D4VWPG2TRFVC7R","created_at":"2026-07-05T01:34:35.508806+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4D4VWPG","created_at":"2026-07-05T01:34:35.508806+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/F4D4VWPG2TRFVC7RLR3T5IQPAM","json":"https://pith.science/pith/F4D4VWPG2TRFVC7RLR3T5IQPAM.json","graph_json":"https://pith.science/api/pith-number/F4D4VWPG2TRFVC7RLR3T5IQPAM/graph.json","events_json":"https://pith.science/api/pith-number/F4D4VWPG2TRFVC7RLR3T5IQPAM/events.json","paper":"https://pith.science/paper/F4D4VWPG"},"agent_actions":{"view_html":"https://pith.science/pith/F4D4VWPG2TRFVC7RLR3T5IQPAM","download_json":"https://pith.science/pith/F4D4VWPG2TRFVC7RLR3T5IQPAM.json","view_paper":"https://pith.science/paper/F4D4VWPG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.05147&json=true","fetch_graph":"https://pith.science/api/pith-number/F4D4VWPG2TRFVC7RLR3T5IQPAM/graph.json","fetch_events":"https://pith.science/api/pith-number/F4D4VWPG2TRFVC7RLR3T5IQPAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4D4VWPG2TRFVC7RLR3T5IQPAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4D4VWPG2TRFVC7RLR3T5IQPAM/action/storage_attestation","attest_author":"https://pith.science/pith/F4D4VWPG2TRFVC7RLR3T5IQPAM/action/author_attestation","sign_citation":"https://pith.science/pith/F4D4VWPG2TRFVC7RLR3T5IQPAM/action/citation_signature","submit_replication":"https://pith.science/pith/F4D4VWPG2TRFVC7RLR3T5IQPAM/action/replication_record"}},"created_at":"2026-07-05T01:34:35.508806+00:00","updated_at":"2026-07-05T01:34:35.508806+00:00"}