{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SJTERNCMHITS7SUHRKKVP4TRND","short_pith_number":"pith:SJTERNCM","canonical_record":{"source":{"id":"2506.07438","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T05:30:35Z","cross_cats_sorted":[],"title_canon_sha256":"e1b8d8571c2a4daa528f7219b625f81a3b480e4afa4ed4f90bf7b8a96594df03","abstract_canon_sha256":"2e98824fff642bccd1b0c7787e3cadcfc6190f1affd95384bb37f00d1d413491"},"schema_version":"1.0"},"canonical_sha256":"926648b44c3a272fca878a9557f27168ff782d0971bad38c3ae3a5fdac11ca28","source":{"kind":"arxiv","id":"2506.07438","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07438","created_at":"2026-07-05T11:25:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07438v2","created_at":"2026-07-05T11:25:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07438","created_at":"2026-07-05T11:25:12Z"},{"alias_kind":"pith_short_12","alias_value":"SJTERNCMHITS","created_at":"2026-07-05T11:25:12Z"},{"alias_kind":"pith_short_16","alias_value":"SJTERNCMHITS7SUH","created_at":"2026-07-05T11:25:12Z"},{"alias_kind":"pith_short_8","alias_value":"SJTERNCM","created_at":"2026-07-05T11:25:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SJTERNCMHITS7SUHRKKVP4TRND","target":"record","payload":{"canonical_record":{"source":{"id":"2506.07438","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T05:30:35Z","cross_cats_sorted":[],"title_canon_sha256":"e1b8d8571c2a4daa528f7219b625f81a3b480e4afa4ed4f90bf7b8a96594df03","abstract_canon_sha256":"2e98824fff642bccd1b0c7787e3cadcfc6190f1affd95384bb37f00d1d413491"},"schema_version":"1.0"},"canonical_sha256":"926648b44c3a272fca878a9557f27168ff782d0971bad38c3ae3a5fdac11ca28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:12.041978Z","signature_b64":"op3H1rUib/dRwWiwsL39W0S20cYyGbSaZcQ9wmH+8twvOsGv5wEsxvDD9QNlNkuzMsFZbMb3l2IlU+U1JLxwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"926648b44c3a272fca878a9557f27168ff782d0971bad38c3ae3a5fdac11ca28","last_reissued_at":"2026-07-05T11:25:12.041469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:12.041469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.07438","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":"2026-07-05T11:25:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y2PiWFDJXTmn9tIK/+laogXL3/2J5Sv5MY4xmA0dvV6EtEC7aKKy5AuzXaANNH41Eki2Qr9h4HFyjYLcjGHpDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:03:37.733704Z"},"content_sha256":"23c2a151e321b19b8f7652a6873c6caf2703941f5cd8c7948ccef23109645e1f","schema_version":"1.0","event_id":"sha256:23c2a151e321b19b8f7652a6873c6caf2703941f5cd8c7948ccef23109645e1f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SJTERNCMHITS7SUHRKKVP4TRND","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LGAI-EMBEDDING-Preview Technical Report","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"ChangWook Jun, Chulmin Yun, Hansol Jang, Honglak Lee, Hyewon Choi, Hyun Kim, Jooyoung Choi, Kyunghoon Bae, Stanley Jungkyu Choi","submitted_at":"2025-06-09T05:30:35Z","abstract_excerpt":"This report presents a unified instruction-based framework for learning generalized text embeddings optimized for both information retrieval (IR) and non-IR tasks. Built upon a decoder-only large language model (Mistral-7B), our approach combines in-context learning, soft supervision, and adaptive hard-negative mining to generate context-aware embeddings without task-specific fine-tuning. Structured instructions and few-shot examples are used to guide the model across diverse tasks, enabling strong performance on classification, semantic similarity, clustering, and reranking benchmarks. To imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07438","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/2506.07438/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":"2026-07-05T11:25:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HCgMiGtfRcQIzBb/RobxquCNV2hxSwkLNP40+vf3CiLyoJxUdPBg/PcN7vxC8HwsW/i6QKxf7DxQHpcFi+tvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:03:37.734215Z"},"content_sha256":"2e63244f90bbad0d7c98697ba6925278b19e13b0cb5a50e7f673d010958fe6ee","schema_version":"1.0","event_id":"sha256:2e63244f90bbad0d7c98697ba6925278b19e13b0cb5a50e7f673d010958fe6ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJTERNCMHITS7SUHRKKVP4TRND/bundle.json","state_url":"https://