{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2NQMNM7URDBHAIYM6JYMVSGV3V","short_pith_number":"pith:2NQMNM7U","canonical_record":{"source":{"id":"1805.01070","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-03T00:46:56Z","cross_cats_sorted":[],"title_canon_sha256":"a1f6aa0d42d96acbd4bf40cb327ffde3555bfa71d74204a95efd340644969546","abstract_canon_sha256":"65d8f5e02ead85f7a867b0abd87ec37f499c13c3755ad6eed43e4ca0f8a70c6f"},"schema_version":"1.0"},"canonical_sha256":"d360c6b3f488c270230cf270cac8d5dd56228d737260ce5b4cd05ef33e9c916b","source":{"kind":"arxiv","id":"1805.01070","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.01070","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"arxiv_version","alias_value":"1805.01070v2","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.01070","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"pith_short_12","alias_value":"2NQMNM7URDBH","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2NQMNM7URDBHAIYM","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2NQMNM7U","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2NQMNM7URDBHAIYM6JYMVSGV3V","target":"record","payload":{"canonical_record":{"source":{"id":"1805.01070","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-03T00:46:56Z","cross_cats_sorted":[],"title_canon_sha256":"a1f6aa0d42d96acbd4bf40cb327ffde3555bfa71d74204a95efd340644969546","abstract_canon_sha256":"65d8f5e02ead85f7a867b0abd87ec37f499c13c3755ad6eed43e4ca0f8a70c6f"},"schema_version":"1.0"},"canonical_sha256":"d360c6b3f488c270230cf270cac8d5dd56228d737260ce5b4cd05ef33e9c916b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:17.415553Z","signature_b64":"0DMmyVKUP+OT/F14N5YMVAh1ef42dyIzV2vikz7Oe0hC1jtTN/mr5y2n+flpkTXRGWdQScvy/RXsaJjknTA1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d360c6b3f488c270230cf270cac8d5dd56228d737260ce5b4cd05ef33e9c916b","last_reissued_at":"2026-05-18T00:11:17.414800Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:17.414800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.01070","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P6jFhN2pVbpix0otyz0SAPN/3CRPXUUjmYX+mOKBBfytj8/0VbcSO/7x0RQoBrI3AARG6A0uAFOdcfwAThL2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:57:03.556264Z"},"content_sha256":"44241184691778cf632505b9c942a0522a00c80850b6ec11c640b2d399e49f83","schema_version":"1.0","event_id":"sha256:44241184691778cf632505b9c942a0522a00c80850b6ec11c640b2d399e49f83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2NQMNM7URDBHAIYM6JYMVSGV3V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexis Conneau, German Kruszewski, Guillaume Lample, Lo\\\"ic Barrault, Marco Baroni","submitted_at":"2018-05-03T00:46:56Z","abstract_excerpt":"Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing. \"Downstream\" tasks, often based on sentence classification, are commonly used to evaluate the quality of sentence representations. The complexity of the tasks makes it however difficult to infer what kind of information is present in the representations. We introduce here 10 probing tasks designed to capture simple linguistic features of sentences, and we use them to study embeddings generated by three different encoders trained in eight di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.01070","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":""},"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":"2026-05-18T00:11:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pxyB4dg4AE9Njns1h1+QnDvFC6/lGf/afwgtVmw34vsA/ADbuRTQy4gjPB2HzKe8DMwnObJtnHnJifQ6rmaTBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:57:03.556996Z"},"content_sha256":"f5d253761df8aaaaa39cbd5eb1d367d64c75192b45cb40b56b60a1be847180e9","schema_version":"1.0","event_id":"sha256:f5d253761df8aaaaa39cbd5eb1d367d64c75192b45cb40b56b60a1be847180e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2NQMNM7URDBHAIYM6JYMVSGV3V/bundle.json","state_url":"https://pith.science/pith/2NQMNM7URDBHAIYM6JYMVSGV3V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2NQMNM7URDBHAIYM6JYMVSGV3V/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":"2026-05-29T15:57:03Z","links":{"resolver":"https://pith.science/pith/2NQMNM7URDBHAIYM6JYMVSGV3V","bundle":"https://pith.science/pith/2NQMNM7URDBHAIYM6JYMVSGV3V/bundle.json","state":"https://pith.science/pith/2NQMNM7URDBHAIYM6JYMVSGV3V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2NQMNM7URDBHAIYM6JYMVSGV3V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2NQMNM7URDBHAIYM6JYMVSGV3V","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":"65d8f5e02ead85f7a867b0abd87ec37f499c13c3755ad6eed43e4ca0f8a70c6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-03T00:46:56Z","title_canon_sha256":"a1f6aa0d42d96acbd4bf40cb327ffde3555bfa71d74204a95efd340644969546"},"schema_version":"1.0","source":{"id":"1805.01070","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.01070","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"arxiv_version","alias_value":"1805.01070v2","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.01070","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"pith_short_12","alias_value":"2NQMNM7URDBH","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2NQMNM7URDBHAIYM","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2NQMNM7U","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:f5d253761df8aaaaa39cbd5eb1d367d64c75192b45cb40b56b60a1be847180e9","target":"graph","created_at":"2026-05-18T00:11:17Z","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"},"paper":{"abstract_excerpt":"Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing. \"Downstream\" tasks, often based on sentence classification, are commonly used to evaluate the quality of sentence representations. The complexity of the tasks makes it however difficult to infer what kind of information is present in the representations. We introduce here 10 probing tasks designed to capture simple linguistic features of sentences, and we use them to study embeddings generated by three different encoders trained in eight di","authors_text":"Alexis Conneau, German Kruszewski, Guillaume Lample, Lo\\\"ic Barrault, Marco Baroni","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-03T00:46:56Z","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.01070","kind":"arxiv","version":2},"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":"sha256:44241184691778cf632505b9c942a0522a00c80850b6ec11c640b2d399e49f83","target":"record","created_at":"2026-05-18T00:11:17Z","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":"65d8f5e02ead85f7a867b0abd87ec37f499c13c3755ad6eed43e4ca0f8a70c6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-03T00:46:56Z","title_canon_sha256":"a1f6aa0d42d96acbd4bf40cb327ffde3555bfa71d74204a95efd340644969546"},"schema_version":"1.0","source":{"id":"1805.01070","kind":"arxiv","version":2}},"canonical_sha256":"d360c6b3f488c270230cf270cac8d5dd56228d737260ce5b4cd05ef33e9c916b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d360c6b3f488c270230cf270cac8d5dd56228d737260ce5b4cd05ef33e9c916b","first_computed_at":"2026-05-18T00:11:17.414800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:17.414800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0DMmyVKUP+OT/F14N5YMVAh1ef42dyIzV2vikz7Oe0hC1jtTN/mr5y2n+flpkTXRGWdQScvy/RXsaJjknTA1Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:17.415553Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.01070","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44241184691778cf632505b9c942a0522a00c80850b6ec11c640b2d399e49f83","sha256:f5d253761df8aaaaa39cbd5eb1d367d64c75192b45cb40b56b60a1be847180e9"],"state_sha256":"a61de032de954e0348f5fcbb91ee0a434d4f806f37c8215fe62582742b209957"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rv2APBwRnwi9gSyBZLXw2UrWai2GEnqOKdYB4AhD8iW5bqIx4esdYDa4RXkEAXe223Z0uLGQDD9nv0rWCa+wBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T15:57:03.560889Z","bundle_sha256":"894c679169acb9dca1cf83e0ce6bc7322ec99409f15b868135b5537e44fa4c8e"}}