{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4BJYMROODYYCYMUFVQYE2OWJMC","short_pith_number":"pith:4BJYMROO","canonical_record":{"source":{"id":"2605.24173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T19:46:08Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"title_canon_sha256":"00e04ca86a49d879c156cb80eaf24510ad38e23ee3dff724a032d83ef491fe03","abstract_canon_sha256":"8282bd2ab5541920b28caeeceb3b87ad26edba91dea0ca6ea63f31e5f55156d3"},"schema_version":"1.0"},"canonical_sha256":"e0538645ce1e302c3285ac304d3ac960a2764f6414d3560273f3f3946da90869","source":{"kind":"arxiv","id":"2605.24173","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24173","created_at":"2026-05-26T01:02:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24173v1","created_at":"2026-05-26T01:02:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24173","created_at":"2026-05-26T01:02:50Z"},{"alias_kind":"pith_short_12","alias_value":"4BJYMROODYYC","created_at":"2026-05-26T01:02:50Z"},{"alias_kind":"pith_short_16","alias_value":"4BJYMROODYYCYMUF","created_at":"2026-05-26T01:02:50Z"},{"alias_kind":"pith_short_8","alias_value":"4BJYMROO","created_at":"2026-05-26T01:02:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4BJYMROODYYCYMUFVQYE2OWJMC","target":"record","payload":{"canonical_record":{"source":{"id":"2605.24173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T19:46:08Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"title_canon_sha256":"00e04ca86a49d879c156cb80eaf24510ad38e23ee3dff724a032d83ef491fe03","abstract_canon_sha256":"8282bd2ab5541920b28caeeceb3b87ad26edba91dea0ca6ea63f31e5f55156d3"},"schema_version":"1.0"},"canonical_sha256":"e0538645ce1e302c3285ac304d3ac960a2764f6414d3560273f3f3946da90869","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:50.569683Z","signature_b64":"l9pfQvQsjcs0SYMIBJS44Hlej/AFwrK/4zAdZ+eT3q2fiZoGVR1oXYH3znaY91efuBWlKjnSSO5w6cxcJN4uAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0538645ce1e302c3285ac304d3ac960a2764f6414d3560273f3f3946da90869","last_reissued_at":"2026-05-26T01:02:50.568819Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:50.568819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.24173","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":"2026-05-26T01:02:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Rh9GNgEWA1GHYslGGJxLheVaqOsctfUYvB51VTAQz/7B44RUjOiRda4P7VZZ7d9/fJwNM2moHCGmAr3uJpwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:50:38.956034Z"},"content_sha256":"d046419ce4c6381a7e117dd026e5270de7dc00ae3d124f3756c3400a0f2f8451","schema_version":"1.0","event_id":"sha256:d046419ce4c6381a7e117dd026e5270de7dc00ae3d124f3756c3400a0f2f8451"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4BJYMROODYYCYMUFVQYE2OWJMC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extracting Training Data from Diffusion Language Models via Infilling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"N. Asokan, Yihan Wang","submitted_at":"2026-05-22T19:46:08Z","abstract_excerpt":"Memorization in large language models has been studied almost exclusively through prefix-conditioned extraction, a natural choice for autoregressive models. However, diffusion language models (DLMs) can denoise masked tokens at arbitrary positions. Thus, prefix-only probing reveals only one facet of memorization in DLMs and significantly underestimates the risk of training-data extraction. In order to realistically model extractability of training data in DLMs, we introduce \\emph{infilling extraction}, a data-extraction protocol parameterized by an arbitrary binary mask that subsumes prefix-on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24173","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/2605.24173/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":"2026-05-26T01:02:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fJotSsbq2c5vndYLDZX0jkR3IqIKKIecMoGRr0PMZ/h+QgMDPyKzlXWq2qfiEC3XyXdRmOBFvk5vXsdJWBMHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:50:38.956857Z"},"content_sha256":"337a6197a03a44156a4cf6f5e006c3c39d64f18620fab50c39560cdbfd85c512","schema_version":"1.0","event_id":"sha256:337a6197a03a44156a4cf6f5e006c3c39d64f18620fab50c39560cdbfd85c512"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4BJYMROODYYCYMUFVQYE2OWJMC/bundle.json","state_url":"https://pith