{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QZFDARWGC3XDMV2DHD2WCQWMGW","short_pith_number":"pith:QZFDARWG","canonical_record":{"source":{"id":"2607.19181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T15:15:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6de99233d11db0b1cfa4a1b3c4ba5f52944bb8404859726dd46279aaa3fa0c55","abstract_canon_sha256":"287da0cbf757d215dbf89687816f1c2812812544d7336099723017d5f4724c67"},"schema_version":"1.0"},"canonical_sha256":"864a3046c616ee36574338f56142cc3599c0d023efd700276250174261526c3d","source":{"kind":"arxiv","id":"2607.19181","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19181","created_at":"2026-07-22T01:24:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19181v1","created_at":"2026-07-22T01:24:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19181","created_at":"2026-07-22T01:24:12Z"},{"alias_kind":"pith_short_12","alias_value":"QZFDARWGC3XD","created_at":"2026-07-22T01:24:12Z"},{"alias_kind":"pith_short_16","alias_value":"QZFDARWGC3XDMV2D","created_at":"2026-07-22T01:24:12Z"},{"alias_kind":"pith_short_8","alias_value":"QZFDARWG","created_at":"2026-07-22T01:24:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QZFDARWGC3XDMV2DHD2WCQWMGW","target":"record","payload":{"canonical_record":{"source":{"id":"2607.19181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T15:15:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6de99233d11db0b1cfa4a1b3c4ba5f52944bb8404859726dd46279aaa3fa0c55","abstract_canon_sha256":"287da0cbf757d215dbf89687816f1c2812812544d7336099723017d5f4724c67"},"schema_version":"1.0"},"canonical_sha256":"864a3046c616ee36574338f56142cc3599c0d023efd700276250174261526c3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:24:12.638214Z","signature_b64":"hmBlZlAp9NgDmRSVnqc+8BreW9okj/EmqWy8v+MJbLKFaWhDUzxGBsG+pPSqhnQ/FK9X2Ua3unL8ENMGq0f5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"864a3046c616ee36574338f56142cc3599c0d023efd700276250174261526c3d","last_reissued_at":"2026-07-22T01:24:12.637364Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:24:12.637364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.19181","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":"2026-07-22T01:24:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"32N1QLGlssM0X9hRYRyoDoNxPSJVTEMN6ryi0DjsY6XQr7iyh+9PDK6AQbIBMohhqUGe/+xwG85HetEhJ1SfCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T14:02:40.123298Z"},"content_sha256":"033f345037af70d6ef2532c6fd63d4df489b7ad2532ae8ca8ce440f0e3193e37","schema_version":"1.0","event_id":"sha256:033f345037af70d6ef2532c6fd63d4df489b7ad2532ae8ca8ce440f0e3193e37"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QZFDARWGC3XDMV2DHD2WCQWMGW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aixiu An, Andreas Fischer, Eloi Eynard, Jean Hennebert, Mark Drenhaus, Michael Jungo, S\\'ebastien Rumley","submitted_at":"2026-07-21T15:15:56Z","abstract_excerpt":"Neural machine translation (NMT) in the legal domain is a linguistically and conceptually demanding task, primarily due to the complexity of legal language and the high level of precision it requires. The recent emergence of reasoning-capable language models opens new possibilities for tackling such challenges. They add to a set of other previously proposed techniques to enhance the translation quality, which includes supervised fine-tuning and reinforcement learning.\n  In this work, we perform a comparison between these various approaches. More particularly, we evaluate small language models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19181","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/2607.19181/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":"2026-07-22T01:24:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gpML8kUj4sXdNI7Gr7s1k0ISirYqsOcPvE16XnA7MrnvaRCplHISwlWeh3+dhEPbAWjySlbLjK4j4dZlOu/rDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T14:02:40.123814Z"},"content_sha256":"7c75ef7f6f8555764ba4ebb295ffc626be8cd1b6723b3eab0d1128ce29206337","schema_version":"1.0","event_id":"sha256:7c75ef7f6f8555764ba4ebb295ffc626be8cd1b6723b3eab0d1128ce29206337"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:QZFDARWGC3XDMV2DHD2WCQWMGW","target":"integrity","payload":{"note":"Identifier '10.18653/v1/2024' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"Association for Computational Linguistics. doi: 10.18653/v1/2024. eacl-srw.17. URL https://aclanthology.org/ 2024.eacl-srw.17/. Banerjee, S. and Lavie, A. Meteor: An automatic metric for mt evaluation with improved correlation with human ju","arxiv_id":"2607.19181","detector":"doi_compliance","evidence":{"doi":"10.18653/v1/2024","arxiv_id":null,"ref_index":2024,"raw_excerpt":"Association for Computational Linguistics. doi: 10.18653/v1/2024. eacl-srw.17. URL https://aclanthology.org/ 2024.eacl-srw.17/. Banerjee, S. and Lavie, A. Meteor: An automatic metric for mt evaluation with improved correlation with human judgments. InProceedings of the acl workshop on in- trinsic and extrinsic evaluation measures for machine translation and/or summarization, pp. 