{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:C2NIUA5XRURBXHEVUDPMYOVZZD","short_pith_number":"pith:C2NIUA5X","canonical_record":{"source":{"id":"2306.11943","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-06-20T23:42:14Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"8632860e8ab9bad0a4a09b525b420892b2f49e6a194efdb3c9f66628e68e381d","abstract_canon_sha256":"f911ed213d5f7603a0282132b9de3401954e2cbf0163a73dcbd0fd21857c2cf1"},"schema_version":"1.0"},"canonical_sha256":"169a8a03b78d221b9c95a0decc3ab9c8e500549f5e012f9cf9c450ffe6fda0ff","source":{"kind":"arxiv","id":"2306.11943","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11943","created_at":"2026-07-05T07:50:02Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11943v2","created_at":"2026-07-05T07:50:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11943","created_at":"2026-07-05T07:50:02Z"},{"alias_kind":"pith_short_12","alias_value":"C2NIUA5XRURB","created_at":"2026-07-05T07:50:02Z"},{"alias_kind":"pith_short_16","alias_value":"C2NIUA5XRURBXHEV","created_at":"2026-07-05T07:50:02Z"},{"alias_kind":"pith_short_8","alias_value":"C2NIUA5X","created_at":"2026-07-05T07:50:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:C2NIUA5XRURBXHEVUDPMYOVZZD","target":"record","payload":{"canonical_record":{"source":{"id":"2306.11943","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-06-20T23:42:14Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"8632860e8ab9bad0a4a09b525b420892b2f49e6a194efdb3c9f66628e68e381d","abstract_canon_sha256":"f911ed213d5f7603a0282132b9de3401954e2cbf0163a73dcbd0fd21857c2cf1"},"schema_version":"1.0"},"canonical_sha256":"169a8a03b78d221b9c95a0decc3ab9c8e500549f5e012f9cf9c450ffe6fda0ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:02.045038Z","signature_b64":"7Qk8lkeeXG9UlQOuoxnIEPdXXugeMELs5z4SJFnAlS07UV9WElkS1jXOnknm5loSCX+O4rVKajNmCRHmTCiiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"169a8a03b78d221b9c95a0decc3ab9c8e500549f5e012f9cf9c450ffe6fda0ff","last_reissued_at":"2026-07-05T07:50:02.044626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:02.044626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.11943","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":"2026-07-05T07:50:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sVWL+NFlX11XU0fC52KmEnnBu1ye9R5UzIdzdXTjfU6LvlZPrinh9F89CZveDVJz/HILWMlghQC6F/V27nJnCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:40:03.462453Z"},"content_sha256":"c811296ebbc81f8335bdb81d31308f0517afd9f5d9b7c30e17c7db87f3c6a596","schema_version":"1.0","event_id":"sha256:c811296ebbc81f8335bdb81d31308f0517afd9f5d9b7c30e17c7db87f3c6a596"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:C2NIUA5XRURBXHEVUDPMYOVZZD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Understanding What Code Language Models Learned","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Cathy Wang, Chengxuan Huang, Dian Yu, Kenji Sagae, Prem Devanbu, Toufique Ahmed","submitted_at":"2023-06-20T23:42:14Z","abstract_excerpt":"Pre-trained language models are effective in a variety of natural language tasks, but it has been argued their capabilities fall short of fully learning meaning or understanding language. To understand the extent to which language models can learn some form of meaning, we investigate their ability to capture semantics of code beyond superficial frequency and co-occurrence. In contrast to previous research on probing models for linguistic features, we study pre-trained models in a setting that allows for objective and straightforward evaluation of a model's ability to learn semantics. In this p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11943","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/2306.11943/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":"2026-07-05T07:50:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fxjb/JjxvSmoIwjfbHzrYB4Bd5z61F96zcj/L0NDYSQbtKx+/I4YOjnr7NngeBxoI+Ig213njnmgyJWwEA+fCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:40:03.462978Z"},"content_sha256":"869cd7ab2414d4250ecb3d331a8f18d588412771e0dea920c55622adf1283e39","schema_version":"1.0","event_id":"sha256:869cd7ab2414d4250ecb3d331a8f18d588412771e0dea920c55622adf1283e39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C2NIUA5XRURBXHEVUDPMYOVZZD/bundle.json","state_url":"https://