{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BAIM75JXNWAGMI2CSDUEYG7WWH","short_pith_number":"pith:BAIM75JX","canonical_record":{"source":{"id":"2303.08117","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-14T17:49:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b83caedd2f85ac8200a221a5eabc7701c64a47131d77496579c42fae0a80918f","abstract_canon_sha256":"1f7b082ca1495e4599780deabaeeaf70dbea164bd3a7aeebc4eca1db489e5cc4"},"schema_version":"1.0"},"canonical_sha256":"0810cff5376d8066234290e84c1bf6b1dfb0668c74520b7e358aefdde7f5f849","source":{"kind":"arxiv","id":"2303.08117","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.08117","created_at":"2026-07-05T07:00:59Z"},{"alias_kind":"arxiv_version","alias_value":"2303.08117v2","created_at":"2026-07-05T07:00:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08117","created_at":"2026-07-05T07:00:59Z"},{"alias_kind":"pith_short_12","alias_value":"BAIM75JXNWAG","created_at":"2026-07-05T07:00:59Z"},{"alias_kind":"pith_short_16","alias_value":"BAIM75JXNWAGMI2C","created_at":"2026-07-05T07:00:59Z"},{"alias_kind":"pith_short_8","alias_value":"BAIM75JX","created_at":"2026-07-05T07:00:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BAIM75JXNWAGMI2CSDUEYG7WWH","target":"record","payload":{"canonical_record":{"source":{"id":"2303.08117","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-14T17:49:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b83caedd2f85ac8200a221a5eabc7701c64a47131d77496579c42fae0a80918f","abstract_canon_sha256":"1f7b082ca1495e4599780deabaeeaf70dbea164bd3a7aeebc4eca1db489e5cc4"},"schema_version":"1.0"},"canonical_sha256":"0810cff5376d8066234290e84c1bf6b1dfb0668c74520b7e358aefdde7f5f849","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:59.487675Z","signature_b64":"sH02kJ9tIUaQJXdH2q0CupG4V8IqA6m5ur8Sua8NWpHS19EXpbOFV1Bw3980cy3sIpsNFT1biyRHg/sPMETaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0810cff5376d8066234290e84c1bf6b1dfb0668c74520b7e358aefdde7f5f849","last_reissued_at":"2026-07-05T07:00:59.487173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:59.487173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.08117","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":"2026-07-05T07:00:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k2lhlpQ5XFbfmh+jecH7qrJky3DBht5hBBA7wNpelFtu/NuRjuO+fQk01zFePW3qZvXgy5HUkBgpxtJ4gdkmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:27:51.120784Z"},"content_sha256":"3e38054984a83d9065d4aa309e62704641790fa660847e5852bae005f1b66cdf","schema_version":"1.0","event_id":"sha256:3e38054984a83d9065d4aa309e62704641790fa660847e5852bae005f1b66cdf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BAIM75JXNWAGMI2CSDUEYG7WWH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Transformers Parse while Predicting the Masked Word?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhishek Panigrahi, Haoyu Zhao, Rong Ge, Sanjeev Arora","submitted_at":"2023-03-14T17:49:50Z","abstract_excerpt":"Pre-trained language models have been shown to encode linguistic structures, e.g. dependency and constituency parse trees, in their embeddings while being trained on unsupervised loss functions like masked language modeling. Some doubts have been raised whether the models actually are doing parsing or only some computation weakly correlated with it. We study questions: (a) Is it possible to explicitly describe transformers with realistic embedding dimension, number of heads, etc. that are capable of doing parsing -- or even approximate parsing? (b) Why do pre-trained models capture parsing str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08117","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/2303.08117/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":"2026-07-05T07:00:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Tnd81KeL8+9t+DQWfS5voLx0bn5j88wO4MCRt5jjIWy8T/WiK3ldAPYCZxRnEHHgdrg7rUYN2RtSbKDLAmQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:27:51.121323Z"},"content_sha256":"b8368852eba6cfd9f2b8ec046f2fcb86b31577995fb21e4b9793fe3c304d3f71","schema_version":"1.0","event_id":"sha256:b8368852eba6cfd9f2b8ec046f2fcb86b31577995fb21e4b9793fe3c304d3f71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BAIM75JXNWAGMI2CSDUEYG7WWH/bundle.json","state_url":"https://pith.science