{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6LKHVFJ7SYNNEBBEMWM5SHBXOJ","short_pith_number":"pith:6LKHVFJ7","canonical_record":{"source":{"id":"2405.05374","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T19:05:18Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"1aa8382fc392496f2ba924a6e0e92b4f7486daedb09559d816c51b300017d9de","abstract_canon_sha256":"cb29da0ccd56d19e2147c8c891ff023ffb9bfa500a8a84f5b88a2d601145e27d"},"schema_version":"1.0"},"canonical_sha256":"f2d47a953f961ad204246599d91c37727f0204b0a4e7dd0dd5648c5bfbec1c75","source":{"kind":"arxiv","id":"2405.05374","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.05374","created_at":"2026-07-05T08:17:17Z"},{"alias_kind":"arxiv_version","alias_value":"2405.05374v1","created_at":"2026-07-05T08:17:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05374","created_at":"2026-07-05T08:17:17Z"},{"alias_kind":"pith_short_12","alias_value":"6LKHVFJ7SYNN","created_at":"2026-07-05T08:17:17Z"},{"alias_kind":"pith_short_16","alias_value":"6LKHVFJ7SYNNEBBE","created_at":"2026-07-05T08:17:17Z"},{"alias_kind":"pith_short_8","alias_value":"6LKHVFJ7","created_at":"2026-07-05T08:17:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6LKHVFJ7SYNNEBBEMWM5SHBXOJ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.05374","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T19:05:18Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"1aa8382fc392496f2ba924a6e0e92b4f7486daedb09559d816c51b300017d9de","abstract_canon_sha256":"cb29da0ccd56d19e2147c8c891ff023ffb9bfa500a8a84f5b88a2d601145e27d"},"schema_version":"1.0"},"canonical_sha256":"f2d47a953f961ad204246599d91c37727f0204b0a4e7dd0dd5648c5bfbec1c75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:17.625388Z","signature_b64":"OEhiil22qtWIdrUvTh1k6eSyQhbozys4njdidTpdEUAPjwERWsOskQst7czx3AS4alY9vAtUEbK1k2aoGhjACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2d47a953f961ad204246599d91c37727f0204b0a4e7dd0dd5648c5bfbec1c75","last_reissued_at":"2026-07-05T08:17:17.624963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:17.624963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.05374","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":"2026-07-05T08:17:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LD17WJhXd/PArHjinw8no0KuLTcQBOaXgbngScXUZoQwFKYlzrAHlEiyR3cYdj867wtZrFG4wigBgvL4yly0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:13:08.477660Z"},"content_sha256":"91f7df42726b8fb0c1f21d4721270502fef040ac61c4e5f7319a9c04dd1fd392","schema_version":"1.0","event_id":"sha256:91f7df42726b8fb0c1f21d4721270502fef040ac61c4e5f7319a9c04dd1fd392"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6LKHVFJ7SYNNEBBEMWM5SHBXOJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Daniel Campos, Danmei Xu, Gaurav Nuti, Luke Merrick","submitted_at":"2024-05-08T19:05:18Z","abstract_excerpt":"This report describes the training dataset creation and recipe behind the family of \\texttt{arctic-embed} text embedding models (a set of five models ranging from 22 to 334 million parameters with weights open-sourced under an Apache-2 license). At the time of their release, each model achieved state-of-the-art retrieval accuracy for models of their size on the MTEB Retrieval leaderboard, with the largest model, arctic-embed-l outperforming closed source embedding models such as Cohere's embed-v3 and Open AI's text-embed-3-large. In addition to the details of our training recipe, we have provi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05374","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/2405.05374/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":"2026-07-05T08:17:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vwt+c17BRUZaV0rGvtcZp8idM8bUWxG8wdf84Al6EIF8FSt30gWcShkSnB08mnMclsnAGISwwjUVPG8/uXVTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:13:08.478166Z"},"content_sha256":"23b66ad8f72d0b2326b9844969a8fd1762694052392e6fac9ed704dab093faca","schema_version":"1.0","event_id":"sha256:23b66ad8f72d0b2326b9844969a8fd1762694052392e6fac9ed704dab093faca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ/bundle.json","state_url":"https