{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GX4SGXFKM25LQS7ZIFIUYBXMQ4","short_pith_number":"pith:GX4SGXFK","canonical_record":{"source":{"id":"2505.16612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T12:47:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"90812593ebde9d501b7dafa7a4ad3e0e2a237fc6e3ef2134b0d898f591553590","abstract_canon_sha256":"f8b5858cdd69410ee44775bc78fd1e82eedbaba45955b1cb2b34d7b8ec33cc84"},"schema_version":"1.0"},"canonical_sha256":"35f9235caa66bab84bf941514c06ec8716254da3a4e5bbc8126052827700d26c","source":{"kind":"arxiv","id":"2505.16612","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16612","created_at":"2026-07-02T01:18:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16612v2","created_at":"2026-07-02T01:18:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16612","created_at":"2026-07-02T01:18:02Z"},{"alias_kind":"pith_short_12","alias_value":"GX4SGXFKM25L","created_at":"2026-07-02T01:18:02Z"},{"alias_kind":"pith_short_16","alias_value":"GX4SGXFKM25LQS7Z","created_at":"2026-07-02T01:18:02Z"},{"alias_kind":"pith_short_8","alias_value":"GX4SGXFK","created_at":"2026-07-02T01:18:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GX4SGXFKM25LQS7ZIFIUYBXMQ4","target":"record","payload":{"canonical_record":{"source":{"id":"2505.16612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T12:47:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"90812593ebde9d501b7dafa7a4ad3e0e2a237fc6e3ef2134b0d898f591553590","abstract_canon_sha256":"f8b5858cdd69410ee44775bc78fd1e82eedbaba45955b1cb2b34d7b8ec33cc84"},"schema_version":"1.0"},"canonical_sha256":"35f9235caa66bab84bf941514c06ec8716254da3a4e5bbc8126052827700d26c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:02.864674Z","signature_b64":"3O/2ZhagOgQ2weEsdmr4L4JfRFyROm8F4qd5CI1DecTgz2LGdZKldLKcSQia6NosSb0XS+DTGpyo8biIFfGEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35f9235caa66bab84bf941514c06ec8716254da3a4e5bbc8126052827700d26c","last_reissued_at":"2026-07-02T01:18:02.864110Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:02.864110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.16612","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":"2026-07-02T01:18:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZMPg1h8Deb45SsWSJl1Zqv4JMajzWqv+oHDv2HrpwyabhrKCt3znnDB1kxLg+04J6u4dbYS9ek676Kg2nwRjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T20:59:42.133235Z"},"content_sha256":"d7091f858f7c6cb2d27a20681763f29a6df18d5d78277fbd6a59b3000a7e1b56","schema_version":"1.0","event_id":"sha256:d7091f858f7c6cb2d27a20681763f29a6df18d5d78277fbd6a59b3000a7e1b56"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GX4SGXFKM25LQS7ZIFIUYBXMQ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Steering Large Language Models for Machine Translation Personalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Arianna Bisazza, Daniel Scalena, Elisabetta Fersini, Gabriele Sarti, Malvina Nissim","submitted_at":"2025-05-22T12:47:16Z","abstract_excerpt":"Large language models have simplified the production of personalized translations reflecting predefined stylistic constraints. However, these systems still struggle when stylistic requirements are implicitly represented by a set of examples, such as texts produced by a specific human translator. In this work, we explore various strategies for personalizing automatically generated translations when few examples are available, with a focus on the challenging domain of literary translation. We begin by determining the feasibility of the task and how style information is encoded within model repre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16612","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/2505.16612/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":"2026-07-02T01:18:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5z/wnrf3Uk/CmxJcsHkA8g+BCbJU5d4J7c7XKtHOjAZVXiEW7PrWHibwEu9RPAqRZiPgMomA6YHccZvrsZewCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T20:59:42.133703Z"},"content_sha256":"f81d29d6ee8628ced9b0ee3ebc0ab62222289ffa007cdb795eab460b2444072f","schema_version":"1.0","event_id":"sha256:f81d29d6ee8628ced9b0ee3ebc0ab62222289ffa007cdb795eab460b2444072f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GX4SGXFKM25LQS7ZIFIUYBXMQ4/bundle.json","state_url":"https