{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GFKEWOQ6QMPCKUEPVHR5Y753AU","short_pith_number":"pith:GFKEWOQ6","canonical_record":{"source":{"id":"2502.01491","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T16:26:06Z","cross_cats_sorted":[],"title_canon_sha256":"cb8a243d73b099413da36d9897d7c0bde2b35d04220df7f15fd26752a711dcc6","abstract_canon_sha256":"fba687a791c4344606ee7e163fe6203d802af98f7a39c5cdd72be7545775e9ab"},"schema_version":"1.0"},"canonical_sha256":"31544b3a1e831e25508fa9e3dc7fbb0535e068dc2ac9c6e87680d7930e79d8e8","source":{"kind":"arxiv","id":"2502.01491","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01491","created_at":"2026-07-05T11:38:26Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01491v2","created_at":"2026-07-05T11:38:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01491","created_at":"2026-07-05T11:38:26Z"},{"alias_kind":"pith_short_12","alias_value":"GFKEWOQ6QMPC","created_at":"2026-07-05T11:38:26Z"},{"alias_kind":"pith_short_16","alias_value":"GFKEWOQ6QMPCKUEP","created_at":"2026-07-05T11:38:26Z"},{"alias_kind":"pith_short_8","alias_value":"GFKEWOQ6","created_at":"2026-07-05T11:38:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GFKEWOQ6QMPCKUEPVHR5Y753AU","target":"record","payload":{"canonical_record":{"source":{"id":"2502.01491","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T16:26:06Z","cross_cats_sorted":[],"title_canon_sha256":"cb8a243d73b099413da36d9897d7c0bde2b35d04220df7f15fd26752a711dcc6","abstract_canon_sha256":"fba687a791c4344606ee7e163fe6203d802af98f7a39c5cdd72be7545775e9ab"},"schema_version":"1.0"},"canonical_sha256":"31544b3a1e831e25508fa9e3dc7fbb0535e068dc2ac9c6e87680d7930e79d8e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:26.697196Z","signature_b64":"anj1qVuMp/v1LLXnrkkpa+U7wJOwzH27WlK5myTHJNcBwfU/iU0ZhHQpBmZKRAMiMQv2ry8+Q+cO/5DxSKqPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31544b3a1e831e25508fa9e3dc7fbb0535e068dc2ac9c6e87680d7930e79d8e8","last_reissued_at":"2026-07-05T11:38:26.696638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:26.696638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.01491","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":"2026-07-05T11:38:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qV0784wlCQI02vvqhfoK2iUo2YsoUBoPOqV6HKrh5eHj8CebGzMN8RFNJcmQvvKhQPr+GSB8u1q/Ljd9iPxqAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:31:35.286191Z"},"content_sha256":"30ba949fd772bd68ec5ebf1b0ffc5419f641b9b5563c9a6ab7ee3e431e5b7abf","schema_version":"1.0","event_id":"sha256:30ba949fd772bd68ec5ebf1b0ffc5419f641b9b5563c9a6ab7ee3e431e5b7abf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GFKEWOQ6QMPCKUEPVHR5Y753AU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Memorization Inheritance in Sequence-Level Knowledge Distillation for Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Verna Dankers, Vikas Raunak","submitted_at":"2025-02-03T16:26:06Z","abstract_excerpt":"In this work, we explore how instance-level memorization in the teacher Neural Machine Translation (NMT) model gets inherited by the student model in sequence-level knowledge distillation (SeqKD). We find that despite not directly seeing the original training data, students memorize more than baseline models (models of the same size, trained on the original data) -- 3.4% for exact matches and 57% for extractive memorization -- and show increased hallucination rates. Further, under this SeqKD setting, we also characterize how students behave on specific training data subgroups, such as subgroup"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01491","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/2502.01491/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":"2026-07-05T11:38:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KEfuwUoTh6vpUFwAfr1JfeJNxbYiWFOdklcKrCr9opZQsUOzhH/6StgP7LoQkoA9jH8yWw1liQzNJ4cVt51LAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:31:35.287065Z"},"content_sha256":"e9f013607829dd8300b734d9e24e926739fe654db29809868ca4a011ca4ef7ee","schema_version":"1.0","event_id":"sha256:e9f013607829dd8300b734d9e24e926739fe654db29809868ca4a011ca4ef7ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GFKEWOQ6QMPCKUEPVHR5Y753AU/bundle.json","state_url":"https://