://pith.science/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ/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":"2026-08-07T17:13:08Z","links":{"resolver":"https://pith.science/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ","bundle":"https://pith.science/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ/bundle.json","state":"https://pith.science/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6LKHVFJ7SYNNEBBEMWM5SHBXOJ","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":"cb29da0ccd56d19e2147c8c891ff023ffb9bfa500a8a84f5b88a2d601145e27d","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T19:05:18Z","title_canon_sha256":"1aa8382fc392496f2ba924a6e0e92b4f7486daedb09559d816c51b300017d9de"},"schema_version":"1.0","source":{"id":"2405.05374","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.05374","created_at":"2026-07-05T08:17:17Z"},{"alias_kind":"arxiv_version","alias_value":"2405.05374v1","created_at":"2026-07-05T08:17:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05374","created_at":"2026-07-05T08:17:17Z"},{"alias_kind":"pith_short_12","alias_value":"6LKHVFJ7SYNN","created_at":"2026-07-05T08:17:17Z"},{"alias_kind":"pith_short_16","alias_value":"6LKHVFJ7SYNNEBBE","created_at":"2026-07-05T08:17:17Z"},{"alias_kind":"pith_short_8","alias_value":"6LKHVFJ7","created_at":"2026-07-05T08:17:17Z"}],"graph_snapshots":[{"event_id":"sha256:23b66ad8f72d0b2326b9844969a8fd1762694052392e6fac9ed704dab093faca","target":"graph","created_at":"2026-07-05T08:17:17Z","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/2405.05374/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This report describes the training dataset creation and recipe behind the family of \\texttt{arctic-embed} text embedding models (a set of five models ranging from 22 to 334 million parameters with weights open-sourced under an Apache-2 license). At the time of their release, each model achieved state-of-the-art retrieval accuracy for models of their size on the MTEB Retrieval leaderboard, with the largest model, arctic-embed-l outperforming closed source embedding models such as Cohere's embed-v3 and Open AI's text-embed-3-large. In addition to the details of our training recipe, we have provi","authors_text":"Daniel Campos, Danmei Xu, Gaurav Nuti, Luke Merrick","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T19:05:18Z","title":"Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05374","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":"sha256:91f7df42726b8fb0c1f21d4721270502fef040ac61c4e5f7319a9c04dd1fd392","target":"record","created_at":"2026-07-05T08:17:17Z","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":"cb29da0ccd56d19e2147c8c891ff023ffb9bfa500a8a84f5b88a2d601145e27d","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T19:05:18Z","title_canon_sha256":"1aa8382fc392496f2ba924a6e0e92b4f7486daedb09559d816c51b300017d9de"},"schema_version":"1.0","source":{"id":"2405.05374","kind":"arxiv","version":1}},"canonical_sha256":"f2d47a953f961ad204246599d91c37727f0204b0a4e7dd0dd5648c5bfbec1c75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2d47a953f961ad204246599d91c37727f0204b0a4e7dd0dd5648c5bfbec1c75","first_computed_at":"2026-07-05T08:17:17.624963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:17:17.624963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OEhiil22qtWIdrUvTh1k6eSyQhbozys4njdidTpdEUAPjwERWsOskQst7czx3AS4alY9vAtUEbK1k2aoGhjACA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:17:17.625388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.05374","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91f7df42726b8fb0c1f21d4721270502fef040ac61c4e5f7319a9c04dd1fd392","sha256:23b66ad8f72d0b2326b9844969a8fd1762694052392e6fac9ed704dab093faca"],"state_sha256":"5e3d06be7f36a541e7bc008e016ee8a629968e9143436a44840bdf0bbced1a34"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pmCYGG2Js9LmMXJMsbqJpW0aphMMXOXqS9F85l1ELOM29+IuEk7roAxVM/Umy370wQL40JYohmB/r3ri7DEJCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:13:08.481879Z","bundle_sha256":"3fa5bbf3673d58a3395d06e3ebc6ce4e25b542b4cdf90a14ce8e9b1fb616881c"}}