://pith.science/pith/GX4SGXFKM25LQS7ZIFIUYBXMQ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GX4SGXFKM25LQS7ZIFIUYBXMQ4/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":"2026-07-04T20:59:42Z","links":{"resolver":"https://pith.science/pith/GX4SGXFKM25LQS7ZIFIUYBXMQ4","bundle":"https://pith.science/pith/GX4SGXFKM25LQS7ZIFIUYBXMQ4/bundle.json","state":"https://pith.science/pith/GX4SGXFKM25LQS7ZIFIUYBXMQ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GX4SGXFKM25LQS7ZIFIUYBXMQ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GX4SGXFKM25LQS7ZIFIUYBXMQ4","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":"f8b5858cdd69410ee44775bc78fd1e82eedbaba45955b1cb2b34d7b8ec33cc84","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T12:47:16Z","title_canon_sha256":"90812593ebde9d501b7dafa7a4ad3e0e2a237fc6e3ef2134b0d898f591553590"},"schema_version":"1.0","source":{"id":"2505.16612","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16612","created_at":"2026-07-02T01:18:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16612v2","created_at":"2026-07-02T01:18:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16612","created_at":"2026-07-02T01:18:02Z"},{"alias_kind":"pith_short_12","alias_value":"GX4SGXFKM25L","created_at":"2026-07-02T01:18:02Z"},{"alias_kind":"pith_short_16","alias_value":"GX4SGXFKM25LQS7Z","created_at":"2026-07-02T01:18:02Z"},{"alias_kind":"pith_short_8","alias_value":"GX4SGXFK","created_at":"2026-07-02T01:18:02Z"}],"graph_snapshots":[{"event_id":"sha256:f81d29d6ee8628ced9b0ee3ebc0ab62222289ffa007cdb795eab460b2444072f","target":"graph","created_at":"2026-07-02T01:18:02Z","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/2505.16612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have simplified the production of personalized translations reflecting predefined stylistic constraints. However, these systems still struggle when stylistic requirements are implicitly represented by a set of examples, such as texts produced by a specific human translator. In this work, we explore various strategies for personalizing automatically generated translations when few examples are available, with a focus on the challenging domain of literary translation. We begin by determining the feasibility of the task and how style information is encoded within model repre","authors_text":"Arianna Bisazza, Daniel Scalena, Elisabetta Fersini, Gabriele Sarti, Malvina Nissim","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T12:47:16Z","title":"Steering Large Language Models for Machine Translation Personalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16612","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:d7091f858f7c6cb2d27a20681763f29a6df18d5d78277fbd6a59b3000a7e1b56","target":"record","created_at":"2026-07-02T01:18:02Z","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":"f8b5858cdd69410ee44775bc78fd1e82eedbaba45955b1cb2b34d7b8ec33cc84","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T12:47:16Z","title_canon_sha256":"90812593ebde9d501b7dafa7a4ad3e0e2a237fc6e3ef2134b0d898f591553590"},"schema_version":"1.0","source":{"id":"2505.16612","kind":"arxiv","version":2}},"canonical_sha256":"35f9235caa66bab84bf941514c06ec8716254da3a4e5bbc8126052827700d26c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35f9235caa66bab84bf941514c06ec8716254da3a4e5bbc8126052827700d26c","first_computed_at":"2026-07-02T01:18:02.864110Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:18:02.864110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3O/2ZhagOgQ2weEsdmr4L4JfRFyROm8F4qd5CI1DecTgz2LGdZKldLKcSQia6NosSb0XS+DTGpyo8biIFfGEDw==","signature_status":"signed_v1","signed_at":"2026-07-02T01:18:02.864674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16612","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7091f858f7c6cb2d27a20681763f29a6df18d5d78277fbd6a59b3000a7e1b56","sha256:f81d29d6ee8628ced9b0ee3ebc0ab62222289ffa007cdb795eab460b2444072f"],"state_sha256":"831902d3e9030ab7c5912e0ef276b31362f62999ddd6225d54c632916f7ddfc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kRWm/IyA7LZvb0vURK+WmrPOywFa0alH+lvYnuaU06XGkF/0jrkzBLzH23DmS7/qkA4AOLSZwef3INN/wnp7Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T20:59:42.136284Z","bundle_sha256":"8cfd2f722ca466a2688894367e323fcf5dcb080dde339ba15ad245cb09e96404"}}