{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KQTM7B4SGCX4YOSQSR7PWZIOKC","short_pith_number":"pith:KQTM7B4S","canonical_record":{"source":{"id":"2402.11842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-02-19T05:13:22Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0336eae4a81fb08c43cb7f3bb77e147e4ceeba666e61ede9c80e73df91426c9c","abstract_canon_sha256":"91f6319930afe381946dc2deda7052dd531d6c99422d56d777927fc0a0962fff"},"schema_version":"1.0"},"canonical_sha256":"5426cf879230afcc3a50947efb650e50b7c94c831f0142bf19e8e71b1efc2419","source":{"kind":"arxiv","id":"2402.11842","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11842","created_at":"2026-07-05T09:38:24Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11842v1","created_at":"2026-07-05T09:38:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11842","created_at":"2026-07-05T09:38:24Z"},{"alias_kind":"pith_short_12","alias_value":"KQTM7B4SGCX4","created_at":"2026-07-05T09:38:24Z"},{"alias_kind":"pith_short_16","alias_value":"KQTM7B4SGCX4YOSQ","created_at":"2026-07-05T09:38:24Z"},{"alias_kind":"pith_short_8","alias_value":"KQTM7B4S","created_at":"2026-07-05T09:38:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KQTM7B4SGCX4YOSQSR7PWZIOKC","target":"record","payload":{"canonical_record":{"source":{"id":"2402.11842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-02-19T05:13:22Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0336eae4a81fb08c43cb7f3bb77e147e4ceeba666e61ede9c80e73df91426c9c","abstract_canon_sha256":"91f6319930afe381946dc2deda7052dd531d6c99422d56d777927fc0a0962fff"},"schema_version":"1.0"},"canonical_sha256":"5426cf879230afcc3a50947efb650e50b7c94c831f0142bf19e8e71b1efc2419","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:24.532844Z","signature_b64":"zcPp5QUDPS3Dc58LthqZObUqvygQ9shQo/m12KI0qN/+BcyLdI0WR9dfTnP1XuLNrPHH+7z0rwCHLtfUMmo+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5426cf879230afcc3a50947efb650e50b7c94c831f0142bf19e8e71b1efc2419","last_reissued_at":"2026-07-05T09:38:24.532369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:24.532369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.11842","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":"2026-07-05T09:38:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4FKDK2y8LKlyvPBelXEzPVgSh1O4QUDf2ucm1OKn98KGv7om5Fo+KgzO+vF6zDLV1HM7q5y570amqnfewP5FAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T21:48:48.675816Z"},"content_sha256":"b0a23afe68359bd02908ef23a0d40836b90b456db59cd7c09507cacdee1ee5ff","schema_version":"1.0","event_id":"sha256:b0a23afe68359bd02908ef23a0d40836b90b456db59cd7c09507cacdee1ee5ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KQTM7B4SGCX4YOSQSR7PWZIOKC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Jianjun Huang, Xiangyu Zhang, Xiangzhe Xu, Yapeng Ye, Zhuo Zhang, Zian Su, Ziyang Huang","submitted_at":"2024-02-19T05:13:22Z","abstract_excerpt":"Transformer based code models have impressive performance in many software engineering tasks. However, their effectiveness degrades when symbols are missing or not informative. The reason is that the model may not learn to pay attention to the right correlations/contexts without the help of symbols. We propose a new method to pre-train general code models when symbols are lacking. We observe that in such cases, programs degenerate to something written in a very primitive language. We hence propose to use program analysis to extract contexts a priori (instead of relying on symbols and masked la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11842","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/2402.11842/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":"2026-07-05T09:38:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LllltOc1fhY+GcXw1pTJ8b6O/WpqKu0WcH6BtMGGNv6pi8Rmadl/tEo89k4g8c1ksBNtROm8Lc1QUo4oLFC2Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T21:48:48.676197Z"},"content_sha256":"98d80ffaa3bbed8a32af0c5896fa9f24afa4f1305990267cd4772ee8e26748b0","schema_version":"1.0","event_id":"sha256:98d80ffaa3bbed8a32af0c5896fa9f24afa4f1305990267cd4772ee8e26748b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KQTM7B4SGCX4YOSQSR7PWZIOKC/bundle.json","state_url":"https