{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:F4D4VWPG2TRFVC7RLR3T5IQPAM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"32a7a2d9c33cce7dd575083344a663630ae797b5a7e4869fd6374a79709c1477","cross_cats_sorted":["cs.LG","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-01T04:16:48Z","title_canon_sha256":"15899628e9425123c1dfb102be87daf8bd547c730b14489c5cdc31af85e59ecd"},"schema_version":"1.0","source":{"id":"2009.05147","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.05147","created_at":"2026-07-05T01:34:35Z"},{"alias_kind":"arxiv_version","alias_value":"2009.05147v1","created_at":"2026-07-05T01:34:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.05147","created_at":"2026-07-05T01:34:35Z"},{"alias_kind":"pith_short_12","alias_value":"F4D4VWPG2TRF","created_at":"2026-07-05T01:34:35Z"},{"alias_kind":"pith_short_16","alias_value":"F4D4VWPG2TRFVC7R","created_at":"2026-07-05T01:34:35Z"},{"alias_kind":"pith_short_8","alias_value":"F4D4VWPG","created_at":"2026-07-05T01:34:35Z"}],"graph_snapshots":[{"event_id":"sha256:cb7289cccbdbb4320223e75084fdb6a050d9a4f5ab609f9d8d420bdd3c5ce5d7","target":"graph","created_at":"2026-07-05T01:34:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2009.05147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andre T. Nguyen, Cynthia Matuszek, Edward Raff, Frank Ferraro, Gaoussou Youssouf Kebe, Kasra Darvish, Luke E. Richards","cross_cats":["cs.LG","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-01T04:16:48Z","title":"Practical Cross-modal Manifold Alignment for Grounded Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.05147","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a9b1c36d5478d3af135c918be7f9ac848b6c948dbf8e3917d50e2a45020465bd","target":"record","created_at":"2026-07-05T01:34:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"32a7a2d9c33cce7dd575083344a663630ae797b5a7e4869fd6374a79709c1477","cross_cats_sorted":["cs.LG","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-01T04:16:48Z","title_canon_sha256":"15899628e9425123c1dfb102be87daf8bd547c730b14489c5cdc31af85e59ecd"},"schema_version":"1.0","source":{"id":"2009.05147","kind":"arxiv","version":1}},"canonical_sha256":"2f07cad9e6d4e25a8bf15c773ea20f0324789fe1de59ce5929860b097e202abf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f07cad9e6d4e25a8bf15c773ea20f0324789fe1de59ce5929860b097e202abf","first_computed_at":"2026-07-05T01:34:35.508743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:34:35.508743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A2sgLasTMXqwiPCmD8FfcPvljeKzp41sEXNNuNQYkndhqc9I45uo5BQQ7lQE8q4Eh3lT0j10AGkjS1svKRqfBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:34:35.509193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.05147","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9b1c36d5478d3af135c918be7f9ac848b6c948dbf8e3917d50e2a45020465bd","sha256:cb7289cccbdbb4320223e75084fdb6a050d9a4f5ab609f9d8d420bdd3c5ce5d7"],"state_sha256":"a920f1a68582c27e77bcf3857779eb02ce32f2f86dcc56aa8396dca24164e8f5"}