pith.science/pith/C2NIUA5XRURBXHEVUDPMYOVZZD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C2NIUA5XRURBXHEVUDPMYOVZZD/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":"2026-08-20T01:40:03Z","links":{"resolver":"https://pith.science/pith/C2NIUA5XRURBXHEVUDPMYOVZZD","bundle":"https://pith.science/pith/C2NIUA5XRURBXHEVUDPMYOVZZD/bundle.json","state":"https://pith.science/pith/C2NIUA5XRURBXHEVUDPMYOVZZD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C2NIUA5XRURBXHEVUDPMYOVZZD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:C2NIUA5XRURBXHEVUDPMYOVZZD","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":"f911ed213d5f7603a0282132b9de3401954e2cbf0163a73dcbd0fd21857c2cf1","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-06-20T23:42:14Z","title_canon_sha256":"8632860e8ab9bad0a4a09b525b420892b2f49e6a194efdb3c9f66628e68e381d"},"schema_version":"1.0","source":{"id":"2306.11943","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11943","created_at":"2026-07-05T07:50:02Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11943v2","created_at":"2026-07-05T07:50:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11943","created_at":"2026-07-05T07:50:02Z"},{"alias_kind":"pith_short_12","alias_value":"C2NIUA5XRURB","created_at":"2026-07-05T07:50:02Z"},{"alias_kind":"pith_short_16","alias_value":"C2NIUA5XRURBXHEV","created_at":"2026-07-05T07:50:02Z"},{"alias_kind":"pith_short_8","alias_value":"C2NIUA5X","created_at":"2026-07-05T07:50:02Z"}],"graph_snapshots":[{"event_id":"sha256:869cd7ab2414d4250ecb3d331a8f18d588412771e0dea920c55622adf1283e39","target":"graph","created_at":"2026-07-05T07:50:02Z","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/2306.11943/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained language models are effective in a variety of natural language tasks, but it has been argued their capabilities fall short of fully learning meaning or understanding language. To understand the extent to which language models can learn some form of meaning, we investigate their ability to capture semantics of code beyond superficial frequency and co-occurrence. In contrast to previous research on probing models for linguistic features, we study pre-trained models in a setting that allows for objective and straightforward evaluation of a model's ability to learn semantics. In this p","authors_text":"Cathy Wang, Chengxuan Huang, Dian Yu, Kenji Sagae, Prem Devanbu, Toufique Ahmed","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-06-20T23:42:14Z","title":"Towards Understanding What Code Language Models Learned"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11943","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:c811296ebbc81f8335bdb81d31308f0517afd9f5d9b7c30e17c7db87f3c6a596","target":"record","created_at":"2026-07-05T07:50:02Z","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":"f911ed213d5f7603a0282132b9de3401954e2cbf0163a73dcbd0fd21857c2cf1","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-06-20T23:42:14Z","title_canon_sha256":"8632860e8ab9bad0a4a09b525b420892b2f49e6a194efdb3c9f66628e68e381d"},"schema_version":"1.0","source":{"id":"2306.11943","kind":"arxiv","version":2}},"canonical_sha256":"169a8a03b78d221b9c95a0decc3ab9c8e500549f5e012f9cf9c450ffe6fda0ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"169a8a03b78d221b9c95a0decc3ab9c8e500549f5e012f9cf9c450ffe6fda0ff","first_computed_at":"2026-07-05T07:50:02.044626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:02.044626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Qk8lkeeXG9UlQOuoxnIEPdXXugeMELs5z4SJFnAlS07UV9WElkS1jXOnknm5loSCX+O4rVKajNmCRHmTCiiCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:02.045038Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.11943","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c811296ebbc81f8335bdb81d31308f0517afd9f5d9b7c30e17c7db87f3c6a596","sha256:869cd7ab2414d4250ecb3d331a8f18d588412771e0dea920c55622adf1283e39"],"state_sha256":"e114d71e8bf9a1c3a50bd7c00f5aa33674521b1ff3dd4bc1fe95097d135f54d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k8r+krIEXo3/NRHBKwqgmpxOrn7RkBjbQ492oqvspx0NPkN8VGDzSBX1mtJh9N5jD3MM3mR4xLV4/HNO/kyeCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T01:40:03.468715Z","bundle_sha256":"48da815953674bfa7e1dd73b1720091ca7971ad756891f560af516e07edd4955"}}