{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PFWBQQ3GIF3ST4JEF3TOA3UX4H","short_pith_number":"pith:PFWBQQ3G","canonical_record":{"source":{"id":"2505.12697","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-19T04:37:53Z","cross_cats_sorted":[],"title_canon_sha256":"693c1955aa61306cdc95de0de3af13c8a4a8f77a4b57650ce82f1e6998fabed2","abstract_canon_sha256":"43ecc2ba563b80e631b16291d827b6d062557211d27f88be71733b225436e5e8"},"schema_version":"1.0"},"canonical_sha256":"796c184366417729f1242ee6e06e97e1c25c8df34b450585d543b783c667514b","source":{"kind":"arxiv","id":"2505.12697","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12697","created_at":"2026-07-05T11:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12697v1","created_at":"2026-07-05T11:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12697","created_at":"2026-07-05T11:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"PFWBQQ3GIF3S","created_at":"2026-07-05T11:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"PFWBQQ3GIF3ST4JE","created_at":"2026-07-05T11:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"PFWBQQ3G","created_at":"2026-07-05T11:05:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PFWBQQ3GIF3ST4JEF3TOA3UX4H","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12697","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-19T04:37:53Z","cross_cats_sorted":[],"title_canon_sha256":"693c1955aa61306cdc95de0de3af13c8a4a8f77a4b57650ce82f1e6998fabed2","abstract_canon_sha256":"43ecc2ba563b80e631b16291d827b6d062557211d27f88be71733b225436e5e8"},"schema_version":"1.0"},"canonical_sha256":"796c184366417729f1242ee6e06e97e1c25c8df34b450585d543b783c667514b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:08.441614Z","signature_b64":"Y1eYgPg87vHUysHkVqgfM5C9TwY9aSa8wg+FxCd/CebVKeoy4yS4gOPjZVMG+ZRh29vKgTgmz83Tctze+oP3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"796c184366417729f1242ee6e06e97e1c25c8df34b450585d543b783c667514b","last_reissued_at":"2026-07-05T11:05:08.440929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:08.440929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12697","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":"2026-07-05T11:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"amZ7BWlbP3z4qDccRZc5hthIe7/vH6RZCvmgvB/87Cbjoi70BzRaOGFX1RlByPz5HVsU3YUbVrhFnRucCaOoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:14:00.866287Z"},"content_sha256":"f606294f227be4433518302e01b227d19c19078115fb85b1e5ba37898214b6d4","schema_version":"1.0","event_id":"sha256:f606294f227be4433518302e01b227d19c19078115fb85b1e5ba37898214b6d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PFWBQQ3GIF3ST4JEF3TOA3UX4H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards A Generalist Code Embedding Model Based On Massive Data Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chaofan Li, Defu Lian, Jianlyu Chen, Yingxia Shao, Zheng Liu","submitted_at":"2025-05-19T04:37:53Z","abstract_excerpt":"Code embedding models attract increasing attention due to the widespread popularity of retrieval-augmented generation (RAG) in software development. These models are expected to capture the rich semantic relationships inherent to code, which differ significantly from those found in text. However, existing models remain severely limited due to the scarcity of high-quality training data. In this work, we introduce \\textbf{CodeR} (\\underline{Code} \\underline{R}etrieval), a state-of-the-art embedding model for general-purpose code retrieval. The superior performance of CodeR is built upon CodeR-Pi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12697","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/2505.12697/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":"2026-07-05T11:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2l3clY1ZgceESR0dx/Zmhjzq4wkqcCBUPW7bDLWqVtIBu3fc79SdPxSjxQhKAqb7jqjl/Ra9AJaDHqFajYMMAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:14:00.866799Z"},"content_sha256":"6c3c03d3a1cf6f20f59e80d8948424edc64789682f2fa49a433c4d6da4f5dd62","schema_version":"1.0","event_id":"sha256:6c3c03d3a1cf6f20f59e80d8948424edc64789682f2fa49a433c4d6da4f5dd62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PFWBQQ3GIF3ST4JEF3TOA3UX4H/bundle.json","state_url":"https://pith.science