{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CKJSAEZPM6XVWFBRTSO5A6OCQG","short_pith_number":"pith:CKJSAEZP","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"},"canonical_sha256":"129320132f67af5b14319c9dd079c28194113112178d9e047f7978b72710eac9","source":{"kind":"arxiv","id":"2312.11272","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11272","created_at":"2026-07-05T07:25:30Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11272v1","created_at":"2026-07-05T07:25:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11272","created_at":"2026-07-05T07:25:30Z"},{"alias_kind":"pith_short_12","alias_value":"CKJSAEZPM6XV","created_at":"2026-07-05T07:25:30Z"},{"alias_kind":"pith_short_16","alias_value":"CKJSAEZPM6XVWFBR","created_at":"2026-07-05T07:25:30Z"},{"alias_kind":"pith_short_8","alias_value":"CKJSAEZP","created_at":"2026-07-05T07:25:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CKJSAEZPM6XVWFBRTSO5A6OCQG","target":"record","payload":{"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"},"canonical_sha256":"129320132f67af5b14319c9dd079c28194113112178d9e047f7978b72710eac9","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"},"source_kind":"arxiv","source_id":"2312.11272","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:25:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w7g8IKKq8g0Tx4BLtB7mywg8Ar2zXk+Wrwgz6R8nR59gcuGxMpG9M491adUbjTjeU6QWOazBAL2c0/K7DFWkBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:22:01.236398Z"},"content_sha256":"a3c4d12c6965ee0f7c73a832bfd9a8823af5067096235b6578480bab051ce3e6","schema_version":"1.0","event_id":"sha256:a3c4d12c6965ee0f7c73a832bfd9a8823af5067096235b6578480bab051ce3e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CKJSAEZPM6XVWFBRTSO5A6OCQG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:25:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K9ocUbB0ugAzusCXz87Ov/2v34Ap4YAmjbj1NusZKnC5cZbbnXIX+LIos41XhQRDUX8dEmOrtC6NPpWT5AhlBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:22:01.236893Z"},"content_sha256":"0178ced84eaaa9977b104c3b843ee1361911c9156dbc05bf07fac0faf1ca8477","schema_version":"1.0","event_id":"sha256:0178ced84eaaa9977b104c3b843ee1361911c9156dbc05bf07fac0faf1ca8477"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CKJSAEZPM6XVWFBRTSO5A6OCQG/bundle.json","state_url":"https://pith.science/pith/CKJSAEZPM6XVWFBRTSO5A6OCQG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CKJSAEZPM6XVWFBRTSO5A6OCQG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-22T22:22:01Z","links":{"resolver":"https://pith.science/pith/CKJSAEZPM6XVWFBRTSO5A6OCQG","bundle":"https://pith.science/pith/CKJSAEZPM6XVWFBRTSO5A6OCQG/bundle.json","state":"https://pith.science/pith/CKJSAEZPM6XVWFBRTSO5A6OCQG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CKJSAEZPM6XVWFBRTSO5A6OCQG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CKJSAEZPM6XVWFBRTSO5A6OCQG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3669db22074102a4e4be00d0241a78ef9f4ef3abdb8b310789d6387863ada85e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-18T15:16:54Z","title_canon_sha256":"56e55daf7054ac52f8f17ee022499a08bae3454698917ca159e228940f1be16c"},"schema_version":"1.0","source":{"id":"2312.11272","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11272","created_at":"2026-07-05T07:25:30Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11272v1","created_at":"2026-07-05T07:25:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11272","created_at":"2026-07-05T07:25:30Z"},{"alias_kind":"pith_short_12","alias_value":"CKJSAEZPM6XV","created_at":"2026-07-05T07:25:30Z"},{"alias_kind":"pith_short_16","alias_value":"CKJSAEZPM6XVWFBR","created_at":"2026-07-05T07:25:30Z"},{"alias_kind":"pith_short_8","alias_value":"CKJSAEZP","created_at":"2026-07-05T07:25:30Z"}],"graph_snapshots":[{"event_id":"sha256:0178ced84eaaa9977b104c3b843ee1361911c9156dbc05bf07fac0faf1ca8477","target":"graph","created_at":"2026-07-05T07:25:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.11272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Paola Merlo, Vivi Nastase","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-18T15:16:54Z","title":"Disentangling continuous and discrete linguistic signals in transformer-based sentence embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11272","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a3c4d12c6965ee0f7c73a832bfd9a8823af5067096235b6578480bab051ce3e6","target":"record","created_at":"2026-07-05T07:25:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3669db22074102a4e4be00d0241a78ef9f4ef3abdb8b310789d6387863ada85e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-18T15:16:54Z","title_canon_sha256":"56e55daf7054ac52f8f17ee022499a08bae3454698917ca159e228940f1be16c"},"schema_version":"1.0","source":{"id":"2312.11272","kind":"arxiv","version":1}},"canonical_sha256":"129320132f67af5b14319c9dd079c28194113112178d9e047f7978b72710eac9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"129320132f67af5b14319c9dd079c28194113112178d9e047f7978b72710eac9","first_computed_at":"2026-07-05T07:25:30.655473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:30.655473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jx4q2R04L0WI5mMgMlf5letNKCHfen6w1k5WawSAarGSECkCpe72REn0CouQKJAUlaO6FfTpmGFagV08je1bCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:30.656111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.11272","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3c4d12c6965ee0f7c73a832bfd9a8823af5067096235b6578480bab051ce3e6","sha256:0178ced84eaaa9977b104c3b843ee1361911c9156dbc05bf07fac0faf1ca8477"],"state_sha256":"ebd4838161ddc3723e6585cc0de62287ba4994df3cd299b18a120ca18556fabf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BtgIDbEs37E52sArHJFWFUotBiucmZH+CMC1IXzg7fk1VR8C2CZj60zd8d+XNvJ9ey1arsZh/KD+Gk53wbxADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T22:22:01.241626Z","bundle_sha256":"f8a1e250cd66989ed31a5694142fedceb33ee4f43188d52e190f3f00c7de453c"}}