{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JDCZWBYNMOOR5SOVTBSZDXNFG4","short_pith_number":"pith:JDCZWBYN","canonical_record":{"source":{"id":"2506.04344","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T18:02:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"758d0afaae2f04373d17ac68e429e5d1d0cca9b87f1d1466a056a213f17362b9","abstract_canon_sha256":"1a2796872eed313ff4585c0a416ac75f9c7a126dc9a2fa066253083bc77c4569"},"schema_version":"1.0"},"canonical_sha256":"48c59b070d639d1ec9d5986591dda5370056ca45c6c0335306db942580821d8e","source":{"kind":"arxiv","id":"2506.04344","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04344","created_at":"2026-07-05T11:16:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04344v1","created_at":"2026-07-05T11:16:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04344","created_at":"2026-07-05T11:16:12Z"},{"alias_kind":"pith_short_12","alias_value":"JDCZWBYNMOOR","created_at":"2026-07-05T11:16:12Z"},{"alias_kind":"pith_short_16","alias_value":"JDCZWBYNMOOR5SOV","created_at":"2026-07-05T11:16:12Z"},{"alias_kind":"pith_short_8","alias_value":"JDCZWBYN","created_at":"2026-07-05T11:16:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JDCZWBYNMOOR5SOVTBSZDXNFG4","target":"record","payload":{"canonical_record":{"source":{"id":"2506.04344","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T18:02:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"758d0afaae2f04373d17ac68e429e5d1d0cca9b87f1d1466a056a213f17362b9","abstract_canon_sha256":"1a2796872eed313ff4585c0a416ac75f9c7a126dc9a2fa066253083bc77c4569"},"schema_version":"1.0"},"canonical_sha256":"48c59b070d639d1ec9d5986591dda5370056ca45c6c0335306db942580821d8e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:12.972944Z","signature_b64":"+xgVc9+4jOPnm4yKLGtZwmwcVA6nv2BzxsTJuWCNcC2kLObZ8MBSDYCZHt1k0TZmv38nQxYbTeqw1+ZHgfu1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48c59b070d639d1ec9d5986591dda5370056ca45c6c0335306db942580821d8e","last_reissued_at":"2026-07-05T11:16:12.972423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:12.972423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.04344","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":"2026-07-05T11:16:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KGPIthcvMR21ec9lpj2EYe15cQQLTBRqY39+0xqolE07Jfs7UyZsNT2r1aULgHTx+Yvjx0g2J8oBo73g4xtrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:55:19.934147Z"},"content_sha256":"3f02081d1e59084907672aff4364b0e0e33204f7931cb93fb60ddd65ed580c49","schema_version":"1.0","event_id":"sha256:3f02081d1e59084907672aff4364b0e0e33204f7931cb93fb60ddd65ed580c49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JDCZWBYNMOOR5SOVTBSZDXNFG4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Benyu Zhang, Caojin Zhang, Jason Liu, Ke Li, Lizhu Zhang, Qiang Zhang, Sai Vidyaranya Nuthalapati, Serena Li, Xiangjun Fan","submitted_at":"2025-06-04T18:02:07Z","abstract_excerpt":"Large decoder-only language models (LLMs) have achieved remarkable success in generation and reasoning tasks, where they generate text responses given instructions. However, many applications, e.g., retrieval augmented generation (RAG), still rely on separate embedding models to generate text embeddings, which can complicate the system and introduce discrepancies in understanding of the query between the embedding model and LLMs. To address this limitation, we propose a simple self-supervised approach, Generative Embedding large language Model (GEM), that enables any large decoder-only LLM to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04344","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/2506.04344/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":"2026-07-05T11:16:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bif/lF7gLa9ndHwuyN1ZJPHaQevV7rv0nV80MbcYO7OhMyCTbApiiqnLJlPWpqBUABWmBIlz4gen7YH2CA2fCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:55:19.936025Z"},"content_sha256":"9cc59b917de34839e5c3d7510199da9a6cf01b9540f1f30c84300315f99a308d","schema_version":"1.0","event_id":"sha256:9cc59b917de34839e5c3d7510199da9a6cf01b9540f1f30c84300315f99a308d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JDCZWBYNMOOR5SOVTBSZDXNFG4/bundle.json","state_url":