{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PQINM2ETNM6UXPTVN6HLBA3DJD","short_pith_number":"pith:PQINM2ET","canonical_record":{"source":{"id":"2412.19048","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-26T04:05:28Z","cross_cats_sorted":[],"title_canon_sha256":"b37907e0632a07dea094a778e29255d2d65d7800444e50bdf3e5e8fa86dad68f","abstract_canon_sha256":"b7c9f43cbca83224363fa53fc67a2ee20ef1ac9f25cafef42ac83cd9f6956aba"},"schema_version":"1.0"},"canonical_sha256":"7c10d668936b3d4bbe756f8eb0836348d9270388536f0d9631e5d5b31136f7db","source":{"kind":"arxiv","id":"2412.19048","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19048","created_at":"2026-07-05T10:04:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19048v2","created_at":"2026-07-05T10:04:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19048","created_at":"2026-07-05T10:04:21Z"},{"alias_kind":"pith_short_12","alias_value":"PQINM2ETNM6U","created_at":"2026-07-05T10:04:21Z"},{"alias_kind":"pith_short_16","alias_value":"PQINM2ETNM6UXPTV","created_at":"2026-07-05T10:04:21Z"},{"alias_kind":"pith_short_8","alias_value":"PQINM2ET","created_at":"2026-07-05T10:04:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PQINM2ETNM6UXPTVN6HLBA3DJD","target":"record","payload":{"canonical_record":{"source":{"id":"2412.19048","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-26T04:05:28Z","cross_cats_sorted":[],"title_canon_sha256":"b37907e0632a07dea094a778e29255d2d65d7800444e50bdf3e5e8fa86dad68f","abstract_canon_sha256":"b7c9f43cbca83224363fa53fc67a2ee20ef1ac9f25cafef42ac83cd9f6956aba"},"schema_version":"1.0"},"canonical_sha256":"7c10d668936b3d4bbe756f8eb0836348d9270388536f0d9631e5d5b31136f7db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:21.327274Z","signature_b64":"Z7e/6t6Xa1GGf0/ptimi/YEe4OQzlXodOjj6MHUqh05BGZdCreVuJ1CPc1DmJLyZja7RrPEcGomJWR610RCBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c10d668936b3d4bbe756f8eb0836348d9270388536f0d9631e5d5b31136f7db","last_reissued_at":"2026-07-05T10:04:21.326859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:21.326859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.19048","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":"2026-07-05T10:04:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rqklzv4H6AfPAE0zgtwHAiS9faszXPFRO9VuuUI12z3O8cKcWNXHnXxXMNYVMDUWquMx/ZyL0tz8n5/AErwuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:33:52.229329Z"},"content_sha256":"7dc785e72a8736a2f4764c5aadbcacccfb3d5d5130962cd614673d130d530dbe","schema_version":"1.0","event_id":"sha256:7dc785e72a8736a2f4764c5aadbcacccfb3d5d5130962cd614673d130d530dbe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PQINM2ETNM6UXPTVN6HLBA3DJD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Jasper and Stella: distillation of SOTA embedding models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Dun Zhang, Fulong Wang, Jiacheng Li, Ziyang Zeng","submitted_at":"2024-12-26T04:05:28Z","abstract_excerpt":"A crucial component in many deep learning applications, such as Frequently Asked Questions (FAQ) and Retrieval-Augmented Generation (RAG), is dense retrieval. In this process, embedding models transform raw text into numerical vectors. However, the embedding models that currently excel on text embedding benchmarks, like the Massive Text Embedding Benchmark (MTEB), often have numerous parameters and high vector dimensionality. This poses challenges for their application in real-world scenarios. To address this issue, we propose a novel multi-stage distillation framework that enables a smaller s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19048","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/2412.19048/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":"2026-07-05T10:04:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pkJcNepvIvWVeaRr0cKa6zctWrlTP7gv/FKJXdL47i5FU+jATcnvkXIiNz9iSxH2nnu+G7sBm9ldFvnWIBdYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:33:52.229875Z"},"content_sha256":"731941a78107f7e5eb5924b82eea45387d4db869a9745ceedb022e390f9bda05","schema_version":"1.0","event_id":"sha256:731941a78107f7e5eb5924b82eea45387d4db869a9745ceedb022e390f9bda05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQINM2ETNM6UXPTVN6HLBA3DJD/bundle.json","state_url":"https://pith.science