{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NWTBLL76FJMTVAK5ECY7JRGBGL","short_pith_number":"pith:NWTBLL76","canonical_record":{"source":{"id":"2309.08590","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-15T17:44:21Z","cross_cats_sorted":[],"title_canon_sha256":"1761a0f06a2dc90188cf7c100d769e00b2eefaed2bb2adc9353b9ea1735440c9","abstract_canon_sha256":"fa4d52b95d4365b2e8a8ba34e973b9f35d69baf0b81528e1bb20b2d19b3c3e19"},"schema_version":"1.0"},"canonical_sha256":"6da615affe2a593a815d20b1f4c4c132ee0c04fad12702cbae3443bdbdd10502","source":{"kind":"arxiv","id":"2309.08590","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08590","created_at":"2026-07-05T06:51:08Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08590v1","created_at":"2026-07-05T06:51:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08590","created_at":"2026-07-05T06:51:08Z"},{"alias_kind":"pith_short_12","alias_value":"NWTBLL76FJMT","created_at":"2026-07-05T06:51:08Z"},{"alias_kind":"pith_short_16","alias_value":"NWTBLL76FJMTVAK5","created_at":"2026-07-05T06:51:08Z"},{"alias_kind":"pith_short_8","alias_value":"NWTBLL76","created_at":"2026-07-05T06:51:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NWTBLL76FJMTVAK5ECY7JRGBGL","target":"record","payload":{"canonical_record":{"source":{"id":"2309.08590","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-15T17:44:21Z","cross_cats_sorted":[],"title_canon_sha256":"1761a0f06a2dc90188cf7c100d769e00b2eefaed2bb2adc9353b9ea1735440c9","abstract_canon_sha256":"fa4d52b95d4365b2e8a8ba34e973b9f35d69baf0b81528e1bb20b2d19b3c3e19"},"schema_version":"1.0"},"canonical_sha256":"6da615affe2a593a815d20b1f4c4c132ee0c04fad12702cbae3443bdbdd10502","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:08.264668Z","signature_b64":"xWNMVf86Qsn8jjctRuEn9lGwpxrxGwLS+fra5b7ExtQCqsRTsl2DhD74I9Ts5qFOyWXL6hat1Pge4Iwe9h/SDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6da615affe2a593a815d20b1f4c4c132ee0c04fad12702cbae3443bdbdd10502","last_reissued_at":"2026-07-05T06:51:08.264219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:08.264219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.08590","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":"2026-07-05T06:51:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YtvgY61mtX/HKppmkzIFth7BPikv9H/lQHO90P3DGEFvv0mLiuwzdtuRq02wyxQM/QeQJrkkO6tZHEE53+LZBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T02:26:49.126326Z"},"content_sha256":"6bee6e23fd1df7141ac6f915c4c94dd397837af44d972c06689039d03dc94705","schema_version":"1.0","event_id":"sha256:6bee6e23fd1df7141ac6f915c4c94dd397837af44d972c06689039d03dc94705"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NWTBLL76FJMTVAK5ECY7JRGBGL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Machine Translation Models Can Learn to be Few-shot Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Joern Wuebker, Johannes E. M. Mosig, Kaden Uhlig, Patrick Simianer, Raphael Reinauer","submitted_at":"2023-09-15T17:44:21Z","abstract_excerpt":"The emergent ability of Large Language Models to use a small number of examples to learn to perform in novel domains and tasks, also called in-context learning (ICL). In this work, we show that a much smaller model can be trained to perform ICL by fine-tuning towards a specialized training objective, exemplified on the task of domain adaptation for neural machine translation. With this capacity for ICL, the model can take advantage of relevant few-shot examples to adapt its output towards the domain. We compare the quality of this domain adaptation to traditional supervised techniques and ICL "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08590","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/2309.08590/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":"2026-07-05T06:51:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jSHa72REpvlPCoIBRgaV/QMc3p1y+NojmpYxbMW9dR+QTZTJIHcXUrKYERh4UEq5s2XcV8bno0Jptlqoib1JDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T02:26:49.126865Z"},"content_sha256":"b370ddf7b480b83757167a178b7906efc89dc4f8b338de3a082a211cbad64a92","schema_version":"1.0","event_id":"sha256:b370ddf7b480b83757167a178b7906efc89dc4f8b338de3a082a211cbad64a92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NWTBLL76FJMTVAK5ECY7JRGBGL/bundle.json","state_url":"https://pith.science