{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JNP7NH3OMTSDEQSBM37S3G2K3B","short_pith_number":"pith:JNP7NH3O","canonical_record":{"source":{"id":"2607.23507","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-26T07:13:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b650dd97f456457eada2f1e669e7889469c0f38222fe649cbd87afa88c99041","abstract_canon_sha256":"c7dfde50b583e8b7fe75e6676d285177da703ddfc4de1dd2de68f962211a06f5"},"schema_version":"1.0"},"canonical_sha256":"4b5ff69f6e64e432424166ff2d9b4ad858df65de9bdd495a1f907a04f1599345","source":{"kind":"arxiv","id":"2607.23507","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23507","created_at":"2026-07-28T01:22:56Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23507v1","created_at":"2026-07-28T01:22:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23507","created_at":"2026-07-28T01:22:56Z"},{"alias_kind":"pith_short_12","alias_value":"JNP7NH3OMTSD","created_at":"2026-07-28T01:22:56Z"},{"alias_kind":"pith_short_16","alias_value":"JNP7NH3OMTSDEQSB","created_at":"2026-07-28T01:22:56Z"},{"alias_kind":"pith_short_8","alias_value":"JNP7NH3O","created_at":"2026-07-28T01:22:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JNP7NH3OMTSDEQSBM37S3G2K3B","target":"record","payload":{"canonical_record":{"source":{"id":"2607.23507","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-26T07:13:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b650dd97f456457eada2f1e669e7889469c0f38222fe649cbd87afa88c99041","abstract_canon_sha256":"c7dfde50b583e8b7fe75e6676d285177da703ddfc4de1dd2de68f962211a06f5"},"schema_version":"1.0"},"canonical_sha256":"4b5ff69f6e64e432424166ff2d9b4ad858df65de9bdd495a1f907a04f1599345","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:56.563094Z","signature_b64":"dBES+MPch9cl67WBx4DFSPwsLVj30eu09skg2EYbGO26aMMuMumEtktZp8KSdZkvNltb1dqiw0ZH+tVusgihDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b5ff69f6e64e432424166ff2d9b4ad858df65de9bdd495a1f907a04f1599345","last_reissued_at":"2026-07-28T01:22:56.562302Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:56.562302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.23507","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":"2026-07-28T01:22:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ambVjVUBm8Ycou6eaBIjdKfnNRP9zpvljFm4XibRpjIbHOEihUs3NQH5H44mQ0uQEwiNNmc/Jk+dACZPB3O6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T14:03:59.889138Z"},"content_sha256":"acd2d3c01e8a7934989aecb1d0901b7990a3bf43892f195dac4eb83edeef1677","schema_version":"1.0","event_id":"sha256:acd2d3c01e8a7934989aecb1d0901b7990a3bf43892f195dac4eb83edeef1677"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JNP7NH3OMTSDEQSBM37S3G2K3B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Choosing a Text Embedding Model: A Practical Benchmarking and Decision Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Madhav S Baidya","submitted_at":"2026-07-26T07:13:33Z","abstract_excerpt":"Choosing the right text embedding model is one of the most consequential -- and most frequently under-examined -- decisions in building a retrieval or search system, yet the model that tops a leaderboard is rarely the best choice for a given deployment. This report develops a practical, evidence-based framework for embedding model selection, built on a benchmarking study that evaluates T3EM (Text 3 Embedding Model), a commercial API-based embedding model, against a broad set of open-source alternatives on English-language retrieval tasks, and situates these findings within the wider Massive Te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23507","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/2607.23507/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":"2026-07-28T01:22:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kNetwWgnOpCrRI4sP2HCsC111VFyjEnbDTQKrs+zLw5BCG9g1nPmxquXEbPcnCXCVRS94CtG2NescGe8551+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T14:03:59.889627Z"},"content_sha256":"52e0cdb45d20c7b3e83ec53fbc6fdf6f289b4601bd738bcde413034ced286610","schema_version":"1.0","event_id":"sha256:52e0cdb45d20c7b3e83ec53fbc6fdf6f289b4601bd738bcde413034ced286610"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JNP7NH3OMTSDEQSBM37S3G2K3B/bundle.json","state_url":"https://pith.