{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:22H2NXV5DRK2M5ZKRZBC5BQFW7","short_pith_number":"pith:22H2NXV5","canonical_record":{"source":{"id":"2406.09355","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-13T17:40:56Z","cross_cats_sorted":[],"title_canon_sha256":"96465305fd33b670e01311e0ae173f08642733122cac75c69ff5687e5932c2ce","abstract_canon_sha256":"27243e92f24ea142eefa7ff74c6f98cbb8bd13a4a74db81e76a89d7774591d48"},"schema_version":"1.0"},"canonical_sha256":"d68fa6debd1c55a6772a8e422e8605b7f8f6ab1a11f1e5de5c6eb7afaec0a721","source":{"kind":"arxiv","id":"2406.09355","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09355","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09355v2","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09355","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"pith_short_12","alias_value":"22H2NXV5DRK2","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"pith_short_16","alias_value":"22H2NXV5DRK2M5ZK","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"pith_short_8","alias_value":"22H2NXV5","created_at":"2026-07-05T10:57:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:22H2NXV5DRK2M5ZKRZBC5BQFW7","target":"record","payload":{"canonical_record":{"source":{"id":"2406.09355","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-13T17:40:56Z","cross_cats_sorted":[],"title_canon_sha256":"96465305fd33b670e01311e0ae173f08642733122cac75c69ff5687e5932c2ce","abstract_canon_sha256":"27243e92f24ea142eefa7ff74c6f98cbb8bd13a4a74db81e76a89d7774591d48"},"schema_version":"1.0"},"canonical_sha256":"d68fa6debd1c55a6772a8e422e8605b7f8f6ab1a11f1e5de5c6eb7afaec0a721","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:52.955764Z","signature_b64":"ELin/lX5G/TLO3aF0oU77jk02LsYTUufkEtJrAj3nM1wggyFPlQpOtKeM9R5I2+Cq4TUijvLzrEmvJd+UQnXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d68fa6debd1c55a6772a8e422e8605b7f8f6ab1a11f1e5de5c6eb7afaec0a721","last_reissued_at":"2026-07-05T10:57:52.955246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:52.955246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.09355","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":"2026-07-05T10:57:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eQmfNdfCZVo8R3VJLq5YgzNAKTDQyim34qMjaXcNInNUaHqT1Mk1MvfHhtkCIG8TlIvhBVOzK3DCw3ExCapwAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:53:54.769615Z"},"content_sha256":"de3628d84873905f792ddc7c0724dd0895371a53fd6275ae9bc5b715cc6311b8","schema_version":"1.0","event_id":"sha256:de3628d84873905f792ddc7c0724dd0895371a53fd6275ae9bc5b715cc6311b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:22H2NXV5DRK2M5ZKRZBC5BQFW7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can't Hide Behind the API: Stealing Black-Box Commercial Embedding Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jasper Xian, Jimmy Lin, Manveer Singh Tamber","submitted_at":"2024-06-13T17:40:56Z","abstract_excerpt":"Embedding models that generate dense vector representations of text are widely used and hold significant commercial value. Companies such as OpenAI and Cohere offer proprietary embedding models via paid APIs, but despite being \"hidden\" behind APIs, these models are not protected from theft. We present, to our knowledge, the first effort to \"steal\" these models for retrieval by training thief models on text-embedding pairs obtained from the APIs. Our experiments demonstrate that it is possible to replicate the retrieval effectiveness of commercial embedding models with a cost of under $300. Not"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09355","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/2406.09355/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":"2026-07-05T10:57:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9UgQybhWn0/cBmmi78xH5/TKzRWxU75Q1NEEi8/ZO5b+CWhI6DY026R7cAqrsuYRIRgiWuYkJnV/GR+3A2hDBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:53:54.770289Z"},"content_sha256":"cad4b321791588961f11e71a66ae99ce37732a3aebe3c7b31e0e2d0bfea66628","schema_version":"1.0","event_id":"sha256:cad4b321791588961f11e71a66ae99ce37732a3aebe3c7b31e0e2d0bfea66628"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/22H2NXV5DRK2M5ZKRZBC5BQFW7/bundle.json","state_url":"https://pith