{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UUKN57VBMGU7PDNUHPWVOMC6LW","short_pith_number":"pith:UUKN57VB","canonical_record":{"source":{"id":"2407.02883","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2024-07-03T07:58:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"87b56b9ceea4cabeb1c9b8835e3f76b17dd4d8d9953bed915ae6f2e2e2ce5a50","abstract_canon_sha256":"ced8b88c170e79365d82ad73defd629d424fef51c9f90f029530980ff3ca63bd"},"schema_version":"1.0"},"canonical_sha256":"a514defea161a9f78db43bed57305e5d930070fcdab95d6e89764292f1d6c993","source":{"kind":"arxiv","id":"2407.02883","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02883","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02883v3","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02883","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"pith_short_12","alias_value":"UUKN57VBMGU7","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"pith_short_16","alias_value":"UUKN57VBMGU7PDNU","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"pith_short_8","alias_value":"UUKN57VB","created_at":"2026-07-05T11:16:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UUKN57VBMGU7PDNUHPWVOMC6LW","target":"record","payload":{"canonical_record":{"source":{"id":"2407.02883","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2024-07-03T07:58:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"87b56b9ceea4cabeb1c9b8835e3f76b17dd4d8d9953bed915ae6f2e2e2ce5a50","abstract_canon_sha256":"ced8b88c170e79365d82ad73defd629d424fef51c9f90f029530980ff3ca63bd"},"schema_version":"1.0"},"canonical_sha256":"a514defea161a9f78db43bed57305e5d930070fcdab95d6e89764292f1d6c993","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:50.031720Z","signature_b64":"DsepFgnHdJbic1csWxsTRoie1D8RJz7nZ2ja2+N6JWFJNqPdveC0VPJ9efE8Vahw/YWrfnLMsME4Upxic/fICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a514defea161a9f78db43bed57305e5d930070fcdab95d6e89764292f1d6c993","last_reissued_at":"2026-07-05T11:16:50.031213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:50.031213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.02883","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ApTVe65HfYlq74efpEI0Rz08aiRAp2X9N5rIAkiDTJmeIzUXjjpB0RN77ipYUueyuT28Jwovkhf6l0x4QWvDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:50:11.641590Z"},"content_sha256":"44439fdfd9afa81028c4d188ed6031f50518204abb792a9f05fdd5bee405532f","schema_version":"1.0","event_id":"sha256:44439fdfd9afa81028c4d188ed6031f50518204abb792a9f05fdd5bee405532f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UUKN57VBMGU7PDNUHPWVOMC6LW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Hao Zhang, Kuicai Dong, Ruiming Tang, Wei Xia, Xiangyang Li, Xinyi Dai, Yasheng Wang, Yi Quan Lee","submitted_at":"2024-07-03T07:58:20Z","abstract_excerpt":"Despite the substantial success of Information Retrieval (IR) in various NLP tasks, most IR systems predominantly handle queries and corpora in natural language, neglecting the domain of code retrieval. Code retrieval is critically important yet remains under-explored, with existing methods and benchmarks inadequately representing the diversity of code in various domains and tasks. Addressing this gap, we present COIR (Code Information Retrieval Benchmark), a robust and comprehensive benchmark specifically designed to assess code retrieval capabilities. COIR comprises ten meticulously curated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02883","kind":"arxiv","version":3},"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/2407.02883/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":"2026-07-05T11:16:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BSJr9mwv+zBlmCSf8fyVISRRuPc6NKC/5UX3rhr+xJuoX5Xc7+SttFTOCUzbxoxKj07KZsieuIRplznoyZ8ABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:50:11.642084Z"},"content_sha256":"5f734b0aed17437586ae5dafda8f6be6b4ebb185e0502f63e4fc4cf19022c313","schema_version":"1.0","event_id":"sha256:5f734b0aed17437586ae5dafda8f6be6b4ebb185e0502f63e4fc4cf19022c313"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UUKN57VBMGU7PDNUHPWVOMC6LW/bundle.json","state_url":"https://pith.science/pith/UUKN57VBMGU7PDNUHPWVOMC6LW