{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:32TGYPCVOYYYSX5XPOPHPYKN6J","short_pith_number":"pith:32TGYPCV","canonical_record":{"source":{"id":"2108.01139","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-02T19:46:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"70118b7b6f2ca4de6ceddde03b4d3bed94bd2bdc863acf44d36888ee55e87318","abstract_canon_sha256":"d1c383c0ba9253fe708d330aac459b95cf84aa791f08b246b4fb90ce6e2c35cb"},"schema_version":"1.0"},"canonical_sha256":"dea66c3c557631895fb77b9e77e14df2640c4193a88618105fa446b6bb0c4aa6","source":{"kind":"arxiv","id":"2108.01139","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.01139","created_at":"2026-07-05T03:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"2108.01139v3","created_at":"2026-07-05T03:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01139","created_at":"2026-07-05T03:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"32TGYPCVOYYY","created_at":"2026-07-05T03:04:28Z"},{"alias_kind":"pith_short_16","alias_value":"32TGYPCVOYYYSX5X","created_at":"2026-07-05T03:04:28Z"},{"alias_kind":"pith_short_8","alias_value":"32TGYPCV","created_at":"2026-07-05T03:04:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:32TGYPCVOYYYSX5XPOPHPYKN6J","target":"record","payload":{"canonical_record":{"source":{"id":"2108.01139","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-02T19:46:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"70118b7b6f2ca4de6ceddde03b4d3bed94bd2bdc863acf44d36888ee55e87318","abstract_canon_sha256":"d1c383c0ba9253fe708d330aac459b95cf84aa791f08b246b4fb90ce6e2c35cb"},"schema_version":"1.0"},"canonical_sha256":"dea66c3c557631895fb77b9e77e14df2640c4193a88618105fa446b6bb0c4aa6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:28.036069Z","signature_b64":"WnW8acKOmi14fKpqJVcl0dcuh+3QsvwI8zIzfkt0tPY/C9HXwNul939xXVF4x88eSQUB3nUAqqLY9OaC0jBWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dea66c3c557631895fb77b9e77e14df2640c4193a88618105fa446b6bb0c4aa6","last_reissued_at":"2026-07-05T03:04:28.035593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:28.035593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.01139","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:04:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ryRxwHRfHAkAdsR3vTx4LrhV91XydForgR/fdo+/Ve0q6d+aH9XgY2jU3nbpH9KN37Vlxvxym3jOIliQ/YAzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:42:25.945438Z"},"content_sha256":"2607b76f4d9232011762b8438da9e98bfb3e35ac1908464954ce24609e1205f8","schema_version":"1.0","event_id":"sha256:2607b76f4d9232011762b8438da9e98bfb3e35ac1908464954ce24609e1205f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:32TGYPCVOYYYSX5XPOPHPYKN6J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PyEuroVoc: A Tool for Multilingual Legal Document Classification with EuroVoc Descriptors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrei-Marius Avram, Dan Tufis, Vasile Pais","submitted_at":"2021-08-02T19:46:21Z","abstract_excerpt":"EuroVoc is a multilingual thesaurus that was built for organizing the legislative documentary of the European Union institutions. It contains thousands of categories at different levels of specificity and its descriptors are targeted by legal texts in almost thirty languages. In this work we propose a unified framework for EuroVoc classification on 22 languages by fine-tuning modern Transformer-based pretrained language models. We study extensively the performance of our trained models and show that they significantly improve the results obtained by a similar tool - JEX - on the same dataset. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01139","kind":"arxiv","version":3},"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/2108.01139/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":"2026-07-05T03:04:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OrP3SU1GsNjdg5cyBt6Vmx5Hfs/5yinfGErVuz2azAt+6sw4tin//jbY9D2gQ7VRAeoGf5bSWh5dYpKt8A0cDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:42:25.945965Z"},"content_sha256":"71e4d9b211fe2f9ee3b3a0acf09a87a9e2029295ee5c77d0768217df0aeaaf87","schema_version":"1.0","event_id":"sha256:71e4d9b211fe2f9ee3b3a0acf09a87a9e2029295ee5c77d0768217df0aeaaf87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/32TGYPCVOYYYSX5XPOPHPYKN6J/bundle.json","state_url":"https://pith.science/pith/32