{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VBBJ7FYBWT6B54D4PYTSD5T5P3","short_pith_number":"pith:VBBJ7FYB","canonical_record":{"source":{"id":"2402.08638","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T18:04:53Z","cross_cats_sorted":[],"title_canon_sha256":"5f631fab9515277b9fd95c7c8b5602fadfbcf6d38ce4d9fb1aac7771b7097f68","abstract_canon_sha256":"33e132dcdda4b2f98e2c2272ed984b39cc7e793d5eb965c58285a93a3386854b"},"schema_version":"1.0"},"canonical_sha256":"a8429f9701b4fc1ef07c7e2721f67d7ed4629979f526b2acd60a1fb2e8510914","source":{"kind":"arxiv","id":"2402.08638","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08638","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08638v5","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08638","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"pith_short_12","alias_value":"VBBJ7FYBWT6B","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"pith_short_16","alias_value":"VBBJ7FYBWT6B54D4","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"pith_short_8","alias_value":"VBBJ7FYB","created_at":"2026-07-05T08:25:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VBBJ7FYBWT6B54D4PYTSD5T5P3","target":"record","payload":{"canonical_record":{"source":{"id":"2402.08638","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T18:04:53Z","cross_cats_sorted":[],"title_canon_sha256":"5f631fab9515277b9fd95c7c8b5602fadfbcf6d38ce4d9fb1aac7771b7097f68","abstract_canon_sha256":"33e132dcdda4b2f98e2c2272ed984b39cc7e793d5eb965c58285a93a3386854b"},"schema_version":"1.0"},"canonical_sha256":"a8429f9701b4fc1ef07c7e2721f67d7ed4629979f526b2acd60a1fb2e8510914","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:31.880965Z","signature_b64":"v39ZWYtHeiJnrVHc5/oqWd74UOy6hoKlV+2lQPCCJ8uNYfHTzBWtBKv1tN9ZuciXeR3BtbeZgnekYhOoxqdDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8429f9701b4fc1ef07c7e2721f67d7ed4629979f526b2acd60a1fb2e8510914","last_reissued_at":"2026-07-05T08:25:31.880514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:31.880514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.08638","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AAdqDVHjOG5KllOGuqrKJjuckahWNMflTOAhaWg+pazBES/RKgyYJWt3ncoBJrkHLkRQwAtjVXUlf+9Yn+UQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:55:17.474625Z"},"content_sha256":"0acb8cfddf1b22443d4e1a2a7f804d89cea7ded711a3a4c7995cd3bb41af34e7","schema_version":"1.0","event_id":"sha256:0acb8cfddf1b22443d4e1a2a7f804d89cea7ded711a3a4c7995cd3bb41af34e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VBBJ7FYBWT6B54D4PYTSD5T5P3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SemRel2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abinew Ali Ayele, Alham Fikri Aji, Chris Biemann, Christine de Kock, Genet Shanko Dekebo, Genta Winata, Gopichand Kanumolu, Hailegnaw Getaneh Tilaye, Ibrahim Said Ahmad, Idris Abdulmumin, Krishnapriya Vishnubhotla, Lokesh Madasu, Manish Shrivastava, Meriem Beloucif, Mohamed Abdalla, Nedjma Ousidhoum, Nirmal Surange, Oumaima Hourrane, Pavan Baswani, Saif M. Mohammad, Samuel Rutunda, Sanchit Ahuja, Seid Muhie Yimam, Shamsuddeen Hassan Muhammad, Sofia Bourhim, Thamar Solorio, Vladimir Araujo","submitted_at":"2024-02-13T18:04:53Z","abstract_excerpt":"Exploring and quantifying semantic relatedness is central to representing language and holds significant implications across various NLP tasks. While earlier NLP research primarily focused on semantic similarity, often within the English language context, we instead investigate the broader phenomenon of semantic relatedness. In this paper, we present \\textit{SemRel}, a new semantic relatedness dataset collection annotated by native speakers across 13 languages: \\textit{Afrikaans, Algerian Arabic, Amharic, English, Hausa, Hindi, Indonesian, Kinyarwanda, Marathi, Moroccan Arabic, Modern Standard"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08638","kind":"arxiv","version":5},"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/2402.08638/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":"2026-07-05T08:25:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O31S2B4bQiKjCZcewP3wtw1mOHUoihNXpqhgb6uM6Lk2GwUF6wyZT1vsRLbFZy9HyuAzuAhgfo2C1GAdnQogBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:55:17.475153Z"},"content_sha256":"52b6418d61ed0fc7782c6fddbba686c0deb286f279b807f4c56b6e943dcfc11f","schema_version":"1.0","event_id":"sha256:52b6418d61ed0fc7782c6fddbba686c0deb286f279b807f4c56b6e943dcfc11f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VBBJ7FYBWT6B54D4PYTSD5T5P3/bundle.json","state_url":"https://pith.science/pith/VBBJ7FYBWT6B54D4PYTSD5