{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:F5BG6ACEUAFMIWXALNPCH5BPSC","short_pith_number":"pith:F5BG6ACE","canonical_record":{"source":{"id":"2310.08232","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T11:25:46Z","cross_cats_sorted":[],"title_canon_sha256":"51041f4a99783677d68fe1868c2111eb05bf17d278422b3cc331ed148890dcca","abstract_canon_sha256":"5a057a0ee014834ae1f06976429e91075d3a6f3712f35dab69bd572ced7922cf"},"schema_version":"1.0"},"canonical_sha256":"2f426f0044a00ac45ae05b5e23f42f908e5f388a0fd5bd7a24ecf82b9843ab34","source":{"kind":"arxiv","id":"2310.08232","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08232","created_at":"2026-07-05T11:07:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08232v2","created_at":"2026-07-05T11:07:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08232","created_at":"2026-07-05T11:07:00Z"},{"alias_kind":"pith_short_12","alias_value":"F5BG6ACEUAFM","created_at":"2026-07-05T11:07:00Z"},{"alias_kind":"pith_short_16","alias_value":"F5BG6ACEUAFMIWXA","created_at":"2026-07-05T11:07:00Z"},{"alias_kind":"pith_short_8","alias_value":"F5BG6ACE","created_at":"2026-07-05T11:07:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:F5BG6ACEUAFMIWXALNPCH5BPSC","target":"record","payload":{"canonical_record":{"source":{"id":"2310.08232","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T11:25:46Z","cross_cats_sorted":[],"title_canon_sha256":"51041f4a99783677d68fe1868c2111eb05bf17d278422b3cc331ed148890dcca","abstract_canon_sha256":"5a057a0ee014834ae1f06976429e91075d3a6f3712f35dab69bd572ced7922cf"},"schema_version":"1.0"},"canonical_sha256":"2f426f0044a00ac45ae05b5e23f42f908e5f388a0fd5bd7a24ecf82b9843ab34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:00.600497Z","signature_b64":"ZGgvfZLJpTmZxNY3ou/rGAalXvkXuhwIQpKw7kKBSVwNM1T5odcx0hr7A0A8rydlCcktAL6Qkw71Aawr8f8sDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f426f0044a00ac45ae05b5e23f42f908e5f388a0fd5bd7a24ecf82b9843ab34","last_reissued_at":"2026-07-05T11:07:00.600018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:00.600018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.08232","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":"2026-07-05T11:07:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8LynJfFoISnA0kuirEWsEGnlvfU9PzQpx/SuJTolOCEtCfKiaN6eBqk4Y35Nh4RI2xTkWHtd/yN4SW3jcryhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:45:22.861140Z"},"content_sha256":"0bca0c1ebd9b8c769faf2ff7c7787def661f1a60296227eb12fdd22d6e29ba98","schema_version":"1.0","event_id":"sha256:0bca0c1ebd9b8c769faf2ff7c7787def661f1a60296227eb12fdd22d6e29ba98"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:F5BG6ACEUAFMIWXALNPCH5BPSC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Models are Universal Embedders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dingkun Long, Meishan Zhang, Min Zhang, Pengjun Xie, Xin Zhang, Yanzhao Zhang, Zehan Li","submitted_at":"2023-10-12T11:25:46Z","abstract_excerpt":"In the large language model (LLM) revolution, embedding is a key component of various systems, such as retrieving knowledge or memories for LLMs or building content moderation filters. As such cases span from English to other natural or programming languages, from retrieval to classification and beyond, it is advantageous to build a unified embedding model rather than dedicated ones for each scenario. In this context, the pre-trained multilingual decoder-only large language models, e.g., BLOOM, emerge as a viable backbone option. To assess their potential, we propose straightforward strategies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08232","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/2310.08232/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":"2026-07-05T11:07:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cal1qWV1okFf8uqUsl6qtJY6CGQfnJvye4j4zYQdW+NWTFci2EOg++EOfAPQFXkJo4OgjdAfVlSkE31ZwAVWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:45:22.861752Z"},"content_sha256":"f976d25f9f60d279e03d4dcaa47342317ea752ec86fc418a4eead22dc26173a3","schema_version":"1.0","event_id":"sha256:f976d25f9f60d279e03d4dcaa47342317ea752ec86fc418a4eead22dc26173a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5BG6ACEUAFMIWXALNPCH5BPSC/bundle.json","state_url":"https://pith