TGYPCVOYYYSX5XPOPHPYKN6J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/32TGYPCVOYYYSX5XPOPHPYKN6J/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":"2026-08-10T16:42:25Z","links":{"resolver":"https://pith.science/pith/32TGYPCVOYYYSX5XPOPHPYKN6J","bundle":"https://pith.science/pith/32TGYPCVOYYYSX5XPOPHPYKN6J/bundle.json","state":"https://pith.science/pith/32TGYPCVOYYYSX5XPOPHPYKN6J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/32TGYPCVOYYYSX5XPOPHPYKN6J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:32TGYPCVOYYYSX5XPOPHPYKN6J","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":"d1c383c0ba9253fe708d330aac459b95cf84aa791f08b246b4fb90ce6e2c35cb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-02T19:46:21Z","title_canon_sha256":"70118b7b6f2ca4de6ceddde03b4d3bed94bd2bdc863acf44d36888ee55e87318"},"schema_version":"1.0","source":{"id":"2108.01139","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.01139","created_at":"2026-07-05T03:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"2108.01139v3","created_at":"2026-07-05T03:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01139","created_at":"2026-07-05T03:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"32TGYPCVOYYY","created_at":"2026-07-05T03:04:28Z"},{"alias_kind":"pith_short_16","alias_value":"32TGYPCVOYYYSX5X","created_at":"2026-07-05T03:04:28Z"},{"alias_kind":"pith_short_8","alias_value":"32TGYPCV","created_at":"2026-07-05T03:04:28Z"}],"graph_snapshots":[{"event_id":"sha256:71e4d9b211fe2f9ee3b3a0acf09a87a9e2029295ee5c77d0768217df0aeaaf87","target":"graph","created_at":"2026-07-05T03:04:28Z","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/2108.01139/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"EuroVoc is a multilingual thesaurus that was built for organizing the legislative documentary of the European Union institutions. It contains thousands of categories at different levels of specificity and its descriptors are targeted by legal texts in almost thirty languages. In this work we propose a unified framework for EuroVoc classification on 22 languages by fine-tuning modern Transformer-based pretrained language models. We study extensively the performance of our trained models and show that they significantly improve the results obtained by a similar tool - JEX - on the same dataset. ","authors_text":"Andrei-Marius Avram, Dan Tufis, Vasile Pais","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-02T19:46:21Z","title":"PyEuroVoc: A Tool for Multilingual Legal Document Classification with EuroVoc Descriptors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01139","kind":"arxiv","version":3},"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":"sha256:2607b76f4d9232011762b8438da9e98bfb3e35ac1908464954ce24609e1205f8","target":"record","created_at":"2026-07-05T03:04:28Z","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":"d1c383c0ba9253fe708d330aac459b95cf84aa791f08b246b4fb90ce6e2c35cb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-02T19:46:21Z","title_canon_sha256":"70118b7b6f2ca4de6ceddde03b4d3bed94bd2bdc863acf44d36888ee55e87318"},"schema_version":"1.0","source":{"id":"2108.01139","kind":"arxiv","version":3}},"canonical_sha256":"dea66c3c557631895fb77b9e77e14df2640c4193a88618105fa446b6bb0c4aa6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dea66c3c557631895fb77b9e77e14df2640c4193a88618105fa446b6bb0c4aa6","first_computed_at":"2026-07-05T03:04:28.035593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:04:28.035593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WnW8acKOmi14fKpqJVcl0dcuh+3QsvwI8zIzfkt0tPY/C9HXwNul939xXVF4x88eSQUB3nUAqqLY9OaC0jBWAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:04:28.036069Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.01139","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2607b76f4d9232011762b8438da9e98bfb3e35ac1908464954ce24609e1205f8","sha256:71e4d9b211fe2f9ee3b3a0acf09a87a9e2029295ee5c77d0768217df0aeaaf87"],"state_sha256":"0434f2fef41d727c97bb60f5684cf406171d924cbd4d9e4f757384ef1b355570"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rXGR4Ai7IS/FPFmGwWM/up+q9IKejtLXlOCbdk89YEXRUx9j8LObyILuzurX/f4LZfKPX5fNTxqKZdZI01a4BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T16:42:25.951122Z","bundle_sha256":"e5a453f9fe8ad95d14999e1df4f8248d4a7b1377607538380f59b38fee1d23e4"}}