{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2YFTWZ3U2UFOPIUR5GILRO4AVL","short_pith_number":"pith:2YFTWZ3U","schema_version":"1.0","canonical_sha256":"d60b3b6774d50ae7a291e990b8bb80aaf988fd3ecfa3484eac3abb811ba8f785","source":{"kind":"arxiv","id":"2606.27406","version":1},"attestation_state":"computed","paper":{"title":"Towards Evaluation of Implicit Software World Models in Coding LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Egor Bogomolov, Yaroslav Zharov","submitted_at":"2026-06-25T08:02:32Z","abstract_excerpt":"Software engineering, whether performed by humans or by AI agents, requires reasoning about how software behaves. We call the internal model that supports such reasoning the software world model, and view current code-execution benchmarks as covering one well-studied slice of it -- control flow. In this paper, we take a step toward a broader evaluation by shifting the observable axis to execution resources: alongside test outcome and exception class, we predict peak memory, wall-clock time, and ranked profiler outputs at method and line granularity. We use SWE-bench Verified as the source of d"},"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":"2606.27406","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-25T08:02:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b16e003fde0714b4ce6d0490efac4160b3e1c31c909a32f5c8fa7315f0767256","abstract_canon_sha256":"26a3084abfe0912541cd8c3f325e3ce7c628467d0f5ca9b3d4f56c70ea338ca8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T00:14:04.996461Z","signature_b64":"X1WXAiW4jB251xS+63Bxp4xMXr0pG4C9yOZvma88jaYbcQ//CgEOFN2rPJ1UnTgl2/8w/bUTth4BFp+wtdLYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d60b3b6774d50ae7a291e990b8bb80aaf988fd3ecfa3484eac3abb811ba8f785","last_reissued_at":"2026-06-29T00:14:04.995989Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T00:14:04.995989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Evaluation of Implicit Software World Models in Coding LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Egor Bogomolov, Yaroslav Zharov","submitted_at":"2026-06-25T08:02:32Z","abstract_excerpt":"Software engineering, whether performed by humans or by AI agents, requires reasoning about how software behaves. We call the internal model that supports such reasoning the software world model, and view current code-execution benchmarks as covering one well-studied slice of it -- control flow. In this paper, we take a step toward a broader evaluation by shifting the observable axis to execution resources: alongside test outcome and exception class, we predict peak memory, wall-clock time, and ranked profiler outputs at method and line granularity. We use SWE-bench Verified as the source of d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27406","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/2606.27406/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":"2606.27406","created_at":"2026-06-29T00:14:04.996046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27406v1","created_at":"2026-06-29T00:14:04.996046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27406","created_at":"2026-06-29T00:14:04.996046+00:00"},{"alias_kind":"pith_short_12","alias_value":"2YFTWZ3U2UFO","created_at":"2026-06-29T00:14:04.996046+00:00"},{"alias_kind":"pith_short_16","alias_value":"2YFTWZ3U2UFOPIUR","created_at":"2026-06-29T00:14:04.996046+00:00"},{"alias_kind":"pith_short_8","alias_value":"2YFTWZ3U","created_at":"2026-06-29T00:14:04.996046+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/2YFTWZ3U2UFOPIUR5GILRO4AVL","json":"https://pith.science/pith/2YFTWZ3U2UFOPIUR5GILRO4AVL.json","graph_json":"https://pith.science/api/pith-number/2YFTWZ3U2UFOPIUR5GILRO4AVL/graph.json","events_json":"https://pith.science/api/pith-number/2YFTWZ3U2UFOPIUR5GILRO4AVL/events.json","paper":"https://pith.science/paper/2YFTWZ3U"},"agent_actions":{"view_html":"https://pith.science/pith/2YFTWZ3U2UFOPIUR5GILRO4AVL","download_json":"https://pith.science/pith/2YFTWZ3U2UFOPIUR5GILRO4AVL.json","view_paper":"https://pith.science/paper/2YFTWZ3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27406&json=true","fetch_graph":"https://pith.science/api/pith-number/2YFTWZ3U2UFOPIUR5GILRO4AVL/graph.json","fetch_events":"https://pith.science/api/pith-number/2YFTWZ3U2UFOPIUR5GILRO4AVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2YFTWZ3U2UFOPIUR5GILRO4AVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2YFTWZ3U2UFOPIUR5GILRO4AVL/action/storage_attestation","attest_author":"https://pith.science/pith/2YFTWZ3U2UFOPIUR5GILRO4AVL/action/author_attestation","sign_citation":"https://pith.science/pith/2YFTWZ3U2UFOPIUR5GILRO4AVL/action/citation_signature","submit_replication":"https://pith.science/pith/2YFTWZ3U2UFOPIUR5GILRO4AVL/action/replication_record"}},"created_at":"2026-06-29T00:14:04.996046+00:00","updated_at":"2026-06-29T00:14:04.996046+00:00"}