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UUKN57VBMGU7PDNUHPWVOMC6LW/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":"2026-08-10T23:50:11Z","links":{"resolver":"https://pith.science/pith/UUKN57VBMGU7PDNUHPWVOMC6LW","bundle":"https://pith.science/pith/UUKN57VBMGU7PDNUHPWVOMC6LW/bundle.json","state":"https://pith.science/pith/UUKN57VBMGU7PDNUHPWVOMC6LW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UUKN57VBMGU7PDNUHPWVOMC6LW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UUKN57VBMGU7PDNUHPWVOMC6LW","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":"ced8b88c170e79365d82ad73defd629d424fef51c9f90f029530980ff3ca63bd","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2024-07-03T07:58:20Z","title_canon_sha256":"87b56b9ceea4cabeb1c9b8835e3f76b17dd4d8d9953bed915ae6f2e2e2ce5a50"},"schema_version":"1.0","source":{"id":"2407.02883","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02883","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02883v3","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02883","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"pith_short_12","alias_value":"UUKN57VBMGU7","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"pith_short_16","alias_value":"UUKN57VBMGU7PDNU","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"pith_short_8","alias_value":"UUKN57VB","created_at":"2026-07-05T11:16:50Z"}],"graph_snapshots":[{"event_id":"sha256:5f734b0aed17437586ae5dafda8f6be6b4ebb185e0502f63e4fc4cf19022c313","target":"graph","created_at":"2026-07-05T11:16:50Z","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/2407.02883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the substantial success of Information Retrieval (IR) in various NLP tasks, most IR systems predominantly handle queries and corpora in natural language, neglecting the domain of code retrieval. Code retrieval is critically important yet remains under-explored, with existing methods and benchmarks inadequately representing the diversity of code in various domains and tasks. Addressing this gap, we present COIR (Code Information Retrieval Benchmark), a robust and comprehensive benchmark specifically designed to assess code retrieval capabilities. COIR comprises ten meticulously curated ","authors_text":"Hao Zhang, Kuicai Dong, Ruiming Tang, Wei Xia, Xiangyang Li, Xinyi Dai, Yasheng Wang, Yi Quan Lee","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2024-07-03T07:58:20Z","title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02883","kind":"arxiv","version":3},"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":"sha256:44439fdfd9afa81028c4d188ed6031f50518204abb792a9f05fdd5bee405532f","target":"record","created_at":"2026-07-05T11:16:50Z","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":"ced8b88c170e79365d82ad73defd629d424fef51c9f90f029530980ff3ca63bd","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2024-07-03T07:58:20Z","title_canon_sha256":"87b56b9ceea4cabeb1c9b8835e3f76b17dd4d8d9953bed915ae6f2e2e2ce5a50"},"schema_version":"1.0","source":{"id":"2407.02883","kind":"arxiv","version":3}},"canonical_sha256":"a514defea161a9f78db43bed57305e5d930070fcdab95d6e89764292f1d6c993","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a514defea161a9f78db43bed57305e5d930070fcdab95d6e89764292f1d6c993","first_computed_at":"2026-07-05T11:16:50.031213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:50.031213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DsepFgnHdJbic1csWxsTRoie1D8RJz7nZ2ja2+N6JWFJNqPdveC0VPJ9efE8Vahw/YWrfnLMsME4Upxic/fICg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:50.031720Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02883","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44439fdfd9afa81028c4d188ed6031f50518204abb792a9f05fdd5bee405532f","sha256:5f734b0aed17437586ae5dafda8f6be6b4ebb185e0502f63e4fc4cf19022c313"],"state_sha256":"39dbf124196762121e4f144aed31f116914f982ee37dda4615cbd98e37c27d2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+odF6Hm08PpShvaGzZnl9le/z/DaGajBu+H8iLLvQLgKJsYug9MDOydPEjFxBgH/HWCW6SbcgN+FcssnKfUCBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T23:50:11.646793Z","bundle_sha256":"cc07d6c526363c62e40a0fce7b9fb3a315598721b0806a8f7cf168db054a763f"}}