{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LYSKY53JXYNFCTXIVDNSTAN4FD","merge_version":"pith-open-graph-merge-v1","event_count":5,"valid_event_count":5,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"420afc6e83a127f6a68cd02c300580ba796bff2d97057a95a173064f6980392f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T19:23:27Z","title_canon_sha256":"b4fa9463f7f2bc9e77529c53eea8c7721d24e97a8393e5106f3c509de81371fb"},"schema_version":"1.0","source":{"id":"2605.22981","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22981","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22981v1","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22981","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"pith_short_12","alias_value":"LYSKY53JXYNF","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"pith_short_16","alias_value":"LYSKY53JXYNFCTXI","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"pith_short_8","alias_value":"LYSKY53J","created_at":"2026-05-25T02:01:33Z"}],"graph_snapshots":[{"event_id":"sha256:bdbf5071d32a612418b0410a0cee13b6427d685e1ac6615520b6d5c0bbdbf266","target":"graph","created_at":"2026-05-25T02:01:33Z","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/2605.22981/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fill-in-the-middle (FIM) is a pretraining objective widely used to equip causal language models with infilling ability, yet its effect on verbatim memorization remains underexplored. We study the memorization dynamics of FIM in a controlled setting by pretraining matched Llama 3.2 models with FIM and standard left-to-right (LTR) objectives on a FineWeb-Gutenberg corpus containing repeated Gutenberg excerpts. With prefix-based probes, FIM more often recovers short or partially matching spans, while LTR more often assigns high confidence to long exact continuations. We observe that verbatim extr","authors_text":"Tanguy Dieudonn\\'e, Tobias von Arx","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T19:23:27Z","title":"Memorization Dynamics of Fill-in-the-Middle Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22981","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":"sha256:457333eb464d55ea39614ae637d13c60dcc8063ff97c13d0673c049aab300246","target":"record","created_at":"2026-05-25T02:01:33Z","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":"420afc6e83a127f6a68cd02c300580ba796bff2d97057a95a173064f6980392f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T19:23:27Z","title_canon_sha256":"b4fa9463f7f2bc9e77529c53eea8c7721d24e97a8393e5106f3c509de81371fb"},"schema_version":"1.0","source":{"id":"2605.22981","kind":"arxiv","version":1}},"canonical_sha256":"5e24ac7769be1a514ee8a8db2981bc28f2eb0022e15d545559f56ff66a741204","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e24ac7769be1a514ee8a8db2981bc28f2eb0022e15d545559f56ff66a741204","first_computed_at":"2026-05-25T02:01:33.109984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:33.109984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZfQ2AioY88c035fcd54ZTwskKLy2T6tWenxW2rZfjdnVr5CYphVYek2vzHDCI+Z1wGGWCxKBJ1dBFHeyXhPwBw==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:33.110627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22981","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:b117fafb85590dbe5e76b26e44029afa8b31ec44fbf2c9fe93287e1b8891d762","sha256:b8fa96a8dbd434b86781013e7c4c3771ba99bbe71e45d4d32784055c1ebdbafc","sha256:ebeecb0c28f1dcf7e8f3471cd7577be4734900177bcc9f43304ec5220944b00c"]}],"invalid_events":[],"applied_event_ids":["sha256:457333eb464d55ea39614ae637d13c60dcc8063ff97c13d0673c049aab300246","sha256:bdbf5071d32a612418b0410a0cee13b6427d685e1ac6615520b6d5c0bbdbf266"],"state_sha256":"e9a9f16e61343a6cc164a5eea3e82421c29317d83e3e52fd2b4ddd0c8e3fdcc5"}