/pith/NWTBLL76FJMTVAK5ECY7JRGBGL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NWTBLL76FJMTVAK5ECY7JRGBGL/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":"2026-08-13T02:26:49Z","links":{"resolver":"https://pith.science/pith/NWTBLL76FJMTVAK5ECY7JRGBGL","bundle":"https://pith.science/pith/NWTBLL76FJMTVAK5ECY7JRGBGL/bundle.json","state":"https://pith.science/pith/NWTBLL76FJMTVAK5ECY7JRGBGL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NWTBLL76FJMTVAK5ECY7JRGBGL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NWTBLL76FJMTVAK5ECY7JRGBGL","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":"fa4d52b95d4365b2e8a8ba34e973b9f35d69baf0b81528e1bb20b2d19b3c3e19","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-15T17:44:21Z","title_canon_sha256":"1761a0f06a2dc90188cf7c100d769e00b2eefaed2bb2adc9353b9ea1735440c9"},"schema_version":"1.0","source":{"id":"2309.08590","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08590","created_at":"2026-07-05T06:51:08Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08590v1","created_at":"2026-07-05T06:51:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08590","created_at":"2026-07-05T06:51:08Z"},{"alias_kind":"pith_short_12","alias_value":"NWTBLL76FJMT","created_at":"2026-07-05T06:51:08Z"},{"alias_kind":"pith_short_16","alias_value":"NWTBLL76FJMTVAK5","created_at":"2026-07-05T06:51:08Z"},{"alias_kind":"pith_short_8","alias_value":"NWTBLL76","created_at":"2026-07-05T06:51:08Z"}],"graph_snapshots":[{"event_id":"sha256:b370ddf7b480b83757167a178b7906efc89dc4f8b338de3a082a211cbad64a92","target":"graph","created_at":"2026-07-05T06:51:08Z","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/2309.08590/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergent ability of Large Language Models to use a small number of examples to learn to perform in novel domains and tasks, also called in-context learning (ICL). In this work, we show that a much smaller model can be trained to perform ICL by fine-tuning towards a specialized training objective, exemplified on the task of domain adaptation for neural machine translation. With this capacity for ICL, the model can take advantage of relevant few-shot examples to adapt its output towards the domain. We compare the quality of this domain adaptation to traditional supervised techniques and ICL ","authors_text":"Joern Wuebker, Johannes E. M. Mosig, Kaden Uhlig, Patrick Simianer, Raphael Reinauer","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-15T17:44:21Z","title":"Neural Machine Translation Models Can Learn to be Few-shot Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08590","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":"sha256:6bee6e23fd1df7141ac6f915c4c94dd397837af44d972c06689039d03dc94705","target":"record","created_at":"2026-07-05T06:51:08Z","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":"fa4d52b95d4365b2e8a8ba34e973b9f35d69baf0b81528e1bb20b2d19b3c3e19","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-15T17:44:21Z","title_canon_sha256":"1761a0f06a2dc90188cf7c100d769e00b2eefaed2bb2adc9353b9ea1735440c9"},"schema_version":"1.0","source":{"id":"2309.08590","kind":"arxiv","version":1}},"canonical_sha256":"6da615affe2a593a815d20b1f4c4c132ee0c04fad12702cbae3443bdbdd10502","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6da615affe2a593a815d20b1f4c4c132ee0c04fad12702cbae3443bdbdd10502","first_computed_at":"2026-07-05T06:51:08.264219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:08.264219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xWNMVf86Qsn8jjctRuEn9lGwpxrxGwLS+fra5b7ExtQCqsRTsl2DhD74I9Ts5qFOyWXL6hat1Pge4Iwe9h/SDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:08.264668Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08590","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bee6e23fd1df7141ac6f915c4c94dd397837af44d972c06689039d03dc94705","sha256:b370ddf7b480b83757167a178b7906efc89dc4f8b338de3a082a211cbad64a92"],"state_sha256":"7e7d5eb20273cb6421c749a0c46e2835f2ae025f9ebc482dd9c0a685a6e2fd58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t1HUgqoLUcF+hwRkfAHlr3Zli4yjtWQdkGlC6N+djDjYTzbAiqwwVrk5804RY/wv4ukQ3OVj27/I0jSI3LPkAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T02:26:49.131849Z","bundle_sha256":"6ef71ecfd39d2b6d69131fbdce81302e9c28b2ffbac7b84c2d99f8572771a5ed"}}