.science/pith/4BJYMROODYYCYMUFVQYE2OWJMC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4BJYMROODYYCYMUFVQYE2OWJMC/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":"2026-06-04T20:50:38Z","links":{"resolver":"https://pith.science/pith/4BJYMROODYYCYMUFVQYE2OWJMC","bundle":"https://pith.science/pith/4BJYMROODYYCYMUFVQYE2OWJMC/bundle.json","state":"https://pith.science/pith/4BJYMROODYYCYMUFVQYE2OWJMC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4BJYMROODYYCYMUFVQYE2OWJMC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4BJYMROODYYCYMUFVQYE2OWJMC","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":"8282bd2ab5541920b28caeeceb3b87ad26edba91dea0ca6ea63f31e5f55156d3","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T19:46:08Z","title_canon_sha256":"00e04ca86a49d879c156cb80eaf24510ad38e23ee3dff724a032d83ef491fe03"},"schema_version":"1.0","source":{"id":"2605.24173","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24173","created_at":"2026-05-26T01:02:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24173v1","created_at":"2026-05-26T01:02:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24173","created_at":"2026-05-26T01:02:50Z"},{"alias_kind":"pith_short_12","alias_value":"4BJYMROODYYC","created_at":"2026-05-26T01:02:50Z"},{"alias_kind":"pith_short_16","alias_value":"4BJYMROODYYCYMUF","created_at":"2026-05-26T01:02:50Z"},{"alias_kind":"pith_short_8","alias_value":"4BJYMROO","created_at":"2026-05-26T01:02:50Z"}],"graph_snapshots":[{"event_id":"sha256:337a6197a03a44156a4cf6f5e006c3c39d64f18620fab50c39560cdbfd85c512","target":"graph","created_at":"2026-05-26T01:02:50Z","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/2605.24173/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Memorization in large language models has been studied almost exclusively through prefix-conditioned extraction, a natural choice for autoregressive models. However, diffusion language models (DLMs) can denoise masked tokens at arbitrary positions. Thus, prefix-only probing reveals only one facet of memorization in DLMs and significantly underestimates the risk of training-data extraction. In order to realistically model extractability of training data in DLMs, we introduce \\emph{infilling extraction}, a data-extraction protocol parameterized by an arbitrary binary mask that subsumes prefix-on","authors_text":"N. Asokan, Yihan Wang","cross_cats":["cs.AI","cs.CR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T19:46:08Z","title":"Extracting Training Data from Diffusion Language Models via Infilling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24173","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:d046419ce4c6381a7e117dd026e5270de7dc00ae3d124f3756c3400a0f2f8451","target":"record","created_at":"2026-05-26T01:02:50Z","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":"8282bd2ab5541920b28caeeceb3b87ad26edba91dea0ca6ea63f31e5f55156d3","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T19:46:08Z","title_canon_sha256":"00e04ca86a49d879c156cb80eaf24510ad38e23ee3dff724a032d83ef491fe03"},"schema_version":"1.0","source":{"id":"2605.24173","kind":"arxiv","version":1}},"canonical_sha256":"e0538645ce1e302c3285ac304d3ac960a2764f6414d3560273f3f3946da90869","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0538645ce1e302c3285ac304d3ac960a2764f6414d3560273f3f3946da90869","first_computed_at":"2026-05-26T01:02:50.568819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:02:50.568819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l9pfQvQsjcs0SYMIBJS44Hlej/AFwrK/4zAdZ+eT3q2fiZoGVR1oXYH3znaY91efuBWlKjnSSO5w6cxcJN4uAA==","signature_status":"signed_v1","signed_at":"2026-05-26T01:02:50.569683Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24173","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d046419ce4c6381a7e117dd026e5270de7dc00ae3d124f3756c3400a0f2f8451","sha256:337a6197a03a44156a4cf6f5e006c3c39d64f18620fab50c39560cdbfd85c512"],"state_sha256":"ae498f8b7465f05d30c5c2d71d32b0b517d1cb881bfa95e2819c9605308d4204"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sQOsLcJ7X7argrjW+T3x2l5ZBjvWe0Dz5NufJraf4/QBfumEkJxfPOROFCkS5cnkuJUKbq+HCbxQjV0FQIqGBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T20:50:38.961330Z","bundle_sha256":"74296985e25c638a2647ee3b937d0e369b651221253436b13d68326432d7e557"}}