.science/pith/F5BG6ACEUAFMIWXALNPCH5BPSC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5BG6ACEUAFMIWXALNPCH5BPSC/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":"2026-08-08T16:45:22Z","links":{"resolver":"https://pith.science/pith/F5BG6ACEUAFMIWXALNPCH5BPSC","bundle":"https://pith.science/pith/F5BG6ACEUAFMIWXALNPCH5BPSC/bundle.json","state":"https://pith.science/pith/F5BG6ACEUAFMIWXALNPCH5BPSC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5BG6ACEUAFMIWXALNPCH5BPSC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:F5BG6ACEUAFMIWXALNPCH5BPSC","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":"5a057a0ee014834ae1f06976429e91075d3a6f3712f35dab69bd572ced7922cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T11:25:46Z","title_canon_sha256":"51041f4a99783677d68fe1868c2111eb05bf17d278422b3cc331ed148890dcca"},"schema_version":"1.0","source":{"id":"2310.08232","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08232","created_at":"2026-07-05T11:07:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08232v2","created_at":"2026-07-05T11:07:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08232","created_at":"2026-07-05T11:07:00Z"},{"alias_kind":"pith_short_12","alias_value":"F5BG6ACEUAFM","created_at":"2026-07-05T11:07:00Z"},{"alias_kind":"pith_short_16","alias_value":"F5BG6ACEUAFMIWXA","created_at":"2026-07-05T11:07:00Z"},{"alias_kind":"pith_short_8","alias_value":"F5BG6ACE","created_at":"2026-07-05T11:07:00Z"}],"graph_snapshots":[{"event_id":"sha256:f976d25f9f60d279e03d4dcaa47342317ea752ec86fc418a4eead22dc26173a3","target":"graph","created_at":"2026-07-05T11:07:00Z","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/2310.08232/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the large language model (LLM) revolution, embedding is a key component of various systems, such as retrieving knowledge or memories for LLMs or building content moderation filters. As such cases span from English to other natural or programming languages, from retrieval to classification and beyond, it is advantageous to build a unified embedding model rather than dedicated ones for each scenario. In this context, the pre-trained multilingual decoder-only large language models, e.g., BLOOM, emerge as a viable backbone option. To assess their potential, we propose straightforward strategies","authors_text":"Dingkun Long, Meishan Zhang, Min Zhang, Pengjun Xie, Xin Zhang, Yanzhao Zhang, Zehan Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T11:25:46Z","title":"Language Models are Universal Embedders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08232","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":"sha256:0bca0c1ebd9b8c769faf2ff7c7787def661f1a60296227eb12fdd22d6e29ba98","target":"record","created_at":"2026-07-05T11:07:00Z","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":"5a057a0ee014834ae1f06976429e91075d3a6f3712f35dab69bd572ced7922cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T11:25:46Z","title_canon_sha256":"51041f4a99783677d68fe1868c2111eb05bf17d278422b3cc331ed148890dcca"},"schema_version":"1.0","source":{"id":"2310.08232","kind":"arxiv","version":2}},"canonical_sha256":"2f426f0044a00ac45ae05b5e23f42f908e5f388a0fd5bd7a24ecf82b9843ab34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f426f0044a00ac45ae05b5e23f42f908e5f388a0fd5bd7a24ecf82b9843ab34","first_computed_at":"2026-07-05T11:07:00.600018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:00.600018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZGgvfZLJpTmZxNY3ou/rGAalXvkXuhwIQpKw7kKBSVwNM1T5odcx0hr7A0A8rydlCcktAL6Qkw71Aawr8f8sDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:00.600497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08232","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bca0c1ebd9b8c769faf2ff7c7787def661f1a60296227eb12fdd22d6e29ba98","sha256:f976d25f9f60d279e03d4dcaa47342317ea752ec86fc418a4eead22dc26173a3"],"state_sha256":"5e57ea0ab5dcdf20d8f275bded34e909de2f1b16e780c4ba01f56acc5acf0b43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"idZZalosgCFEJFTXSekwXB2Wh7YdbV8v8pFh9B4ADI9XSFDaGGyor4Unimw2hCDmQ1lnDojgnu8jz5qx0aA3BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:45:22.865723Z","bundle_sha256":"48add6f0e8594f9f3ecc6dd3daf88eb1cc21150825f5d7ee3a4a227a058b7f87"}}