{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4QUXSHGD22YSS5VRQ43D3X567L","short_pith_number":"pith:4QUXSHGD","canonical_record":{"source":{"id":"2608.12771","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-13T03:29:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"256787b77855946b906683e0a0e5d6fe0edbde38302edaf78715a01917074d25","abstract_canon_sha256":"d002c4c9cfe615e2db952e0361c7a01fed4a3a99fe4cac4bb42ff37c0d5c9dc4"},"schema_version":"1.0"},"canonical_sha256":"e429791cc3d6b12976b187363ddfbefacc6980f4ddf306af3322fb4bb48d5c42","source":{"kind":"arxiv","id":"2608.12771","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12771","created_at":"2026-08-14T00:47:45Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12771v1","created_at":"2026-08-14T00:47:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12771","created_at":"2026-08-14T00:47:45Z"},{"alias_kind":"pith_short_12","alias_value":"4QUXSHGD22YS","created_at":"2026-08-14T00:47:45Z"},{"alias_kind":"pith_short_16","alias_value":"4QUXSHGD22YSS5VR","created_at":"2026-08-14T00:47:45Z"},{"alias_kind":"pith_short_8","alias_value":"4QUXSHGD","created_at":"2026-08-14T00:47:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4QUXSHGD22YSS5VRQ43D3X567L","target":"record","payload":{"canonical_record":{"source":{"id":"2608.12771","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-13T03:29:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"256787b77855946b906683e0a0e5d6fe0edbde38302edaf78715a01917074d25","abstract_canon_sha256":"d002c4c9cfe615e2db952e0361c7a01fed4a3a99fe4cac4bb42ff37c0d5c9dc4"},"schema_version":"1.0"},"canonical_sha256":"e429791cc3d6b12976b187363ddfbefacc6980f4ddf306af3322fb4bb48d5c42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:47:45.214624Z","signature_b64":"4ZtEpRlbBeJLF2T37/eauEHTTthQSF0vDHqIE3Jl9q6dLZRH08JlMek9qjQgriu4ksaXPngABDzAX/X3vXOHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e429791cc3d6b12976b187363ddfbefacc6980f4ddf306af3322fb4bb48d5c42","last_reissued_at":"2026-08-14T00:47:45.201333Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:47:45.201333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.12771","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":"2026-08-14T00:47:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u8db71gPhDBsgb9DYzZdrmnWMt2ejGgwjVx+UgeWxLYyYjkiRqkU/1CCJiT0wxnFNZR4py6qcyIDGPxuqY8eDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:45:29.479893Z"},"content_sha256":"9a9b3ba109c19ccaeda2abb88f070edcb5e0138fcccf799a0e7fe62d6b5fcab5","schema_version":"1.0","event_id":"sha256:9a9b3ba109c19ccaeda2abb88f070edcb5e0138fcccf799a0e7fe62d6b5fcab5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4QUXSHGD22YSS5VRQ43D3X567L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Memorization Diagnostics for Code LLMs Should be Scale-Aware","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Abdoul Aziz Bonkoungou, Alberick Euraste Djir\\'e, El Hacen Diallo, Iyiola Emmanuel Olatunji, Jacques Klein, Prateek Kumar Rajput, Tegawend\\'e F. Bissyand\\'e, Xunzhu Tang, Yewei Song","submitted_at":"2026-08-13T03:29:00Z","abstract_excerpt":"The extent to which large language models for code rely on memorization over genuine understanding remains highly debated. While current literature frequently reports widespread memorization, evaluating the underlying probing techniques across dense architectures reveals a severe breakdown in their utility at scale. Traditional encoder-style probes using perturbations such as synonym fuzzing or dead-code insertion struggle to expose memorization in scaled models, even on known-contaminated benchmarks, and decoder-style probes that rely on log probabilities show similar performance degradation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12771","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/2608.12771/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":"2026-08-14T00:47:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Iuf2fnUwbwjHWVAs0f5u/tl8fEA0oByC86w3vuAGBBMoAQo4jdvvb910T5w/aDgew+76IBpvNpqhS1IdQNMNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:45:29.480557Z"},"content_sha256":"c5eb6d0de3ac947e47385cb3b3211b8a6cec46b1c4c3548a7230624adf89a73e","schema_version":"1.0","event_id":"sha256:c5eb6d0de3ac947e47385cb3b3211b8a6cec46b1c4c3548a7230624adf89a73e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4QUXSHGD22YSS5VRQ43D3X567L/bundle.json","state_url":"https://pith.science