65–72,","parse_status":"well_formed","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"],"resolution_status":"hard_miss"},"severity":"critical","ref_index":2024,"audited_at":"2026-08-01T13:19:26.452120Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2024","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"c2a39f63e5dddf13873987d7ccffd7054bb529d35c41c0ac51e45b932af7bc1c","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":15859,"payload_sha256":"c58de8598d10fb18f91ba03f9eb3501e138bcc4a3ba718f79da7be08940b7c34","signature_b64":"BVYtGHLhAavCE4d7/IU5NM33G38EtBY6ZeVLgrLlF/RA+Y2LM/MzIRMVbFYNOpK0A+vn8Hy4MX3TC9Pe1KzuBA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T13:23:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S7TPdon8hY35reg2WkLgxtYyhRvc9Zzvk5x2EtpJs+68HvpXvUxqwwKaCeY6LHYmH7K1jpDTpuofZBOW00i6Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T14:02:40.126690Z"},"content_sha256":"df1fc0d35ff04516a80edf755ef474bfd1e3fde9f33cd5853b6121f466f6c423","schema_version":"1.0","event_id":"sha256:df1fc0d35ff04516a80edf755ef474bfd1e3fde9f33cd5853b6121f466f6c423"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QZFDARWGC3XDMV2DHD2WCQWMGW/bundle.json","state_url":"https://pith.science/pith/QZFDARWGC3XDMV2DHD2WCQWMGW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QZFDARWGC3XDMV2DHD2WCQWMGW/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":"2026-08-03T14:02:40Z","links":{"resolver":"https://pith.science/pith/QZFDARWGC3XDMV2DHD2WCQWMGW","bundle":"https://pith.science/pith/QZFDARWGC3XDMV2DHD2WCQWMGW/bundle.json","state":"https://pith.science/pith/QZFDARWGC3XDMV2DHD2WCQWMGW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QZFDARWGC3XDMV2DHD2WCQWMGW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QZFDARWGC3XDMV2DHD2WCQWMGW","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"287da0cbf757d215dbf89687816f1c2812812544d7336099723017d5f4724c67","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T15:15:56Z","title_canon_sha256":"6de99233d11db0b1cfa4a1b3c4ba5f52944bb8404859726dd46279aaa3fa0c55"},"schema_version":"1.0","source":{"id":"2607.19181","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19181","created_at":"2026-07-22T01:24:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19181v1","created_at":"2026-07-22T01:24:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19181","created_at":"2026-07-22T01:24:12Z"},{"alias_kind":"pith_short_12","alias_value":"QZFDARWGC3XD","created_at":"2026-07-22T01:24:12Z"},{"alias_kind":"pith_short_16","alias_value":"QZFDARWGC3XDMV2D","created_at":"2026-07-22T01:24:12Z"},{"alias_kind":"pith_short_8","alias_value":"QZFDARWG","created_at":"2026-07-22T01:24:12Z"}],"graph_snapshots":[{"event_id":"sha256:7c75ef7f6f8555764ba4ebb295ffc626be8cd1b6723b3eab0d1128ce29206337","target":"graph","created_at":"2026-07-22T01:24:12Z","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/2607.19181/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural machine translation (NMT) in the legal domain is a linguistically and conceptually demanding task, primarily due to the complexity of legal language and the high level of precision it requires. The recent emergence of reasoning-capable language models opens new possibilities for tackling such challenges. They add to a set of other previously proposed techniques to enhance the translation quality, which includes supervised fine-tuning and reinforcement learning.\n  In this work, we perform a comparison between these various approaches. More particularly, we evaluate small language models ","authors_text":"Aixiu An, Andreas Fischer, Eloi Eynard, Jean Hennebert, Mark Drenhaus, Michael Jungo, S\\'ebastien Rumley","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T15:15:56Z","title":"Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19181","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":"sha256:033f345037af70d6ef2532c6fd63d4df489b7ad2532ae8ca8ce440f0e3193e37","target":"record","created_at":"2026-07-22T01:24:12Z","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":"287da0cbf757d215dbf89687816f1c2812812544d7336099723017d5f4724c67","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T15:15:56Z","title_canon_sha256":"6de99233d11db0b1cfa4a1b3c4ba5f52944bb8404859726dd46279aaa3fa0c55"},"schema_version":"1.0","source":{"id":"2607.19181","kind":"arxiv","version":1}},"canonical_sha256":"864a3046c616ee36574338f56142cc3599c0d023efd700276250174261526c3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"864a3046c616ee36574338f56142cc3599c0d023efd700276250174261526c3d","first_computed_at":"2026-07-22T01:24:12.637364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:24:12.637364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hmBlZlAp9NgDmRSVnqc+8BreW9okj/EmqWy8v+MJbLKFaWhDUzxGBsG+pPSqhnQ/FK9X2Ua3unL8ENMGq0f5Dg==","signature_status":"signed_v1","signed_at":"2026-07-22T01:24:12.638214Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19181","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:033f345037af70d6ef2532c6fd63d4df489b7ad2532ae8ca8ce440f0e3193e37","sha256:7c75ef7f6f8555764ba4ebb295ffc626be8cd1b6723b3eab0d1128ce29206337","sha256:df1fc0d35ff04516a80edf755ef474bfd1e3fde9f33cd5853b6121f466f6c423"],"state_sha256":"5b7988af1e2298de1d8400245a134f3fd51110d46a486014bb4f66ad3899d352"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LjoSwiodIt6PfMghuwiKKRrR9QuQhYefhOwvb7QZbjtJTNAjfVD719p3EIY/IxbFkhZMeA57KE9O1sl69J/8Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T14:02:40.129136Z","bundle_sha256":"926092a493add72f820385525b802c6679c37884df088007306d023b0ce9e23e"}}