://pith.science/pith/KQTM7B4SGCX4YOSQSR7PWZIOKC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KQTM7B4SGCX4YOSQSR7PWZIOKC/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":"2026-07-06T21:48:48Z","links":{"resolver":"https://pith.science/pith/KQTM7B4SGCX4YOSQSR7PWZIOKC","bundle":"https://pith.science/pith/KQTM7B4SGCX4YOSQSR7PWZIOKC/bundle.json","state":"https://pith.science/pith/KQTM7B4SGCX4YOSQSR7PWZIOKC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KQTM7B4SGCX4YOSQSR7PWZIOKC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KQTM7B4SGCX4YOSQSR7PWZIOKC","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":"91f6319930afe381946dc2deda7052dd531d6c99422d56d777927fc0a0962fff","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-02-19T05:13:22Z","title_canon_sha256":"0336eae4a81fb08c43cb7f3bb77e147e4ceeba666e61ede9c80e73df91426c9c"},"schema_version":"1.0","source":{"id":"2402.11842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11842","created_at":"2026-07-05T09:38:24Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11842v1","created_at":"2026-07-05T09:38:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11842","created_at":"2026-07-05T09:38:24Z"},{"alias_kind":"pith_short_12","alias_value":"KQTM7B4SGCX4","created_at":"2026-07-05T09:38:24Z"},{"alias_kind":"pith_short_16","alias_value":"KQTM7B4SGCX4YOSQ","created_at":"2026-07-05T09:38:24Z"},{"alias_kind":"pith_short_8","alias_value":"KQTM7B4S","created_at":"2026-07-05T09:38:24Z"}],"graph_snapshots":[{"event_id":"sha256:98d80ffaa3bbed8a32af0c5896fa9f24afa4f1305990267cd4772ee8e26748b0","target":"graph","created_at":"2026-07-05T09:38:24Z","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/2402.11842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer based code models have impressive performance in many software engineering tasks. However, their effectiveness degrades when symbols are missing or not informative. The reason is that the model may not learn to pay attention to the right correlations/contexts without the help of symbols. We propose a new method to pre-train general code models when symbols are lacking. We observe that in such cases, programs degenerate to something written in a very primitive language. We hence propose to use program analysis to extract contexts a priori (instead of relying on symbols and masked la","authors_text":"Jianjun Huang, Xiangyu Zhang, Xiangzhe Xu, Yapeng Ye, Zhuo Zhang, Zian Su, Ziyang Huang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-02-19T05:13:22Z","title":"CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11842","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:b0a23afe68359bd02908ef23a0d40836b90b456db59cd7c09507cacdee1ee5ff","target":"record","created_at":"2026-07-05T09:38:24Z","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":"91f6319930afe381946dc2deda7052dd531d6c99422d56d777927fc0a0962fff","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-02-19T05:13:22Z","title_canon_sha256":"0336eae4a81fb08c43cb7f3bb77e147e4ceeba666e61ede9c80e73df91426c9c"},"schema_version":"1.0","source":{"id":"2402.11842","kind":"arxiv","version":1}},"canonical_sha256":"5426cf879230afcc3a50947efb650e50b7c94c831f0142bf19e8e71b1efc2419","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5426cf879230afcc3a50947efb650e50b7c94c831f0142bf19e8e71b1efc2419","first_computed_at":"2026-07-05T09:38:24.532369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:24.532369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zcPp5QUDPS3Dc58LthqZObUqvygQ9shQo/m12KI0qN/+BcyLdI0WR9dfTnP1XuLNrPHH+7z0rwCHLtfUMmo+Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:24.532844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0a23afe68359bd02908ef23a0d40836b90b456db59cd7c09507cacdee1ee5ff","sha256:98d80ffaa3bbed8a32af0c5896fa9f24afa4f1305990267cd4772ee8e26748b0"],"state_sha256":"bd856a524f8458a55e2643d76106ab5856345d74dafb9fced1d4e5709b683913"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X5ShIHBSk6IEm+FRpaqdCifG+8F2wxkB77G87EdV1L0FHqgvopcGFjV9gbk7JMf5RHUaBefFK4FbTZqwSdd3CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T21:48:48.678212Z","bundle_sha256":"d928d1c0d1b6df8d2e77b969d2cc869e7bdffb46d5292fdfa1dc3302f66f8d38"}}