{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QNF3DFM2BVLPZ737VJ3PGRP2ZB","short_pith_number":"pith:QNF3DFM2","schema_version":"1.0","canonical_sha256":"834bb1959a0d56fcff7faa76f345fac846135e707d8cc1f3b302d41e23e2cb9a","source":{"kind":"arxiv","id":"2111.05827","version":2},"attestation_state":"computed","paper":{"title":"Data-Driven AI Model Signal-Awareness Enhancement and Introspection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alessandro Morari, Jim Laredo, Sahil Suneja, Yufan Zhuang, Yunhui Zheng","submitted_at":"2021-11-10T17:58:18Z","abstract_excerpt":"AI modeling for source code understanding tasks has been making significant progress, and is being adopted in production development pipelines. However, reliability concerns, especially whether the models are actually learning task-related aspects of source code, are being raised. While recent model-probing approaches have observed a lack of signal awareness in many AI-for-code models, i.e. models not capturing task-relevant signals, they do not offer solutions to rectify this problem. In this paper, we explore data-driven approaches to enhance models' signal-awareness: 1) we combine the SE co"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2111.05827","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2021-11-10T17:58:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"edec0507b330d7455fc2082ae9445d2b023e66df7962710645a030b4ff31ea37","abstract_canon_sha256":"6265635e7fffd7bc09d4632b11e5ecae81e06acc2269adee4034a58c5b197575"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:46.039635Z","signature_b64":"LgXJrRkKuPJZoIu4SbNYaULusKTzgwpTePCD9ROG71EOtGLBvRslmVf0ughKawB3QSeVa8CqLCa0WjEbOuyRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"834bb1959a0d56fcff7faa76f345fac846135e707d8cc1f3b302d41e23e2cb9a","last_reissued_at":"2026-07-05T03:46:46.039272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:46.039272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Driven AI Model Signal-Awareness Enhancement and Introspection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alessandro Morari, Jim Laredo, Sahil Suneja, Yufan Zhuang, Yunhui Zheng","submitted_at":"2021-11-10T17:58:18Z","abstract_excerpt":"AI modeling for source code understanding tasks has been making significant progress, and is being adopted in production development pipelines. However, reliability concerns, especially whether the models are actually learning task-related aspects of source code, are being raised. While recent model-probing approaches have observed a lack of signal awareness in many AI-for-code models, i.e. models not capturing task-relevant signals, they do not offer solutions to rectify this problem. In this paper, we explore data-driven approaches to enhance models' signal-awareness: 1) we combine the SE co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05827","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/2111.05827/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.05827","created_at":"2026-07-05T03:46:46.039333+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.05827v2","created_at":"2026-07-05T03:46:46.039333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05827","created_at":"2026-07-05T03:46:46.039333+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNF3DFM2BVLP","created_at":"2026-07-05T03:46:46.039333+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNF3DFM2BVLPZ737","created_at":"2026-07-05T03:46:46.039333+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNF3DFM2","created_at":"2026-07-05T03:46:46.039333+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB","json":"https://pith.science/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB.json","graph_json":"https://pith.science/api/pith-number/QNF3DFM2BVLPZ737VJ3PGRP2ZB/graph.json","events_json":"https://pith.science/api/pith-number/QNF3DFM2BVLPZ737VJ3PGRP2ZB/events.json","paper":"https://pith.science/paper/QNF3DFM2"},"agent_actions":{"view_html":"https://pith.science/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB","download_json":"https://pith.science/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB.json","view_paper":"https://pith.science/paper/QNF3DFM2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.05827&json=true","fetch_graph":"https://pith.science/api/pith-number/QNF3DFM2BVLPZ737VJ3PGRP2ZB/graph.json","fetch_events":"https://pith.science/api/pith-number/QNF3DFM2BVLPZ737VJ3PGRP2ZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB/action/storage_attestation","attest_author":"https://pith.science/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB/action/author_attestation","sign_citation":"https://pith.science/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB/action/citation_signature","submit_replication":"https://pith.science/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB/action/replication_record"}},"created_at":"2026-07-05T03:46:46.039333+00:00","updated_at":"2026-07-05T03:46:46.039333+00:00"}