/pith/PQINM2ETNM6UXPTVN6HLBA3DJD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQINM2ETNM6UXPTVN6HLBA3DJD/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":"2026-08-04T14:33:52Z","links":{"resolver":"https://pith.science/pith/PQINM2ETNM6UXPTVN6HLBA3DJD","bundle":"https://pith.science/pith/PQINM2ETNM6UXPTVN6HLBA3DJD/bundle.json","state":"https://pith.science/pith/PQINM2ETNM6UXPTVN6HLBA3DJD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQINM2ETNM6UXPTVN6HLBA3DJD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PQINM2ETNM6UXPTVN6HLBA3DJD","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":"b7c9f43cbca83224363fa53fc67a2ee20ef1ac9f25cafef42ac83cd9f6956aba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-26T04:05:28Z","title_canon_sha256":"b37907e0632a07dea094a778e29255d2d65d7800444e50bdf3e5e8fa86dad68f"},"schema_version":"1.0","source":{"id":"2412.19048","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19048","created_at":"2026-07-05T10:04:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19048v2","created_at":"2026-07-05T10:04:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19048","created_at":"2026-07-05T10:04:21Z"},{"alias_kind":"pith_short_12","alias_value":"PQINM2ETNM6U","created_at":"2026-07-05T10:04:21Z"},{"alias_kind":"pith_short_16","alias_value":"PQINM2ETNM6UXPTV","created_at":"2026-07-05T10:04:21Z"},{"alias_kind":"pith_short_8","alias_value":"PQINM2ET","created_at":"2026-07-05T10:04:21Z"}],"graph_snapshots":[{"event_id":"sha256:731941a78107f7e5eb5924b82eea45387d4db869a9745ceedb022e390f9bda05","target":"graph","created_at":"2026-07-05T10:04:21Z","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/2412.19048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A crucial component in many deep learning applications, such as Frequently Asked Questions (FAQ) and Retrieval-Augmented Generation (RAG), is dense retrieval. In this process, embedding models transform raw text into numerical vectors. However, the embedding models that currently excel on text embedding benchmarks, like the Massive Text Embedding Benchmark (MTEB), often have numerous parameters and high vector dimensionality. This poses challenges for their application in real-world scenarios. To address this issue, we propose a novel multi-stage distillation framework that enables a smaller s","authors_text":"Dun Zhang, Fulong Wang, Jiacheng Li, Ziyang Zeng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-26T04:05:28Z","title":"Jasper and Stella: distillation of SOTA embedding models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19048","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":"sha256:7dc785e72a8736a2f4764c5aadbcacccfb3d5d5130962cd614673d130d530dbe","target":"record","created_at":"2026-07-05T10:04:21Z","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":"b7c9f43cbca83224363fa53fc67a2ee20ef1ac9f25cafef42ac83cd9f6956aba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-26T04:05:28Z","title_canon_sha256":"b37907e0632a07dea094a778e29255d2d65d7800444e50bdf3e5e8fa86dad68f"},"schema_version":"1.0","source":{"id":"2412.19048","kind":"arxiv","version":2}},"canonical_sha256":"7c10d668936b3d4bbe756f8eb0836348d9270388536f0d9631e5d5b31136f7db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c10d668936b3d4bbe756f8eb0836348d9270388536f0d9631e5d5b31136f7db","first_computed_at":"2026-07-05T10:04:21.326859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:21.326859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z7e/6t6Xa1GGf0/ptimi/YEe4OQzlXodOjj6MHUqh05BGZdCreVuJ1CPc1DmJLyZja7RrPEcGomJWR610RCBCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:21.327274Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19048","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dc785e72a8736a2f4764c5aadbcacccfb3d5d5130962cd614673d130d530dbe","sha256:731941a78107f7e5eb5924b82eea45387d4db869a9745ceedb022e390f9bda05"],"state_sha256":"3692a6867a88561257f4de281a4bb5fa52b67fbc4c6eab1b90c8b3aafdb9d525"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V9hxybzBi2RJ4CXzJbesy0AYe8fZGDRWzw2/FqkuwxuIrpAYvDQElAji785jxopZCbLhEWpd9UBk8nEVfMr9Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T14:33:52.234366Z","bundle_sha256":"a7e64b44f37ef46b5dd40b0e79f53bc1fb3b12448dbe6963a2bffe1dd1122f7d"}}