{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:N5KLXINTCKUMC6T56BBUBRZRWS","short_pith_number":"pith:N5KLXINT","schema_version":"1.0","canonical_sha256":"6f54bba1b312a8c17a7df04340c731b4807b4a68e7ed35eed30a27b1ca7cc87a","source":{"kind":"arxiv","id":"2310.17611","version":1},"attestation_state":"computed","paper":{"title":"Uncovering Meanings of Embeddings via Partial Orthogonality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bryon Aragam, Victor Veitch, Yibo Jiang","submitted_at":"2023-10-26T17:34:32Z","abstract_excerpt":"Machine learning tools often rely on embedding text as vectors of real numbers. In this paper, we study how the semantic structure of language is encoded in the algebraic structure of such embeddings. Specifically, we look at a notion of ``semantic independence'' capturing the idea that, e.g., ``eggplant'' and ``tomato'' are independent given ``vegetable''. Although such examples are intuitive, it is difficult to formalize such a notion of semantic independence. The key observation here is that any sensible formalization should obey a set of so-called independence axioms, and thus any algebrai"},"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":"2310.17611","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T17:34:32Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"d313f49d664ccf281d99b5ee1815c9fa09c658b7ab27f2897387b9deb3d9041c","abstract_canon_sha256":"1bd5a91a0d835bd37f6592bc339f018ee93f8f384103fa51768bc18f0d12e2ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:36.893283Z","signature_b64":"Ob2id8D9dCRW087vq4L1DIThTeEnkZDQKFUkXBR7w8SEhNXNm9CYaajQV0QU+nTKO8LC7CdbzuHAC462LK7qAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f54bba1b312a8c17a7df04340c731b4807b4a68e7ed35eed30a27b1ca7cc87a","last_reissued_at":"2026-07-05T07:05:36.892868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:36.892868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncovering Meanings of Embeddings via Partial Orthogonality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bryon Aragam, Victor Veitch, Yibo Jiang","submitted_at":"2023-10-26T17:34:32Z","abstract_excerpt":"Machine learning tools often rely on embedding text as vectors of real numbers. In this paper, we study how the semantic structure of language is encoded in the algebraic structure of such embeddings. Specifically, we look at a notion of ``semantic independence'' capturing the idea that, e.g., ``eggplant'' and ``tomato'' are independent given ``vegetable''. Although such examples are intuitive, it is difficult to formalize such a notion of semantic independence. The key observation here is that any sensible formalization should obey a set of so-called independence axioms, and thus any algebrai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17611","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/2310.17611/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":"2310.17611","created_at":"2026-07-05T07:05:36.892928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17611v1","created_at":"2026-07-05T07:05:36.892928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17611","created_at":"2026-07-05T07:05:36.892928+00:00"},{"alias_kind":"pith_short_12","alias_value":"N5KLXINTCKUM","created_at":"2026-07-05T07:05:36.892928+00:00"},{"alias_kind":"pith_short_16","alias_value":"N5KLXINTCKUMC6T5","created_at":"2026-07-05T07:05:36.892928+00:00"},{"alias_kind":"pith_short_8","alias_value":"N5KLXINT","created_at":"2026-07-05T07:05:36.892928+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2311.03658","citing_title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08846","citing_title":"Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N5KLXINTCKUMC6T56BBUBRZRWS","json":"https://pith.science/pith/N5KLXINTCKUMC6T56BBUBRZRWS.json","graph_json":"https://pith.science/api/pith-number/N5KLXINTCKUMC6T56BBUBRZRWS/graph.json","events_json":"https://pith.science/api/pith-number/N5KLXINTCKUMC6T56BBUBRZRWS/events.json","paper":"https://pith.science/paper/N5KLXINT"},"agent_actions":{"view_html":"https://pith.science/pith/N5KLXINTCKUMC6T56BBUBRZRWS","download_json":"https://pith.science/pith/N5KLXINTCKUMC6T56BBUBRZRWS.json","view_paper":"https://pith.science/paper/N5KLXINT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17611&json=true","fetch_graph":"https://pith.science/api/pith-number/N5KLXINTCKUMC6T56BBUBRZRWS/graph.json","fetch_events":"https://pith.science/api/pith-number/N5KLXINTCKUMC6T56BBUBRZRWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N5KLXINTCKUMC6T56BBUBRZRWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N5KLXINTCKUMC6T56BBUBRZRWS/action/storage_attestation","attest_author":"https://pith.science/pith/N5KLXINTCKUMC6T56BBUBRZRWS/action/author_attestation","sign_citation":"https://pith.science/pith/N5KLXINTCKUMC6T56BBUBRZRWS/action/citation_signature","submit_replication":"https://pith.science/pith/N5KLXINTCKUMC6T56BBUBRZRWS/action/replication_record"}},"created_at":"2026-07-05T07:05:36.892928+00:00","updated_at":"2026-07-05T07:05:36.892928+00:00"}