.science/pith/22H2NXV5DRK2M5ZKRZBC5BQFW7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/22H2NXV5DRK2M5ZKRZBC5BQFW7/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":"2026-08-23T10:53:54Z","links":{"resolver":"https://pith.science/pith/22H2NXV5DRK2M5ZKRZBC5BQFW7","bundle":"https://pith.science/pith/22H2NXV5DRK2M5ZKRZBC5BQFW7/bundle.json","state":"https://pith.science/pith/22H2NXV5DRK2M5ZKRZBC5BQFW7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/22H2NXV5DRK2M5ZKRZBC5BQFW7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:22H2NXV5DRK2M5ZKRZBC5BQFW7","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":"27243e92f24ea142eefa7ff74c6f98cbb8bd13a4a74db81e76a89d7774591d48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-13T17:40:56Z","title_canon_sha256":"96465305fd33b670e01311e0ae173f08642733122cac75c69ff5687e5932c2ce"},"schema_version":"1.0","source":{"id":"2406.09355","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09355","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09355v2","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09355","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"pith_short_12","alias_value":"22H2NXV5DRK2","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"pith_short_16","alias_value":"22H2NXV5DRK2M5ZK","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"pith_short_8","alias_value":"22H2NXV5","created_at":"2026-07-05T10:57:52Z"}],"graph_snapshots":[{"event_id":"sha256:cad4b321791588961f11e71a66ae99ce37732a3aebe3c7b31e0e2d0bfea66628","target":"graph","created_at":"2026-07-05T10:57:52Z","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/2406.09355/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embedding models that generate dense vector representations of text are widely used and hold significant commercial value. Companies such as OpenAI and Cohere offer proprietary embedding models via paid APIs, but despite being \"hidden\" behind APIs, these models are not protected from theft. We present, to our knowledge, the first effort to \"steal\" these models for retrieval by training thief models on text-embedding pairs obtained from the APIs. Our experiments demonstrate that it is possible to replicate the retrieval effectiveness of commercial embedding models with a cost of under $300. Not","authors_text":"Jasper Xian, Jimmy Lin, Manveer Singh Tamber","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-13T17:40:56Z","title":"Can't Hide Behind the API: Stealing Black-Box Commercial Embedding Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09355","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:de3628d84873905f792ddc7c0724dd0895371a53fd6275ae9bc5b715cc6311b8","target":"record","created_at":"2026-07-05T10:57:52Z","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":"27243e92f24ea142eefa7ff74c6f98cbb8bd13a4a74db81e76a89d7774591d48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-13T17:40:56Z","title_canon_sha256":"96465305fd33b670e01311e0ae173f08642733122cac75c69ff5687e5932c2ce"},"schema_version":"1.0","source":{"id":"2406.09355","kind":"arxiv","version":2}},"canonical_sha256":"d68fa6debd1c55a6772a8e422e8605b7f8f6ab1a11f1e5de5c6eb7afaec0a721","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d68fa6debd1c55a6772a8e422e8605b7f8f6ab1a11f1e5de5c6eb7afaec0a721","first_computed_at":"2026-07-05T10:57:52.955246Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:52.955246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ELin/lX5G/TLO3aF0oU77jk02LsYTUufkEtJrAj3nM1wggyFPlQpOtKeM9R5I2+Cq4TUijvLzrEmvJd+UQnXAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:52.955764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09355","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de3628d84873905f792ddc7c0724dd0895371a53fd6275ae9bc5b715cc6311b8","sha256:cad4b321791588961f11e71a66ae99ce37732a3aebe3c7b31e0e2d0bfea66628"],"state_sha256":"bb107b1a5e61d5e197e12bb93624aad3df25eecda752bfda7e71f17a88f1ad79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UCzOn6uJxEHKRxkpl7FjxKG7QZg0H9K3zTqwXSNrLRuvMKBfOp4rL70uUZkl3vtpfyQo6TM3IPcr1QjR/To8CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T10:53:54.775325Z","bundle_sha256":"86c462f13416b007f340607ae342108c74ebdcbf6fe3275f72cbb981d6344560"}}