pith.science/pith/SJTERNCMHITS7SUHRKKVP4TRND/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJTERNCMHITS7SUHRKKVP4TRND/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":"2026-08-17T13:03:37Z","links":{"resolver":"https://pith.science/pith/SJTERNCMHITS7SUHRKKVP4TRND","bundle":"https://pith.science/pith/SJTERNCMHITS7SUHRKKVP4TRND/bundle.json","state":"https://pith.science/pith/SJTERNCMHITS7SUHRKKVP4TRND/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJTERNCMHITS7SUHRKKVP4TRND/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SJTERNCMHITS7SUHRKKVP4TRND","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":"2e98824fff642bccd1b0c7787e3cadcfc6190f1affd95384bb37f00d1d413491","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T05:30:35Z","title_canon_sha256":"e1b8d8571c2a4daa528f7219b625f81a3b480e4afa4ed4f90bf7b8a96594df03"},"schema_version":"1.0","source":{"id":"2506.07438","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07438","created_at":"2026-07-05T11:25:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07438v2","created_at":"2026-07-05T11:25:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07438","created_at":"2026-07-05T11:25:12Z"},{"alias_kind":"pith_short_12","alias_value":"SJTERNCMHITS","created_at":"2026-07-05T11:25:12Z"},{"alias_kind":"pith_short_16","alias_value":"SJTERNCMHITS7SUH","created_at":"2026-07-05T11:25:12Z"},{"alias_kind":"pith_short_8","alias_value":"SJTERNCM","created_at":"2026-07-05T11:25:12Z"}],"graph_snapshots":[{"event_id":"sha256:2e63244f90bbad0d7c98697ba6925278b19e13b0cb5a50e7f673d010958fe6ee","target":"graph","created_at":"2026-07-05T11:25:12Z","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/2506.07438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This report presents a unified instruction-based framework for learning generalized text embeddings optimized for both information retrieval (IR) and non-IR tasks. Built upon a decoder-only large language model (Mistral-7B), our approach combines in-context learning, soft supervision, and adaptive hard-negative mining to generate context-aware embeddings without task-specific fine-tuning. Structured instructions and few-shot examples are used to guide the model across diverse tasks, enabling strong performance on classification, semantic similarity, clustering, and reranking benchmarks. To imp","authors_text":"ChangWook Jun, Chulmin Yun, Hansol Jang, Honglak Lee, Hyewon Choi, Hyun Kim, Jooyoung Choi, Kyunghoon Bae, Stanley Jungkyu Choi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T05:30:35Z","title":"LGAI-EMBEDDING-Preview Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07438","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":"sha256:23c2a151e321b19b8f7652a6873c6caf2703941f5cd8c7948ccef23109645e1f","target":"record","created_at":"2026-07-05T11:25:12Z","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":"2e98824fff642bccd1b0c7787e3cadcfc6190f1affd95384bb37f00d1d413491","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T05:30:35Z","title_canon_sha256":"e1b8d8571c2a4daa528f7219b625f81a3b480e4afa4ed4f90bf7b8a96594df03"},"schema_version":"1.0","source":{"id":"2506.07438","kind":"arxiv","version":2}},"canonical_sha256":"926648b44c3a272fca878a9557f27168ff782d0971bad38c3ae3a5fdac11ca28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"926648b44c3a272fca878a9557f27168ff782d0971bad38c3ae3a5fdac11ca28","first_computed_at":"2026-07-05T11:25:12.041469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:12.041469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"op3H1rUib/dRwWiwsL39W0S20cYyGbSaZcQ9wmH+8twvOsGv5wEsxvDD9QNlNkuzMsFZbMb3l2IlU+U1JLxwBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:12.041978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07438","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23c2a151e321b19b8f7652a6873c6caf2703941f5cd8c7948ccef23109645e1f","sha256:2e63244f90bbad0d7c98697ba6925278b19e13b0cb5a50e7f673d010958fe6ee"],"state_sha256":"0cdf8a5d62a9ae0650d403aee8a9c30773171567019351579804608e6b2346a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Tcdw8wrgJk1g+QskiUDJb48D7b4omCqww6WYKhhhI1hV+qSs8j7qTS/3n2CzpVxW+sxFRLvB2OasLvOWzAABA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T13:03:37.740061Z","bundle_sha256":"f7c17720cbbaf6be4e04ef6ebb2585ced5ebe9eb76fc52a6a33e1b9452e0e163"}}