{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XTO2WV7QXYP2UA5DVZ75WZQMAV","short_pith_number":"pith:XTO2WV7Q","canonical_record":{"source":{"id":"2204.06201","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-13T07:07:37Z","cross_cats_sorted":[],"title_canon_sha256":"db2bfe0243ac6069b49b82ddf42a382f38497ed3a3850e16433f2d4e7722cffb","abstract_canon_sha256":"c8c4cb02daa80d4da172a251dae06deaa9a6e6b3e76fd72f92f3325781d9267e"},"schema_version":"1.0"},"canonical_sha256":"bcddab57f0be1faa03a3ae7fdb660c056babec1c873f97d431c67e69b9993116","source":{"kind":"arxiv","id":"2204.06201","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.06201","created_at":"2026-07-05T04:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2204.06201v1","created_at":"2026-07-05T04:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.06201","created_at":"2026-07-05T04:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"XTO2WV7QXYP2","created_at":"2026-07-05T04:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"XTO2WV7QXYP2UA5D","created_at":"2026-07-05T04:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"XTO2WV7Q","created_at":"2026-07-05T04:14:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XTO2WV7QXYP2UA5DVZ75WZQMAV","target":"record","payload":{"canonical_record":{"source":{"id":"2204.06201","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-13T07:07:37Z","cross_cats_sorted":[],"title_canon_sha256":"db2bfe0243ac6069b49b82ddf42a382f38497ed3a3850e16433f2d4e7722cffb","abstract_canon_sha256":"c8c4cb02daa80d4da172a251dae06deaa9a6e6b3e76fd72f92f3325781d9267e"},"schema_version":"1.0"},"canonical_sha256":"bcddab57f0be1faa03a3ae7fdb660c056babec1c873f97d431c67e69b9993116","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:31.249636Z","signature_b64":"LeydQ7UySUpSqyL9IyFf2eP+AAy9Mn4xhwH86oSzbH9KjumtORqp723nPwqtMei/kYyL9sWzDuWGHJdOoJy7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcddab57f0be1faa03a3ae7fdb660c056babec1c873f97d431c67e69b9993116","last_reissued_at":"2026-07-05T04:14:31.249173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:31.249173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.06201","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":"2026-07-05T04:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pqkIraxdBps2DwWfE6Q0Y7bEriANee/3mycoosJTZ8s3DHz9uusFz40/M+j6p9o1wd7N2F7ZRK8eY2t/r08uDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:31:14.981013Z"},"content_sha256":"3efed1dfa22a5e5ed4addb92cfbaccb72de8ff5ebb70a42c544aea8d61582b68","schema_version":"1.0","event_id":"sha256:3efed1dfa22a5e5ed4addb92cfbaccb72de8ff5ebb70a42c544aea8d61582b68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XTO2WV7QXYP2UA5DVZ75WZQMAV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probing for Constituency Structure in Neural Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Arps, Hassan Sajjad, Laura Kallmeyer, Younes Samih","submitted_at":"2022-04-13T07:07:37Z","abstract_excerpt":"In this paper, we investigate to which extent contextual neural language models (LMs) implicitly learn syntactic structure. More concretely, we focus on constituent structure as represented in the Penn Treebank (PTB). Using standard probing techniques based on diagnostic classifiers, we assess the accuracy of representing constituents of different categories within the neuron activations of a LM such as RoBERTa. In order to make sure that our probe focuses on syntactic knowledge and not on implicit semantic generalizations, we also experiment on a PTB version that is obtained by randomly repla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.06201","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/2204.06201/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":"2026-07-05T04:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m4a+lHDq3UkwEcRhNGTgnYVqj1umvZ//eK8+q23Mkt32dU2r4qg2EYW4IUgUNvoCjGCTm0u1rU+PkzFSrH22BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:31:14.981927Z"},"content_sha256":"127061d8470f5e2a4ee825f6dae8cbd852f1559aad174c5c72e77493eb7ca071","schema_version":"1.0","event_id":"sha256:127061d8470f5e2a4ee825f6dae8cbd852f1559aad174c5c72e77493eb7ca071"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XTO2WV7QXYP2UA5DVZ75WZQMAV/bundle.json","state_url":"https://pith.science