/pith/PFWBQQ3GIF3ST4JEF3TOA3UX4H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PFWBQQ3GIF3ST4JEF3TOA3UX4H/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":"2026-08-04T16:14:00Z","links":{"resolver":"https://pith.science/pith/PFWBQQ3GIF3ST4JEF3TOA3UX4H","bundle":"https://pith.science/pith/PFWBQQ3GIF3ST4JEF3TOA3UX4H/bundle.json","state":"https://pith.science/pith/PFWBQQ3GIF3ST4JEF3TOA3UX4H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PFWBQQ3GIF3ST4JEF3TOA3UX4H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PFWBQQ3GIF3ST4JEF3TOA3UX4H","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":"43ecc2ba563b80e631b16291d827b6d062557211d27f88be71733b225436e5e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-19T04:37:53Z","title_canon_sha256":"693c1955aa61306cdc95de0de3af13c8a4a8f77a4b57650ce82f1e6998fabed2"},"schema_version":"1.0","source":{"id":"2505.12697","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12697","created_at":"2026-07-05T11:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12697v1","created_at":"2026-07-05T11:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12697","created_at":"2026-07-05T11:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"PFWBQQ3GIF3S","created_at":"2026-07-05T11:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"PFWBQQ3GIF3ST4JE","created_at":"2026-07-05T11:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"PFWBQQ3G","created_at":"2026-07-05T11:05:08Z"}],"graph_snapshots":[{"event_id":"sha256:6c3c03d3a1cf6f20f59e80d8948424edc64789682f2fa49a433c4d6da4f5dd62","target":"graph","created_at":"2026-07-05T11:05:08Z","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/2505.12697/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code embedding models attract increasing attention due to the widespread popularity of retrieval-augmented generation (RAG) in software development. These models are expected to capture the rich semantic relationships inherent to code, which differ significantly from those found in text. However, existing models remain severely limited due to the scarcity of high-quality training data. In this work, we introduce \\textbf{CodeR} (\\underline{Code} \\underline{R}etrieval), a state-of-the-art embedding model for general-purpose code retrieval. The superior performance of CodeR is built upon CodeR-Pi","authors_text":"Chaofan Li, Defu Lian, Jianlyu Chen, Yingxia Shao, Zheng Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-19T04:37:53Z","title":"Towards A Generalist Code Embedding Model Based On Massive Data Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12697","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:f606294f227be4433518302e01b227d19c19078115fb85b1e5ba37898214b6d4","target":"record","created_at":"2026-07-05T11:05:08Z","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":"43ecc2ba563b80e631b16291d827b6d062557211d27f88be71733b225436e5e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-19T04:37:53Z","title_canon_sha256":"693c1955aa61306cdc95de0de3af13c8a4a8f77a4b57650ce82f1e6998fabed2"},"schema_version":"1.0","source":{"id":"2505.12697","kind":"arxiv","version":1}},"canonical_sha256":"796c184366417729f1242ee6e06e97e1c25c8df34b450585d543b783c667514b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"796c184366417729f1242ee6e06e97e1c25c8df34b450585d543b783c667514b","first_computed_at":"2026-07-05T11:05:08.440929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:08.440929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y1eYgPg87vHUysHkVqgfM5C9TwY9aSa8wg+FxCd/CebVKeoy4yS4gOPjZVMG+ZRh29vKgTgmz83Tctze+oP3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:08.441614Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12697","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f606294f227be4433518302e01b227d19c19078115fb85b1e5ba37898214b6d4","sha256:6c3c03d3a1cf6f20f59e80d8948424edc64789682f2fa49a433c4d6da4f5dd62"],"state_sha256":"397ed05af1cae48dd6c91ba1c1d429272844f13b41d688c7555f26c3d47a9c53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r3X0mNDDghucwQMzk4tPUNvguWi2Ab9bfbixwdOVd1XCEUmjqejFOGWCkMM/6ZegzgHrLnxqO9yEZm9J8K5/Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:14:00.870883Z","bundle_sha256":"35a846a8a6d5b75cd1c67828358fd7f0bd2bf5430133dc791b6bf9f61536c81d"}}