{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GFOT3LZBOHF5KZZPGBD6MUK2WG","short_pith_number":"pith:GFOT3LZB","canonical_record":{"source":{"id":"2010.12784","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T05:06:29Z","cross_cats_sorted":[],"title_canon_sha256":"f5bb1494f4215eda268bfec63d858c9bb757319aa9dfa9293eeb43e024e14196","abstract_canon_sha256":"51fcc538a4689a646800a6ee6fefa50609b761b2b996612dcbb8e79aed674ec1"},"schema_version":"1.0"},"canonical_sha256":"315d3daf2171cbd5672f3047e6515ab1a87f5f1dd5848335380008b57d6600a1","source":{"kind":"arxiv","id":"2010.12784","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12784","created_at":"2026-07-05T03:36:52Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12784v2","created_at":"2026-07-05T03:36:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12784","created_at":"2026-07-05T03:36:52Z"},{"alias_kind":"pith_short_12","alias_value":"GFOT3LZBOHF5","created_at":"2026-07-05T03:36:52Z"},{"alias_kind":"pith_short_16","alias_value":"GFOT3LZBOHF5KZZP","created_at":"2026-07-05T03:36:52Z"},{"alias_kind":"pith_short_8","alias_value":"GFOT3LZB","created_at":"2026-07-05T03:36:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GFOT3LZBOHF5KZZPGBD6MUK2WG","target":"record","payload":{"canonical_record":{"source":{"id":"2010.12784","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T05:06:29Z","cross_cats_sorted":[],"title_canon_sha256":"f5bb1494f4215eda268bfec63d858c9bb757319aa9dfa9293eeb43e024e14196","abstract_canon_sha256":"51fcc538a4689a646800a6ee6fefa50609b761b2b996612dcbb8e79aed674ec1"},"schema_version":"1.0"},"canonical_sha256":"315d3daf2171cbd5672f3047e6515ab1a87f5f1dd5848335380008b57d6600a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:52.122191Z","signature_b64":"3k9Gd98eZ/qGqRPtI8yJWeM0oiAx2OlKcPZ3Tqp1+5kG/WOYbHLgYhxL8E9JRVU46RzCYV4s/hhLxahdDE3ECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"315d3daf2171cbd5672f3047e6515ab1a87f5f1dd5848335380008b57d6600a1","last_reissued_at":"2026-07-05T03:36:52.121698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:52.121698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.12784","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":"2026-07-05T03:36:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nIrFkVL+TABT6sleTZ+x9/oArBRad3oBVGPJu3SzGXT9PGuLSD1MysLV0S20UtwuaGALmzlgDOJjTiNOfY/kCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T08:13:01.454399Z"},"content_sha256":"64e32eba360fd5ad9a5a218f5020dc2e7832a0a8f5aab4448bb99f44d46ea6b2","schema_version":"1.0","event_id":"sha256:64e32eba360fd5ad9a5a218f5020dc2e7832a0a8f5aab4448bb99f44d46ea6b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GFOT3LZBOHF5KZZPGBD6MUK2WG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Clustering of Text Representations for Supervision-free Probing of Syntax","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoyue Shi, Kevin Gimpel, Mrinmaya Sachan, Vikram Gupta","submitted_at":"2020-10-24T05:06:29Z","abstract_excerpt":"We explore deep clustering of text representations for unsupervised model interpretation and induction of syntax. As these representations are high-dimensional, out-of-the-box methods like KMeans do not work well. Thus, our approach jointly transforms the representations into a lower-dimensional cluster-friendly space and clusters them. We consider two notions of syntax: Part of speech Induction (POSI) and constituency labelling (CoLab) in this work. Interestingly, we find that Multilingual BERT (mBERT) contains surprising amount of syntactic knowledge of English; possibly even as much as Engl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12784","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/2010.12784/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":"2026-07-05T03:36:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FOzAiQR4T1UvGQqcuIJ6yaYVF09+y1Uo71ESjz0/DRT54U/mJMbbaYxmORHtNYqGNEtFaIBsl8vjVjpsUHgpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T08:13:01.455335Z"},"content_sha256":"ac2653b7e0d1c8ec3f47e43f62c5e276b5d2a226aa51eb7fde732747d8c74c51","schema_version":"1.0","event_id":"sha256:ac2653b7e0d1c8ec3f47e43f62c5e276b5d2a226aa51eb7fde732747d8c74c51"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GFOT3LZBOHF5KZZPGBD6MUK2WG/bundle.json","state_url":"https://pith.