/pith/BAIM75JXNWAGMI2CSDUEYG7WWH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BAIM75JXNWAGMI2CSDUEYG7WWH/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":"2026-08-17T14:27:51Z","links":{"resolver":"https://pith.science/pith/BAIM75JXNWAGMI2CSDUEYG7WWH","bundle":"https://pith.science/pith/BAIM75JXNWAGMI2CSDUEYG7WWH/bundle.json","state":"https://pith.science/pith/BAIM75JXNWAGMI2CSDUEYG7WWH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BAIM75JXNWAGMI2CSDUEYG7WWH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BAIM75JXNWAGMI2CSDUEYG7WWH","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":"1f7b082ca1495e4599780deabaeeaf70dbea164bd3a7aeebc4eca1db489e5cc4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-14T17:49:50Z","title_canon_sha256":"b83caedd2f85ac8200a221a5eabc7701c64a47131d77496579c42fae0a80918f"},"schema_version":"1.0","source":{"id":"2303.08117","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.08117","created_at":"2026-07-05T07:00:59Z"},{"alias_kind":"arxiv_version","alias_value":"2303.08117v2","created_at":"2026-07-05T07:00:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08117","created_at":"2026-07-05T07:00:59Z"},{"alias_kind":"pith_short_12","alias_value":"BAIM75JXNWAG","created_at":"2026-07-05T07:00:59Z"},{"alias_kind":"pith_short_16","alias_value":"BAIM75JXNWAGMI2C","created_at":"2026-07-05T07:00:59Z"},{"alias_kind":"pith_short_8","alias_value":"BAIM75JX","created_at":"2026-07-05T07:00:59Z"}],"graph_snapshots":[{"event_id":"sha256:b8368852eba6cfd9f2b8ec046f2fcb86b31577995fb21e4b9793fe3c304d3f71","target":"graph","created_at":"2026-07-05T07:00:59Z","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/2303.08117/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained language models have been shown to encode linguistic structures, e.g. dependency and constituency parse trees, in their embeddings while being trained on unsupervised loss functions like masked language modeling. Some doubts have been raised whether the models actually are doing parsing or only some computation weakly correlated with it. We study questions: (a) Is it possible to explicitly describe transformers with realistic embedding dimension, number of heads, etc. that are capable of doing parsing -- or even approximate parsing? (b) Why do pre-trained models capture parsing str","authors_text":"Abhishek Panigrahi, Haoyu Zhao, Rong Ge, Sanjeev Arora","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-14T17:49:50Z","title":"Do Transformers Parse while Predicting the Masked Word?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08117","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":"sha256:3e38054984a83d9065d4aa309e62704641790fa660847e5852bae005f1b66cdf","target":"record","created_at":"2026-07-05T07:00:59Z","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":"1f7b082ca1495e4599780deabaeeaf70dbea164bd3a7aeebc4eca1db489e5cc4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-14T17:49:50Z","title_canon_sha256":"b83caedd2f85ac8200a221a5eabc7701c64a47131d77496579c42fae0a80918f"},"schema_version":"1.0","source":{"id":"2303.08117","kind":"arxiv","version":2}},"canonical_sha256":"0810cff5376d8066234290e84c1bf6b1dfb0668c74520b7e358aefdde7f5f849","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0810cff5376d8066234290e84c1bf6b1dfb0668c74520b7e358aefdde7f5f849","first_computed_at":"2026-07-05T07:00:59.487173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:59.487173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sH02kJ9tIUaQJXdH2q0CupG4V8IqA6m5ur8Sua8NWpHS19EXpbOFV1Bw3980cy3sIpsNFT1biyRHg/sPMETaCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:59.487675Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.08117","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e38054984a83d9065d4aa309e62704641790fa660847e5852bae005f1b66cdf","sha256:b8368852eba6cfd9f2b8ec046f2fcb86b31577995fb21e4b9793fe3c304d3f71"],"state_sha256":"e38340597c05595c739609c0b4e82887922d3a65796049fe5a1b3112dbe47bb6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jKMuGoiayxETOrpy5ArNeAQSe2vYDoSEW6W0ZCH/Mk5QW2lnWrUs9udhL7TCBAnRSCk4ST0MH8QaF+w+NU/fCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T14:27:51.125684Z","bundle_sha256":"1e7f7a721fc7459ad0cdb5c4857dde7e73d555cc627a5e101146ed44132186b3"}}