T5P3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VBBJ7FYBWT6B54D4PYTSD5T5P3/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":"2026-08-23T10:55:17Z","links":{"resolver":"https://pith.science/pith/VBBJ7FYBWT6B54D4PYTSD5T5P3","bundle":"https://pith.science/pith/VBBJ7FYBWT6B54D4PYTSD5T5P3/bundle.json","state":"https://pith.science/pith/VBBJ7FYBWT6B54D4PYTSD5T5P3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VBBJ7FYBWT6B54D4PYTSD5T5P3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VBBJ7FYBWT6B54D4PYTSD5T5P3","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":"33e132dcdda4b2f98e2c2272ed984b39cc7e793d5eb965c58285a93a3386854b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T18:04:53Z","title_canon_sha256":"5f631fab9515277b9fd95c7c8b5602fadfbcf6d38ce4d9fb1aac7771b7097f68"},"schema_version":"1.0","source":{"id":"2402.08638","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08638","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08638v5","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08638","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"pith_short_12","alias_value":"VBBJ7FYBWT6B","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"pith_short_16","alias_value":"VBBJ7FYBWT6B54D4","created_at":"2026-07-05T08:25:31Z"},{"alias_kind":"pith_short_8","alias_value":"VBBJ7FYB","created_at":"2026-07-05T08:25:31Z"}],"graph_snapshots":[{"event_id":"sha256:52b6418d61ed0fc7782c6fddbba686c0deb286f279b807f4c56b6e943dcfc11f","target":"graph","created_at":"2026-07-05T08:25:31Z","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/2402.08638/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploring and quantifying semantic relatedness is central to representing language and holds significant implications across various NLP tasks. While earlier NLP research primarily focused on semantic similarity, often within the English language context, we instead investigate the broader phenomenon of semantic relatedness. In this paper, we present \\textit{SemRel}, a new semantic relatedness dataset collection annotated by native speakers across 13 languages: \\textit{Afrikaans, Algerian Arabic, Amharic, English, Hausa, Hindi, Indonesian, Kinyarwanda, Marathi, Moroccan Arabic, Modern Standard","authors_text":"Abinew Ali Ayele, Alham Fikri Aji, Chris Biemann, Christine de Kock, Genet Shanko Dekebo, Genta Winata, Gopichand Kanumolu, Hailegnaw Getaneh Tilaye, Ibrahim Said Ahmad, Idris Abdulmumin, Krishnapriya Vishnubhotla, Lokesh Madasu, Manish Shrivastava, Meriem Beloucif, Mohamed Abdalla, Nedjma Ousidhoum, Nirmal Surange, Oumaima Hourrane, Pavan Baswani, Saif M. Mohammad, Samuel Rutunda, Sanchit Ahuja, Seid Muhie Yimam, Shamsuddeen Hassan Muhammad, Sofia Bourhim, Thamar Solorio, Vladimir Araujo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T18:04:53Z","title":"SemRel2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08638","kind":"arxiv","version":5},"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":"sha256:0acb8cfddf1b22443d4e1a2a7f804d89cea7ded711a3a4c7995cd3bb41af34e7","target":"record","created_at":"2026-07-05T08:25:31Z","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":"33e132dcdda4b2f98e2c2272ed984b39cc7e793d5eb965c58285a93a3386854b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T18:04:53Z","title_canon_sha256":"5f631fab9515277b9fd95c7c8b5602fadfbcf6d38ce4d9fb1aac7771b7097f68"},"schema_version":"1.0","source":{"id":"2402.08638","kind":"arxiv","version":5}},"canonical_sha256":"a8429f9701b4fc1ef07c7e2721f67d7ed4629979f526b2acd60a1fb2e8510914","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8429f9701b4fc1ef07c7e2721f67d7ed4629979f526b2acd60a1fb2e8510914","first_computed_at":"2026-07-05T08:25:31.880514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:31.880514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v39ZWYtHeiJnrVHc5/oqWd74UOy6hoKlV+2lQPCCJ8uNYfHTzBWtBKv1tN9ZuciXeR3BtbeZgnekYhOoxqdDBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:31.880965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08638","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0acb8cfddf1b22443d4e1a2a7f804d89cea7ded711a3a4c7995cd3bb41af34e7","sha256:52b6418d61ed0fc7782c6fddbba686c0deb286f279b807f4c56b6e943dcfc11f"],"state_sha256":"9056fcdd104e6e35078482beab1b08adda08a9287b63cb688e69bf51d3795e53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ALnmS9QgsgdZiVj4hg53v8iONFvsykmHNKs93XtSvLoLj+/B4qk7L/+yRUno4p4agbZDitZ5211aLEq9OX/mDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T10:55:17.479975Z","bundle_sha256":"b6293a6612b173d07e71500afdbb78515375db881e9c3a5502e180cdfba4ff5d"}}