"https://pith.science/pith/JDCZWBYNMOOR5SOVTBSZDXNFG4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JDCZWBYNMOOR5SOVTBSZDXNFG4/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":"2026-08-08T04:55:19Z","links":{"resolver":"https://pith.science/pith/JDCZWBYNMOOR5SOVTBSZDXNFG4","bundle":"https://pith.science/pith/JDCZWBYNMOOR5SOVTBSZDXNFG4/bundle.json","state":"https://pith.science/pith/JDCZWBYNMOOR5SOVTBSZDXNFG4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JDCZWBYNMOOR5SOVTBSZDXNFG4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JDCZWBYNMOOR5SOVTBSZDXNFG4","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":"1a2796872eed313ff4585c0a416ac75f9c7a126dc9a2fa066253083bc77c4569","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T18:02:07Z","title_canon_sha256":"758d0afaae2f04373d17ac68e429e5d1d0cca9b87f1d1466a056a213f17362b9"},"schema_version":"1.0","source":{"id":"2506.04344","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04344","created_at":"2026-07-05T11:16:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04344v1","created_at":"2026-07-05T11:16:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04344","created_at":"2026-07-05T11:16:12Z"},{"alias_kind":"pith_short_12","alias_value":"JDCZWBYNMOOR","created_at":"2026-07-05T11:16:12Z"},{"alias_kind":"pith_short_16","alias_value":"JDCZWBYNMOOR5SOV","created_at":"2026-07-05T11:16:12Z"},{"alias_kind":"pith_short_8","alias_value":"JDCZWBYN","created_at":"2026-07-05T11:16:12Z"}],"graph_snapshots":[{"event_id":"sha256:9cc59b917de34839e5c3d7510199da9a6cf01b9540f1f30c84300315f99a308d","target":"graph","created_at":"2026-07-05T11:16:12Z","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/2506.04344/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large decoder-only language models (LLMs) have achieved remarkable success in generation and reasoning tasks, where they generate text responses given instructions. However, many applications, e.g., retrieval augmented generation (RAG), still rely on separate embedding models to generate text embeddings, which can complicate the system and introduce discrepancies in understanding of the query between the embedding model and LLMs. To address this limitation, we propose a simple self-supervised approach, Generative Embedding large language Model (GEM), that enables any large decoder-only LLM to ","authors_text":"Benyu Zhang, Caojin Zhang, Jason Liu, Ke Li, Lizhu Zhang, Qiang Zhang, Sai Vidyaranya Nuthalapati, Serena Li, Xiangjun Fan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04344","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":"sha256:3f02081d1e59084907672aff4364b0e0e33204f7931cb93fb60ddd65ed580c49","target":"record","created_at":"2026-07-05T11:16:12Z","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":"1a2796872eed313ff4585c0a416ac75f9c7a126dc9a2fa066253083bc77c4569","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T18:02:07Z","title_canon_sha256":"758d0afaae2f04373d17ac68e429e5d1d0cca9b87f1d1466a056a213f17362b9"},"schema_version":"1.0","source":{"id":"2506.04344","kind":"arxiv","version":1}},"canonical_sha256":"48c59b070d639d1ec9d5986591dda5370056ca45c6c0335306db942580821d8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48c59b070d639d1ec9d5986591dda5370056ca45c6c0335306db942580821d8e","first_computed_at":"2026-07-05T11:16:12.972423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:12.972423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+xgVc9+4jOPnm4yKLGtZwmwcVA6nv2BzxsTJuWCNcC2kLObZ8MBSDYCZHt1k0TZmv38nQxYbTeqw1+ZHgfu1Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:12.972944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04344","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f02081d1e59084907672aff4364b0e0e33204f7931cb93fb60ddd65ed580c49","sha256:9cc59b917de34839e5c3d7510199da9a6cf01b9540f1f30c84300315f99a308d"],"state_sha256":"b718a3b90033acc9bbbdea0761cd8e55d256ff72615b97fc8e26fb33c38ba6e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BBZAq4LYWdDkB0kMXppz2rwkoYJ+1gkbB9BhBPMXbGWEd8p86sP5nlZb4hoJc9/Pv44Zqlj5rHa2rCPAqM5kCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:55:19.954145Z","bundle_sha256":"681e1f835ae249dc848804ff82c9c81851e223cd4a370f245374b6c5d3ba1e02"}}