science/pith/JNP7NH3OMTSDEQSBM37S3G2K3B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JNP7NH3OMTSDEQSBM37S3G2K3B/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":"2026-08-01T14:03:59Z","links":{"resolver":"https://pith.science/pith/JNP7NH3OMTSDEQSBM37S3G2K3B","bundle":"https://pith.science/pith/JNP7NH3OMTSDEQSBM37S3G2K3B/bundle.json","state":"https://pith.science/pith/JNP7NH3OMTSDEQSBM37S3G2K3B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JNP7NH3OMTSDEQSBM37S3G2K3B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JNP7NH3OMTSDEQSBM37S3G2K3B","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":"c7dfde50b583e8b7fe75e6676d285177da703ddfc4de1dd2de68f962211a06f5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-26T07:13:33Z","title_canon_sha256":"7b650dd97f456457eada2f1e669e7889469c0f38222fe649cbd87afa88c99041"},"schema_version":"1.0","source":{"id":"2607.23507","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23507","created_at":"2026-07-28T01:22:56Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23507v1","created_at":"2026-07-28T01:22:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23507","created_at":"2026-07-28T01:22:56Z"},{"alias_kind":"pith_short_12","alias_value":"JNP7NH3OMTSD","created_at":"2026-07-28T01:22:56Z"},{"alias_kind":"pith_short_16","alias_value":"JNP7NH3OMTSDEQSB","created_at":"2026-07-28T01:22:56Z"},{"alias_kind":"pith_short_8","alias_value":"JNP7NH3O","created_at":"2026-07-28T01:22:56Z"}],"graph_snapshots":[{"event_id":"sha256:52e0cdb45d20c7b3e83ec53fbc6fdf6f289b4601bd738bcde413034ced286610","target":"graph","created_at":"2026-07-28T01:22:56Z","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/2607.23507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Choosing the right text embedding model is one of the most consequential -- and most frequently under-examined -- decisions in building a retrieval or search system, yet the model that tops a leaderboard is rarely the best choice for a given deployment. This report develops a practical, evidence-based framework for embedding model selection, built on a benchmarking study that evaluates T3EM (Text 3 Embedding Model), a commercial API-based embedding model, against a broad set of open-source alternatives on English-language retrieval tasks, and situates these findings within the wider Massive Te","authors_text":"Madhav S Baidya","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-26T07:13:33Z","title":"Choosing a Text Embedding Model: A Practical Benchmarking and Decision Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23507","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:acd2d3c01e8a7934989aecb1d0901b7990a3bf43892f195dac4eb83edeef1677","target":"record","created_at":"2026-07-28T01:22:56Z","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":"c7dfde50b583e8b7fe75e6676d285177da703ddfc4de1dd2de68f962211a06f5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-26T07:13:33Z","title_canon_sha256":"7b650dd97f456457eada2f1e669e7889469c0f38222fe649cbd87afa88c99041"},"schema_version":"1.0","source":{"id":"2607.23507","kind":"arxiv","version":1}},"canonical_sha256":"4b5ff69f6e64e432424166ff2d9b4ad858df65de9bdd495a1f907a04f1599345","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b5ff69f6e64e432424166ff2d9b4ad858df65de9bdd495a1f907a04f1599345","first_computed_at":"2026-07-28T01:22:56.562302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:22:56.562302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dBES+MPch9cl67WBx4DFSPwsLVj30eu09skg2EYbGO26aMMuMumEtktZp8KSdZkvNltb1dqiw0ZH+tVusgihDA==","signature_status":"signed_v1","signed_at":"2026-07-28T01:22:56.563094Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23507","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acd2d3c01e8a7934989aecb1d0901b7990a3bf43892f195dac4eb83edeef1677","sha256:52e0cdb45d20c7b3e83ec53fbc6fdf6f289b4601bd738bcde413034ced286610"],"state_sha256":"008425e9ee46bcf1c014a12816ef13dbd3115871cf8b24cb0912f2f8728bc9c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wZGF2Ydoy3P4EvC7RiydmJIvRES+VnyFgP3mPr1J2skXJZkEHUIdOERzZD5KKrJKFF5ja8rCNzXMfRV1okC8BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T14:03:59.893439Z","bundle_sha256":"e1634def21cb43f8b0bc5c4d84b5fe69a984209b8e3d3f8dd8df6d5ecfa87509"}}