science/pith/GFOT3LZBOHF5KZZPGBD6MUK2WG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GFOT3LZBOHF5KZZPGBD6MUK2WG/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":"2026-08-15T08:13:01Z","links":{"resolver":"https://pith.science/pith/GFOT3LZBOHF5KZZPGBD6MUK2WG","bundle":"https://pith.science/pith/GFOT3LZBOHF5KZZPGBD6MUK2WG/bundle.json","state":"https://pith.science/pith/GFOT3LZBOHF5KZZPGBD6MUK2WG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GFOT3LZBOHF5KZZPGBD6MUK2WG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GFOT3LZBOHF5KZZPGBD6MUK2WG","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":"51fcc538a4689a646800a6ee6fefa50609b761b2b996612dcbb8e79aed674ec1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T05:06:29Z","title_canon_sha256":"f5bb1494f4215eda268bfec63d858c9bb757319aa9dfa9293eeb43e024e14196"},"schema_version":"1.0","source":{"id":"2010.12784","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12784","created_at":"2026-07-05T03:36:52Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12784v2","created_at":"2026-07-05T03:36:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12784","created_at":"2026-07-05T03:36:52Z"},{"alias_kind":"pith_short_12","alias_value":"GFOT3LZBOHF5","created_at":"2026-07-05T03:36:52Z"},{"alias_kind":"pith_short_16","alias_value":"GFOT3LZBOHF5KZZP","created_at":"2026-07-05T03:36:52Z"},{"alias_kind":"pith_short_8","alias_value":"GFOT3LZB","created_at":"2026-07-05T03:36:52Z"}],"graph_snapshots":[{"event_id":"sha256:ac2653b7e0d1c8ec3f47e43f62c5e276b5d2a226aa51eb7fde732747d8c74c51","target":"graph","created_at":"2026-07-05T03:36:52Z","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/2010.12784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore deep clustering of text representations for unsupervised model interpretation and induction of syntax. As these representations are high-dimensional, out-of-the-box methods like KMeans do not work well. Thus, our approach jointly transforms the representations into a lower-dimensional cluster-friendly space and clusters them. We consider two notions of syntax: Part of speech Induction (POSI) and constituency labelling (CoLab) in this work. Interestingly, we find that Multilingual BERT (mBERT) contains surprising amount of syntactic knowledge of English; possibly even as much as Engl","authors_text":"Haoyue Shi, Kevin Gimpel, Mrinmaya Sachan, Vikram Gupta","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T05:06:29Z","title":"Deep Clustering of Text Representations for Supervision-free Probing of Syntax"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12784","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":"sha256:64e32eba360fd5ad9a5a218f5020dc2e7832a0a8f5aab4448bb99f44d46ea6b2","target":"record","created_at":"2026-07-05T03:36:52Z","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":"51fcc538a4689a646800a6ee6fefa50609b761b2b996612dcbb8e79aed674ec1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T05:06:29Z","title_canon_sha256":"f5bb1494f4215eda268bfec63d858c9bb757319aa9dfa9293eeb43e024e14196"},"schema_version":"1.0","source":{"id":"2010.12784","kind":"arxiv","version":2}},"canonical_sha256":"315d3daf2171cbd5672f3047e6515ab1a87f5f1dd5848335380008b57d6600a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"315d3daf2171cbd5672f3047e6515ab1a87f5f1dd5848335380008b57d6600a1","first_computed_at":"2026-07-05T03:36:52.121698Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:36:52.121698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3k9Gd98eZ/qGqRPtI8yJWeM0oiAx2OlKcPZ3Tqp1+5kG/WOYbHLgYhxL8E9JRVU46RzCYV4s/hhLxahdDE3ECQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:36:52.122191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12784","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64e32eba360fd5ad9a5a218f5020dc2e7832a0a8f5aab4448bb99f44d46ea6b2","sha256:ac2653b7e0d1c8ec3f47e43f62c5e276b5d2a226aa51eb7fde732747d8c74c51"],"state_sha256":"a7a7fee202ba9d09490196d8a9441df36a8bbf4159e9a4c15409cf5fc6e990fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4YaL1Ynq21OORSd2GxPwXqzRtqEp5YHvIN5GK4c3N0LFG0M2ItD62lp38AcU9iX7bq6kScatluU+y/e9eRVEDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T08:13:01.466622Z","bundle_sha256":"08340e001ff4fe0fca964edd508c6f8f0106a7e3f8961d7e87d61f003fdf97ae"}}