{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XQDNORI5OWO5AUEQSXLZ62HMKJ","short_pith_number":"pith:XQDNORI5","schema_version":"1.0","canonical_sha256":"bc06d7451d759dd0509095d79f68ec5267db39dea4fcea47289b01400f445f54","source":{"kind":"arxiv","id":"2606.06994","version":1},"attestation_state":"computed","paper":{"title":"Principles of Concept Representation in Sentence Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Andre Freitas, Isabelle Mohr, John Dujany, Jonathan Souquet","submitted_at":"2026-06-05T07:33:05Z","abstract_excerpt":"What makes a sentence encoder produce good concept representations? We approach this through the lens of representational compositionality: an encoder supports a concept family only when its latent space admits a low-distortion realization of the corresponding semantic operator. This framing predicts both where current encoders succeed and where they are structurally mismatched to their supervision. Through a controlled ablation over encoder conditions trained on 3.3 million synonym and definition pairs from WordNet and Wiktionary, evaluated on three decontaminated splits and a modifier-labele"},"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":"2606.06994","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T07:33:05Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"cc1321e5b4e6389a3ad59e15d9d7ef207afaba05a5d2996b02c667e17d143f17","abstract_canon_sha256":"8661ce95ddadc4fcc78b4a21b2e5e090efb6c26f4a6cd9542fb1ec0f435c02ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:40.226733Z","signature_b64":"gSnOj/uvOMqeFCzyQg5NX6r0SlI1NpYfS+xUrNhbkT6/VziafK7KzT+9x1O4JvbA5qNcA9gR7J8B198KMLNXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc06d7451d759dd0509095d79f68ec5267db39dea4fcea47289b01400f445f54","last_reissued_at":"2026-06-08T01:04:40.225574Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:40.225574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Principles of Concept Representation in Sentence Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Andre Freitas, Isabelle Mohr, John Dujany, Jonathan Souquet","submitted_at":"2026-06-05T07:33:05Z","abstract_excerpt":"What makes a sentence encoder produce good concept representations? We approach this through the lens of representational compositionality: an encoder supports a concept family only when its latent space admits a low-distortion realization of the corresponding semantic operator. This framing predicts both where current encoders succeed and where they are structurally mismatched to their supervision. Through a controlled ablation over encoder conditions trained on 3.3 million synonym and definition pairs from WordNet and Wiktionary, evaluated on three decontaminated splits and a modifier-labele"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06994","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/2606.06994/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":"2606.06994","created_at":"2026-06-08T01:04:40.225719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06994v1","created_at":"2026-06-08T01:04:40.225719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06994","created_at":"2026-06-08T01:04:40.225719+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQDNORI5OWO5","created_at":"2026-06-08T01:04:40.225719+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQDNORI5OWO5AUEQ","created_at":"2026-06-08T01:04:40.225719+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQDNORI5","created_at":"2026-06-08T01:04:40.225719+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/XQDNORI5OWO5AUEQSXLZ62HMKJ","json":"https://pith.science/pith/XQDNORI5OWO5AUEQSXLZ62HMKJ.json","graph_json":"https://pith.science/api/pith-number/XQDNORI5OWO5AUEQSXLZ62HMKJ/graph.json","events_json":"https://pith.science/api/pith-number/XQDNORI5OWO5AUEQSXLZ62HMKJ/events.json","paper":"https://pith.science/paper/XQDNORI5"},"agent_actions":{"view_html":"https://pith.science/pith/XQDNORI5OWO5AUEQSXLZ62HMKJ","download_json":"https://pith.science/pith/XQDNORI5OWO5AUEQSXLZ62HMKJ.json","view_paper":"https://pith.science/paper/XQDNORI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06994&json=true","fetch_graph":"https://pith.science/api/pith-number/XQDNORI5OWO5AUEQSXLZ62HMKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XQDNORI5OWO5AUEQSXLZ62HMKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQDNORI5OWO5AUEQSXLZ62HMKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQDNORI5OWO5AUEQSXLZ62HMKJ/action/storage_attestation","attest_author":"https://pith.science/pith/XQDNORI5OWO5AUEQSXLZ62HMKJ/action/author_attestation","sign_citation":"https://pith.science/pith/XQDNORI5OWO5AUEQSXLZ62HMKJ/action/citation_signature","submit_replication":"https://pith.science/pith/XQDNORI5OWO5AUEQSXLZ62HMKJ/action/replication_record"}},"created_at":"2026-06-08T01:04:40.225719+00:00","updated_at":"2026-06-08T01:04:40.225719+00:00"}