/pith/4QUXSHGD22YSS5VRQ43D3X567L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4QUXSHGD22YSS5VRQ43D3X567L/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":"2026-08-17T22:45:29Z","links":{"resolver":"https://pith.science/pith/4QUXSHGD22YSS5VRQ43D3X567L","bundle":"https://pith.science/pith/4QUXSHGD22YSS5VRQ43D3X567L/bundle.json","state":"https://pith.science/pith/4QUXSHGD22YSS5VRQ43D3X567L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4QUXSHGD22YSS5VRQ43D3X567L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4QUXSHGD22YSS5VRQ43D3X567L","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":"d002c4c9cfe615e2db952e0361c7a01fed4a3a99fe4cac4bb42ff37c0d5c9dc4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-13T03:29:00Z","title_canon_sha256":"256787b77855946b906683e0a0e5d6fe0edbde38302edaf78715a01917074d25"},"schema_version":"1.0","source":{"id":"2608.12771","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12771","created_at":"2026-08-14T00:47:45Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12771v1","created_at":"2026-08-14T00:47:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12771","created_at":"2026-08-14T00:47:45Z"},{"alias_kind":"pith_short_12","alias_value":"4QUXSHGD22YS","created_at":"2026-08-14T00:47:45Z"},{"alias_kind":"pith_short_16","alias_value":"4QUXSHGD22YSS5VR","created_at":"2026-08-14T00:47:45Z"},{"alias_kind":"pith_short_8","alias_value":"4QUXSHGD","created_at":"2026-08-14T00:47:45Z"}],"graph_snapshots":[{"event_id":"sha256:c5eb6d0de3ac947e47385cb3b3211b8a6cec46b1c4c3548a7230624adf89a73e","target":"graph","created_at":"2026-08-14T00:47:45Z","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/2608.12771/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The extent to which large language models for code rely on memorization over genuine understanding remains highly debated. While current literature frequently reports widespread memorization, evaluating the underlying probing techniques across dense architectures reveals a severe breakdown in their utility at scale. Traditional encoder-style probes using perturbations such as synonym fuzzing or dead-code insertion struggle to expose memorization in scaled models, even on known-contaminated benchmarks, and decoder-style probes that rely on log probabilities show similar performance degradation.","authors_text":"Abdoul Aziz Bonkoungou, Alberick Euraste Djir\\'e, El Hacen Diallo, Iyiola Emmanuel Olatunji, Jacques Klein, Prateek Kumar Rajput, Tegawend\\'e F. Bissyand\\'e, Xunzhu Tang, Yewei Song","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-13T03:29:00Z","title":"Memorization Diagnostics for Code LLMs Should be Scale-Aware"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12771","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":"sha256:9a9b3ba109c19ccaeda2abb88f070edcb5e0138fcccf799a0e7fe62d6b5fcab5","target":"record","created_at":"2026-08-14T00:47:45Z","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":"d002c4c9cfe615e2db952e0361c7a01fed4a3a99fe4cac4bb42ff37c0d5c9dc4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-13T03:29:00Z","title_canon_sha256":"256787b77855946b906683e0a0e5d6fe0edbde38302edaf78715a01917074d25"},"schema_version":"1.0","source":{"id":"2608.12771","kind":"arxiv","version":1}},"canonical_sha256":"e429791cc3d6b12976b187363ddfbefacc6980f4ddf306af3322fb4bb48d5c42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e429791cc3d6b12976b187363ddfbefacc6980f4ddf306af3322fb4bb48d5c42","first_computed_at":"2026-08-14T00:47:45.201333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T00:47:45.201333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4ZtEpRlbBeJLF2T37/eauEHTTthQSF0vDHqIE3Jl9q6dLZRH08JlMek9qjQgriu4ksaXPngABDzAX/X3vXOHAg==","signature_status":"signed_v1","signed_at":"2026-08-14T00:47:45.214624Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.12771","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a9b3ba109c19ccaeda2abb88f070edcb5e0138fcccf799a0e7fe62d6b5fcab5","sha256:c5eb6d0de3ac947e47385cb3b3211b8a6cec46b1c4c3548a7230624adf89a73e"],"state_sha256":"8a170c41d0afb311b8bc0cefa06fb60305174d7da2464d896495a2501091e725"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kOacTRvdKRhvphkluLK3uNedIdvobOUTHn1XwIOK04Njb8lZeLpXEdlBkwYmWU1MJuxO3oQJ+a3hPiaYylreDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T22:45:29.487719Z","bundle_sha256":"1c56be7265b26e6d9b6a3e5a2c3b112980ee315212e66e7978907bff5f7660c4"}}