{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B4PMBXBBUTQ2FV2NOEBVO2BCUO","short_pith_number":"pith:B4PMBXBB","schema_version":"1.0","canonical_sha256":"0f1ec0dc21a4e1a2d74d7103576822a3b9bef15393f7b81b2b7007bb47025931","source":{"kind":"arxiv","id":"2608.03565","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Tabular Learners with Context-Aware Semantic Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"G\\\"unther Schindler, Johannes H\\\"ohne, Maximilian Schambach","submitted_at":"2026-08-04T12:29:37Z","abstract_excerpt":"While modern tabular learners excel at capturing statistical patterns, they frequently operate in a semantic vacuum, treating textual features as discrete symbols, ignoring the rich semantics inherent in feature names or cell entries. We propose CASE (Context-Aware Semantic Embeddings), a novel framework that bridges the gap between the semantic understanding of Large Language Models (LLMs) and the statistical capabilities of tabular learners. Unlike existing methods that embed rows in isolation, CASE utilizes a contextualization strategy: we pre-fill the KV cache of a custom-trained Gemma 3-b"},"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":"2608.03565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T12:29:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3330e1b9f53d28bea6e82ecba86ef75601e04a1e6855b54f75e45dfd3b064028","abstract_canon_sha256":"2c41b8009b9b8d5d159b86e930e8b45873e9d53e0424524aa47130d39923a551"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:36:39.418189Z","signature_b64":"0tzSxdSgQXCxsPvEvKEBoZeCOOOwIHJ3XnEZs9Ed2Sqka2PfAJeEQxi2Ib3+k6CtPWOPuZPLA8KlVhSVDH+OBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f1ec0dc21a4e1a2d74d7103576822a3b9bef15393f7b81b2b7007bb47025931","last_reissued_at":"2026-08-05T01:36:39.416630Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:36:39.416630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Tabular Learners with Context-Aware Semantic Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"G\\\"unther Schindler, Johannes H\\\"ohne, Maximilian Schambach","submitted_at":"2026-08-04T12:29:37Z","abstract_excerpt":"While modern tabular learners excel at capturing statistical patterns, they frequently operate in a semantic vacuum, treating textual features as discrete symbols, ignoring the rich semantics inherent in feature names or cell entries. We propose CASE (Context-Aware Semantic Embeddings), a novel framework that bridges the gap between the semantic understanding of Large Language Models (LLMs) and the statistical capabilities of tabular learners. Unlike existing methods that embed rows in isolation, CASE utilizes a contextualization strategy: we pre-fill the KV cache of a custom-trained Gemma 3-b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03565","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/2608.03565/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":"2608.03565","created_at":"2026-08-05T01:36:39.417110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03565v1","created_at":"2026-08-05T01:36:39.417110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03565","created_at":"2026-08-05T01:36:39.417110+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4PMBXBBUTQ2","created_at":"2026-08-05T01:36:39.417110+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4PMBXBBUTQ2FV2N","created_at":"2026-08-05T01:36:39.417110+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4PMBXBB","created_at":"2026-08-05T01:36:39.417110+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/B4PMBXBBUTQ2FV2NOEBVO2BCUO","json":"https://pith.science/pith/B4PMBXBBUTQ2FV2NOEBVO2BCUO.json","graph_json":"https://pith.science/api/pith-number/B4PMBXBBUTQ2FV2NOEBVO2BCUO/graph.json","events_json":"https://pith.science/api/pith-number/B4PMBXBBUTQ2FV2NOEBVO2BCUO/events.json","paper":"https://pith.science/paper/B4PMBXBB"},"agent_actions":{"view_html":"https://pith.science/pith/B4PMBXBBUTQ2FV2NOEBVO2BCUO","download_json":"https://pith.science/pith/B4PMBXBBUTQ2FV2NOEBVO2BCUO.json","view_paper":"https://pith.science/paper/B4PMBXBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03565&json=true","fetch_graph":"https://pith.science/api/pith-number/B4PMBXBBUTQ2FV2NOEBVO2BCUO/graph.json","fetch_events":"https://pith.science/api/pith-number/B4PMBXBBUTQ2FV2NOEBVO2BCUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4PMBXBBUTQ2FV2NOEBVO2BCUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4PMBXBBUTQ2FV2NOEBVO2BCUO/action/storage_attestation","attest_author":"https://pith.science/pith/B4PMBXBBUTQ2FV2NOEBVO2BCUO/action/author_attestation","sign_citation":"https://pith.science/pith/B4PMBXBBUTQ2FV2NOEBVO2BCUO/action/citation_signature","submit_replication":"https://pith.science/pith/B4PMBXBBUTQ2FV2NOEBVO2BCUO/action/replication_record"}},"created_at":"2026-08-05T01:36:39.417110+00:00","updated_at":"2026-08-05T01:36:39.417110+00:00"}