{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CKJSAEZPM6XVWFBRTSO5A6OCQG","short_pith_number":"pith:CKJSAEZP","schema_version":"1.0","canonical_sha256":"129320132f67af5b14319c9dd079c28194113112178d9e047f7978b72710eac9","source":{"kind":"arxiv","id":"2312.11272","version":1},"attestation_state":"computed","paper":{"title":"Disentangling continuous and discrete linguistic signals in transformer-based sentence embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Paola Merlo, Vivi Nastase","submitted_at":"2023-12-18T15:16:54Z","abstract_excerpt":"Sentence and word embeddings encode structural and semantic information in a distributed manner. Part of the information encoded -- particularly lexical information -- can be seen as continuous, whereas other -- like structural information -- is most often discrete. We explore whether we can compress transformer-based sentence embeddings into a representation that separates different linguistic signals -- in particular, information relevant to subject-verb agreement and verb alternations. We show that by compressing an input sequence that shares a targeted phenomenon into the latent layer of a"},"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":"2312.11272","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-18T15:16:54Z","cross_cats_sorted":[],"title_canon_sha256":"56e55daf7054ac52f8f17ee022499a08bae3454698917ca159e228940f1be16c","abstract_canon_sha256":"3669db22074102a4e4be00d0241a78ef9f4ef3abdb8b310789d6387863ada85e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:30.656111Z","signature_b64":"jx4q2R04L0WI5mMgMlf5letNKCHfen6w1k5WawSAarGSECkCpe72REn0CouQKJAUlaO6FfTpmGFagV08je1bCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"129320132f67af5b14319c9dd079c28194113112178d9e047f7978b72710eac9","last_reissued_at":"2026-07-05T07:25:30.655473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:30.655473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling continuous and discrete linguistic signals in transformer-based sentence embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Paola Merlo, Vivi Nastase","submitted_at":"2023-12-18T15:16:54Z","abstract_excerpt":"Sentence and word embeddings encode structural and semantic information in a distributed manner. Part of the information encoded -- particularly lexical information -- can be seen as continuous, whereas other -- like structural information -- is most often discrete. We explore whether we can compress transformer-based sentence embeddings into a representation that separates different linguistic signals -- in particular, information relevant to subject-verb agreement and verb alternations. We show that by compressing an input sequence that shares a targeted phenomenon into the latent layer of a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11272","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/2312.11272/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":"2312.11272","created_at":"2026-07-05T07:25:30.655551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11272v1","created_at":"2026-07-05T07:25:30.655551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11272","created_at":"2026-07-05T07:25:30.655551+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKJSAEZPM6XV","created_at":"2026-07-05T07:25:30.655551+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKJSAEZPM6XVWFBR","created_at":"2026-07-05T07:25:30.655551+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKJSAEZP","created_at":"2026-07-05T07:25:30.655551+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/CKJSAEZPM6XVWFBRTSO5A6OCQG","json":"https://pith.science/pith/CKJSAEZPM6XVWFBRTSO5A6OCQG.json","graph_json":"https://pith.science/api/pith-number/CKJSAEZPM6XVWFBRTSO5A6OCQG/graph.json","events_json":"https://pith.science/api/pith-number/CKJSAEZPM6XVWFBRTSO5A6OCQG/events.json","paper":"https://pith.science/paper/CKJSAEZP"},"agent_actions":{"view_html":"https://pith.science/pith/CKJSAEZPM6XVWFBRTSO5A6OCQG","download_json":"https://pith.science/pith/CKJSAEZPM6XVWFBRTSO5A6OCQG.json","view_paper":"https://pith.science/paper/CKJSAEZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11272&json=true","fetch_graph":"https://pith.science/api/pith-number/CKJSAEZPM6XVWFBRTSO5A6OCQG/graph.json","fetch_events":"https://pith.science/api/pith-number/CKJSAEZPM6XVWFBRTSO5A6OCQG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKJSAEZPM6XVWFBRTSO5A6OCQG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKJSAEZPM6XVWFBRTSO5A6OCQG/action/storage_attestation","attest_author":"https://pith.science/pith/CKJSAEZPM6XVWFBRTSO5A6OCQG/action/author_attestation","sign_citation":"https://pith.science/pith/CKJSAEZPM6XVWFBRTSO5A6OCQG/action/citation_signature","submit_replication":"https://pith.science/pith/CKJSAEZPM6XVWFBRTSO5A6OCQG/action/replication_record"}},"created_at":"2026-07-05T07:25:30.655551+00:00","updated_at":"2026-07-05T07:25:30.655551+00:00"}