{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QNF3DFM2BVLPZ737VJ3PGRP2ZB","short_pith_number":"pith:QNF3DFM2","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"},"canonical_sha256":"834bb1959a0d56fcff7faa76f345fac846135e707d8cc1f3b302d41e23e2cb9a","source":{"kind":"arxiv","id":"2111.05827","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.05827","created_at":"2026-07-05T03:46:46Z"},{"alias_kind":"arxiv_version","alias_value":"2111.05827v2","created_at":"2026-07-05T03:46:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05827","created_at":"2026-07-05T03:46:46Z"},{"alias_kind":"pith_short_12","alias_value":"QNF3DFM2BVLP","created_at":"2026-07-05T03:46:46Z"},{"alias_kind":"pith_short_16","alias_value":"QNF3DFM2BVLPZ737","created_at":"2026-07-05T03:46:46Z"},{"alias_kind":"pith_short_8","alias_value":"QNF3DFM2","created_at":"2026-07-05T03:46:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QNF3DFM2BVLPZ737VJ3PGRP2ZB","target":"record","payload":{"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"},"canonical_sha256":"834bb1959a0d56fcff7faa76f345fac846135e707d8cc1f3b302d41e23e2cb9a","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"},"source_kind":"arxiv","source_id":"2111.05827","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":"2026-07-05T03:46:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eX1Lghm93L77TvhHgrrzHrBg97GEcwoVWsnBks4Y5mclpkmMIM5h1YXIzTdkr5Ktmr2ZOT8ELgzL5pCQ0HLRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:46:46.535466Z"},"content_sha256":"56748e0ab5930df71afbbc952d9396691709fc4a7816dce891e33d3ce0c17f8d","schema_version":"1.0","event_id":"sha256:56748e0ab5930df71afbbc952d9396691709fc4a7816dce891e33d3ce0c17f8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QNF3DFM2BVLPZ737VJ3PGRP2ZB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:46:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pmMB1NX4QbpORRmwvzCXfkjT3HIvzU6F7nKP0rttrHluVh5V26KUhQLIXMM4P7l8NZmFn5jzSAmceaROYUi6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:46:46.535859Z"},"content_sha256":"2e4f647a1665f4ae72921c3fbbf8d61a89b086b7cad5cfb6522fe2288ecef700","schema_version":"1.0","event_id":"sha256:2e4f647a1665f4ae72921c3fbbf8d61a89b086b7cad5cfb6522fe2288ecef700"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB/bundle.json","state_url":"https://pith.science/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB/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":"2026-07-06T13:46:46Z","links":{"resolver":"https://pith.science/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB","bundle":"https://pith.science/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB/bundle.json","state":"https://pith.science/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QNF3DFM2BVLPZ737VJ3PGRP2ZB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QNF3DFM2BVLPZ737VJ3PGRP2ZB","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":"6265635e7fffd7bc09d4632b11e5ecae81e06acc2269adee4034a58c5b197575","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2021-11-10T17:58:18Z","title_canon_sha256":"edec0507b330d7455fc2082ae9445d2b023e66df7962710645a030b4ff31ea37"},"schema_version":"1.0","source":{"id":"2111.05827","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.05827","created_at":"2026-07-05T03:46:46Z"},{"alias_kind":"arxiv_version","alias_value":"2111.05827v2","created_at":"2026-07-05T03:46:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05827","created_at":"2026-07-05T03:46:46Z"},{"alias_kind":"pith_short_12","alias_value":"QNF3DFM2BVLP","created_at":"2026-07-05T03:46:46Z"},{"alias_kind":"pith_short_16","alias_value":"QNF3DFM2BVLPZ737","created_at":"2026-07-05T03:46:46Z"},{"alias_kind":"pith_short_8","alias_value":"QNF3DFM2","created_at":"2026-07-05T03:46:46Z"}],"graph_snapshots":[{"event_id":"sha256:2e4f647a1665f4ae72921c3fbbf8d61a89b086b7cad5cfb6522fe2288ecef700","target":"graph","created_at":"2026-07-05T03:46:46Z","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/2111.05827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alessandro Morari, Jim Laredo, Sahil Suneja, Yufan Zhuang, Yunhui Zheng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2021-11-10T17:58:18Z","title":"Data-Driven AI Model Signal-Awareness Enhancement and Introspection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05827","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":"sha256:56748e0ab5930df71afbbc952d9396691709fc4a7816dce891e33d3ce0c17f8d","target":"record","created_at":"2026-07-05T03:46:46Z","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":"6265635e7fffd7bc09d4632b11e5ecae81e06acc2269adee4034a58c5b197575","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2021-11-10T17:58:18Z","title_canon_sha256":"edec0507b330d7455fc2082ae9445d2b023e66df7962710645a030b4ff31ea37"},"schema_version":"1.0","source":{"id":"2111.05827","kind":"arxiv","version":2}},"canonical_sha256":"834bb1959a0d56fcff7faa76f345fac846135e707d8cc1f3b302d41e23e2cb9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"834bb1959a0d56fcff7faa76f345fac846135e707d8cc1f3b302d41e23e2cb9a","first_computed_at":"2026-07-05T03:46:46.039272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:46:46.039272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LgXJrRkKuPJZoIu4SbNYaULusKTzgwpTePCD9ROG71EOtGLBvRslmVf0ughKawB3QSeVa8CqLCa0WjEbOuyRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:46:46.039635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.05827","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56748e0ab5930df71afbbc952d9396691709fc4a7816dce891e33d3ce0c17f8d","sha256:2e4f647a1665f4ae72921c3fbbf8d61a89b086b7cad5cfb6522fe2288ecef700"],"state_sha256":"802f86d3b86c256de559e11d4f6cafa1422a67fa992813c517ee9b0adf38b1eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZiaIvc+buEdNUAxSTyXMad6veHftQ5hqnJbJ+Vz8rzYdS8h8OhU73p8ZBU0IZGN+7liDX5WFTw4wrU+TPVAIDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T13:46:46.537817Z","bundle_sha256":"fdf54bab2cbae602dfcfee3e304fd20afbb74f8f624098de990df97d316263eb"}}