{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J2OTCAOD3BGK656CUZILXSZ4BG","short_pith_number":"pith:J2OTCAOD","schema_version":"1.0","canonical_sha256":"4e9d3101c3d84caf77c2a650bbcb3c09baa27b796fc420ce9b36bc53770f16f9","source":{"kind":"arxiv","id":"2406.16563","version":2},"attestation_state":"computed","paper":{"title":"Are there identifiable structural parts in the sentence embedding whole?","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":"2024-06-24T11:58:33Z","abstract_excerpt":"Sentence embeddings from transformer models encode in a fixed length vector much linguistic information. We explore the hypothesis that these embeddings consist of overlapping layers of information that can be separated, and on which specific types of information -- such as information about chunks and their structural and semantic properties -- can be detected. We show that this is the case using a dataset consisting of sentences with known chunk structure, and two linguistic intelligence datasets, solving which relies on detecting chunks and their grammatical number, and respectively, their "},"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":"2406.16563","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T11:58:33Z","cross_cats_sorted":[],"title_canon_sha256":"bc12784e88d49844130801d9240736f6717000d20db78d40c8297750f4471536","abstract_canon_sha256":"04fcd2f04542a6da20bde654cfbee44f259aa93517538f7928f123e058c94b1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:00.830369Z","signature_b64":"R19/kXCLcFfpGQYtCyhfppafTXk6ZF1J/SHlzYQq8Rzy2e770HJPx3m/ovB924ZoRcU5SANKkmCTo8Qexz87Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e9d3101c3d84caf77c2a650bbcb3c09baa27b796fc420ce9b36bc53770f16f9","last_reissued_at":"2026-07-05T08:39:00.829871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:00.829871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are there identifiable structural parts in the sentence embedding whole?","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":"2024-06-24T11:58:33Z","abstract_excerpt":"Sentence embeddings from transformer models encode in a fixed length vector much linguistic information. We explore the hypothesis that these embeddings consist of overlapping layers of information that can be separated, and on which specific types of information -- such as information about chunks and their structural and semantic properties -- can be detected. We show that this is the case using a dataset consisting of sentences with known chunk structure, and two linguistic intelligence datasets, solving which relies on detecting chunks and their grammatical number, and respectively, their "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16563","kind":"arxiv","version":2},"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/2406.16563/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":"2406.16563","created_at":"2026-07-05T08:39:00.829928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16563v2","created_at":"2026-07-05T08:39:00.829928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16563","created_at":"2026-07-05T08:39:00.829928+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2OTCAOD3BGK","created_at":"2026-07-05T08:39:00.829928+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2OTCAOD3BGK656C","created_at":"2026-07-05T08:39:00.829928+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2OTCAOD","created_at":"2026-07-05T08:39:00.829928+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/J2OTCAOD3BGK656CUZILXSZ4BG","json":"https://pith.science/pith/J2OTCAOD3BGK656CUZILXSZ4BG.json","graph_json":"https://pith.science/api/pith-number/J2OTCAOD3BGK656CUZILXSZ4BG/graph.json","events_json":"https://pith.science/api/pith-number/J2OTCAOD3BGK656CUZILXSZ4BG/events.json","paper":"https://pith.science/paper/J2OTCAOD"},"agent_actions":{"view_html":"https://pith.science/pith/J2OTCAOD3BGK656CUZILXSZ4BG","download_json":"https://pith.science/pith/J2OTCAOD3BGK656CUZILXSZ4BG.json","view_paper":"https://pith.science/paper/J2OTCAOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16563&json=true","fetch_graph":"https://pith.science/api/pith-number/J2OTCAOD3BGK656CUZILXSZ4BG/graph.json","fetch_events":"https://pith.science/api/pith-number/J2OTCAOD3BGK656CUZILXSZ4BG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2OTCAOD3BGK656CUZILXSZ4BG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2OTCAOD3BGK656CUZILXSZ4BG/action/storage_attestation","attest_author":"https://pith.science/pith/J2OTCAOD3BGK656CUZILXSZ4BG/action/author_attestation","sign_citation":"https://pith.science/pith/J2OTCAOD3BGK656CUZILXSZ4BG/action/citation_signature","submit_replication":"https://pith.science/pith/J2OTCAOD3BGK656CUZILXSZ4BG/action/replication_record"}},"created_at":"2026-07-05T08:39:00.829928+00:00","updated_at":"2026-07-05T08:39:00.829928+00:00"}