/pith/XTO2WV7QXYP2UA5DVZ75WZQMAV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XTO2WV7QXYP2UA5DVZ75WZQMAV/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":"2026-08-09T07:31:14Z","links":{"resolver":"https://pith.science/pith/XTO2WV7QXYP2UA5DVZ75WZQMAV","bundle":"https://pith.science/pith/XTO2WV7QXYP2UA5DVZ75WZQMAV/bundle.json","state":"https://pith.science/pith/XTO2WV7QXYP2UA5DVZ75WZQMAV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XTO2WV7QXYP2UA5DVZ75WZQMAV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XTO2WV7QXYP2UA5DVZ75WZQMAV","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":"c8c4cb02daa80d4da172a251dae06deaa9a6e6b3e76fd72f92f3325781d9267e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-13T07:07:37Z","title_canon_sha256":"db2bfe0243ac6069b49b82ddf42a382f38497ed3a3850e16433f2d4e7722cffb"},"schema_version":"1.0","source":{"id":"2204.06201","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.06201","created_at":"2026-07-05T04:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2204.06201v1","created_at":"2026-07-05T04:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.06201","created_at":"2026-07-05T04:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"XTO2WV7QXYP2","created_at":"2026-07-05T04:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"XTO2WV7QXYP2UA5D","created_at":"2026-07-05T04:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"XTO2WV7Q","created_at":"2026-07-05T04:14:31Z"}],"graph_snapshots":[{"event_id":"sha256:127061d8470f5e2a4ee825f6dae8cbd852f1559aad174c5c72e77493eb7ca071","target":"graph","created_at":"2026-07-05T04:14:31Z","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/2204.06201/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we investigate to which extent contextual neural language models (LMs) implicitly learn syntactic structure. More concretely, we focus on constituent structure as represented in the Penn Treebank (PTB). Using standard probing techniques based on diagnostic classifiers, we assess the accuracy of representing constituents of different categories within the neuron activations of a LM such as RoBERTa. In order to make sure that our probe focuses on syntactic knowledge and not on implicit semantic generalizations, we also experiment on a PTB version that is obtained by randomly repla","authors_text":"David Arps, Hassan Sajjad, Laura Kallmeyer, Younes Samih","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-13T07:07:37Z","title":"Probing for Constituency Structure in Neural Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.06201","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":"sha256:3efed1dfa22a5e5ed4addb92cfbaccb72de8ff5ebb70a42c544aea8d61582b68","target":"record","created_at":"2026-07-05T04:14:31Z","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":"c8c4cb02daa80d4da172a251dae06deaa9a6e6b3e76fd72f92f3325781d9267e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-13T07:07:37Z","title_canon_sha256":"db2bfe0243ac6069b49b82ddf42a382f38497ed3a3850e16433f2d4e7722cffb"},"schema_version":"1.0","source":{"id":"2204.06201","kind":"arxiv","version":1}},"canonical_sha256":"bcddab57f0be1faa03a3ae7fdb660c056babec1c873f97d431c67e69b9993116","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcddab57f0be1faa03a3ae7fdb660c056babec1c873f97d431c67e69b9993116","first_computed_at":"2026-07-05T04:14:31.249173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:14:31.249173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LeydQ7UySUpSqyL9IyFf2eP+AAy9Mn4xhwH86oSzbH9KjumtORqp723nPwqtMei/kYyL9sWzDuWGHJdOoJy7Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:14:31.249636Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.06201","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3efed1dfa22a5e5ed4addb92cfbaccb72de8ff5ebb70a42c544aea8d61582b68","sha256:127061d8470f5e2a4ee825f6dae8cbd852f1559aad174c5c72e77493eb7ca071"],"state_sha256":"5b03507cd7122fde96aca98d1c02dc27e602e5f5868b81c9a1d83a4f0101ad17"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oQgNJj3Ur5I3Ydn6zXSSrQm42FjK46mJBr6Hjey7WuP5Tk9xJWShgfGF/eOn9YK6xNPw12SUnGGnJjXAwe/BBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:31:14.986716Z","bundle_sha256":"73c496a0149a8cfe43873aeb28e5bba663b5e7e3f6cde8b95268ebc275b23901"}}