pith.science/pith/GFKEWOQ6QMPCKUEPVHR5Y753AU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GFKEWOQ6QMPCKUEPVHR5Y753AU/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":"2026-08-10T08:31:35Z","links":{"resolver":"https://pith.science/pith/GFKEWOQ6QMPCKUEPVHR5Y753AU","bundle":"https://pith.science/pith/GFKEWOQ6QMPCKUEPVHR5Y753AU/bundle.json","state":"https://pith.science/pith/GFKEWOQ6QMPCKUEPVHR5Y753AU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GFKEWOQ6QMPCKUEPVHR5Y753AU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GFKEWOQ6QMPCKUEPVHR5Y753AU","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":"fba687a791c4344606ee7e163fe6203d802af98f7a39c5cdd72be7545775e9ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T16:26:06Z","title_canon_sha256":"cb8a243d73b099413da36d9897d7c0bde2b35d04220df7f15fd26752a711dcc6"},"schema_version":"1.0","source":{"id":"2502.01491","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01491","created_at":"2026-07-05T11:38:26Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01491v2","created_at":"2026-07-05T11:38:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01491","created_at":"2026-07-05T11:38:26Z"},{"alias_kind":"pith_short_12","alias_value":"GFKEWOQ6QMPC","created_at":"2026-07-05T11:38:26Z"},{"alias_kind":"pith_short_16","alias_value":"GFKEWOQ6QMPCKUEP","created_at":"2026-07-05T11:38:26Z"},{"alias_kind":"pith_short_8","alias_value":"GFKEWOQ6","created_at":"2026-07-05T11:38:26Z"}],"graph_snapshots":[{"event_id":"sha256:e9f013607829dd8300b734d9e24e926739fe654db29809868ca4a011ca4ef7ee","target":"graph","created_at":"2026-07-05T11:38:26Z","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/2502.01491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we explore how instance-level memorization in the teacher Neural Machine Translation (NMT) model gets inherited by the student model in sequence-level knowledge distillation (SeqKD). We find that despite not directly seeing the original training data, students memorize more than baseline models (models of the same size, trained on the original data) -- 3.4% for exact matches and 57% for extractive memorization -- and show increased hallucination rates. Further, under this SeqKD setting, we also characterize how students behave on specific training data subgroups, such as subgroup","authors_text":"Verna Dankers, Vikas Raunak","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T16:26:06Z","title":"Memorization Inheritance in Sequence-Level Knowledge Distillation for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01491","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":"sha256:30ba949fd772bd68ec5ebf1b0ffc5419f641b9b5563c9a6ab7ee3e431e5b7abf","target":"record","created_at":"2026-07-05T11:38:26Z","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":"fba687a791c4344606ee7e163fe6203d802af98f7a39c5cdd72be7545775e9ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T16:26:06Z","title_canon_sha256":"cb8a243d73b099413da36d9897d7c0bde2b35d04220df7f15fd26752a711dcc6"},"schema_version":"1.0","source":{"id":"2502.01491","kind":"arxiv","version":2}},"canonical_sha256":"31544b3a1e831e25508fa9e3dc7fbb0535e068dc2ac9c6e87680d7930e79d8e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31544b3a1e831e25508fa9e3dc7fbb0535e068dc2ac9c6e87680d7930e79d8e8","first_computed_at":"2026-07-05T11:38:26.696638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:26.696638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"anj1qVuMp/v1LLXnrkkpa+U7wJOwzH27WlK5myTHJNcBwfU/iU0ZhHQpBmZKRAMiMQv2ry8+Q+cO/5DxSKqPCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:26.697196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01491","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30ba949fd772bd68ec5ebf1b0ffc5419f641b9b5563c9a6ab7ee3e431e5b7abf","sha256:e9f013607829dd8300b734d9e24e926739fe654db29809868ca4a011ca4ef7ee"],"state_sha256":"f75fe76bebbbcf497f73173527b0aede81bee020c96f28eb112154a3c0fa6062"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XtQMxBY0ZpZUsN/jK/yogp5fFpRYRc994N3U/h9UWasHHY1JPhVzPT/J2M8qCY7RWiexC67SquScPOQED9TCAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:31:35.291874Z","bundle_sha256":"2db69bf802824530b31b5e0fe07df5f563f98d3fee9849359e59e84b34a83197"}}