{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JF2ONQ5JWZFHMPMFWR3MJZ4NEW","short_pith_number":"pith:JF2ONQ5J","canonical_record":{"source":{"id":"2607.17378","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2026-07-19T18:37:49Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"1992af78d3ffff0a3efb2c18819e5885be5ad294ddb3c24b9abca7529fbb4b65","abstract_canon_sha256":"8ccf1f019ce0477665de37a70cf11c15ed0483696abe6f07f12ba9a6b003003b"},"schema_version":"1.0"},"canonical_sha256":"4974e6c3a9b64a763d85b476c4e78d25bd679137b5ed8ad1f7df90cee4541a48","source":{"kind":"arxiv","id":"2607.17378","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17378","created_at":"2026-07-21T01:21:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17378v1","created_at":"2026-07-21T01:21:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17378","created_at":"2026-07-21T01:21:30Z"},{"alias_kind":"pith_short_12","alias_value":"JF2ONQ5JWZFH","created_at":"2026-07-21T01:21:30Z"},{"alias_kind":"pith_short_16","alias_value":"JF2ONQ5JWZFHMPMF","created_at":"2026-07-21T01:21:30Z"},{"alias_kind":"pith_short_8","alias_value":"JF2ONQ5J","created_at":"2026-07-21T01:21:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JF2ONQ5JWZFHMPMFWR3MJZ4NEW","target":"record","payload":{"canonical_record":{"source":{"id":"2607.17378","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2026-07-19T18:37:49Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"1992af78d3ffff0a3efb2c18819e5885be5ad294ddb3c24b9abca7529fbb4b65","abstract_canon_sha256":"8ccf1f019ce0477665de37a70cf11c15ed0483696abe6f07f12ba9a6b003003b"},"schema_version":"1.0"},"canonical_sha256":"4974e6c3a9b64a763d85b476c4e78d25bd679137b5ed8ad1f7df90cee4541a48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:30.257636Z","signature_b64":"oLUF/KYxlw83el5GOJK3qNv29FSM0G1XrrbTvBXcNBGBR5dAivBhKZtBKRoAnVJ4zebgagAccLNwLqeq9ZWGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4974e6c3a9b64a763d85b476c4e78d25bd679137b5ed8ad1f7df90cee4541a48","last_reissued_at":"2026-07-21T01:21:30.256828Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:30.256828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.17378","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":"2026-07-21T01:21:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4igBSRZ2WEJBqlpAwYRn3oW2gxQxYXBoJeoIKnY1TmLmuFYywDXihnyJMBIHIYxT4XGH0/lsemMhLhg3t2zWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:58:10.928568Z"},"content_sha256":"868b0ef4c06b745b5f83d95f3dae74dc54e81ee4c88058619bee6fddee802873","schema_version":"1.0","event_id":"sha256:868b0ef4c06b745b5f83d95f3dae74dc54e81ee4c88058619bee6fddee802873"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JF2ONQ5JWZFHMPMFWR3MJZ4NEW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Econometrics with Pre-Trained Embeddings for Unstructured Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"econ.EM","authors_text":"Yuya Shimizu","submitted_at":"2026-07-19T18:37:49Z","abstract_excerpt":"Unstructured data, such as images and text, are increasingly used in empirical economics. Since training machine-learning models on unstructured data is costly, economists often use off-the-shelf pre-trained deep learning models developed by computer scientists to extract embeddings, which are then used as covariates in target economic analyses. Despite the popularity of this practice, its theoretical foundations remain limited. There are two main difficulties. First, the pre-trained model is usually trained on a different dataset and for a different task. Consequently, it is unclear when such"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17378","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/2607.17378/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":"2026-07-21T01:21:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CgtXRwxwsqfzMwtJwG0vjy+AUWxoe4GjeLwp8KEMYK963c8qrIyeW1ITWlzIpXmOmMdkl/xK7koj+fCks39YAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:58:10.929094Z"},"content_sha256":"7b26bf2b0e4e8b08cb47ec445e55be50c7a6e9211dac4a9d64ae71b0f64aeb01","schema_version":"1.0","event_id":"sha256:7b26bf2b0e4e8b08cb47ec445e55be50c7a6e9211dac4a9d64ae71b0f64aeb01"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JF2ONQ5JWZFHMPMFWR3MJZ4NEW/bundle.json","state_url":"https://pith.science/pith/JF2ONQ5JWZFHMPMFWR3MJZ4NEW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JF2ONQ5JWZFHMPMFWR3MJZ4NEW/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":"2026-08-04T19:58:10Z","links":{"resolver":"https://pith.science/pith/JF2ONQ5JWZFHMPMFWR3MJZ4NEW","bundle":"https://pith.science/pith/JF2ONQ5JWZFHMPMFWR3MJZ4NEW/bundle.json","state":"https://pith.science/pith/JF2ONQ5JWZFHMPMFWR3MJZ4NEW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JF2ONQ5JWZFHMPMFWR3MJZ4NEW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JF2ONQ5JWZFHMPMFWR3MJZ4NEW","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":"8ccf1f019ce0477665de37a70cf11c15ed0483696abe6f07f12ba9a6b003003b","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2026-07-19T18:37:49Z","title_canon_sha256":"1992af78d3ffff0a3efb2c18819e5885be5ad294ddb3c24b9abca7529fbb4b65"},"schema_version":"1.0","source":{"id":"2607.17378","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17378","created_at":"2026-07-21T01:21:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17378v1","created_at":"2026-07-21T01:21:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17378","created_at":"2026-07-21T01:21:30Z"},{"alias_kind":"pith_short_12","alias_value":"JF2ONQ5JWZFH","created_at":"2026-07-21T01:21:30Z"},{"alias_kind":"pith_short_16","alias_value":"JF2ONQ5JWZFHMPMF","created_at":"2026-07-21T01:21:30Z"},{"alias_kind":"pith_short_8","alias_value":"JF2ONQ5J","created_at":"2026-07-21T01:21:30Z"}],"graph_snapshots":[{"event_id":"sha256:7b26bf2b0e4e8b08cb47ec445e55be50c7a6e9211dac4a9d64ae71b0f64aeb01","target":"graph","created_at":"2026-07-21T01:21:30Z","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/2607.17378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unstructured data, such as images and text, are increasingly used in empirical economics. Since training machine-learning models on unstructured data is costly, economists often use off-the-shelf pre-trained deep learning models developed by computer scientists to extract embeddings, which are then used as covariates in target economic analyses. Despite the popularity of this practice, its theoretical foundations remain limited. There are two main difficulties. First, the pre-trained model is usually trained on a different dataset and for a different task. Consequently, it is unclear when such","authors_text":"Yuya Shimizu","cross_cats":["math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2026-07-19T18:37:49Z","title":"Econometrics with Pre-Trained Embeddings for Unstructured Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17378","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":"sha256:868b0ef4c06b745b5f83d95f3dae74dc54e81ee4c88058619bee6fddee802873","target":"record","created_at":"2026-07-21T01:21:30Z","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":"8ccf1f019ce0477665de37a70cf11c15ed0483696abe6f07f12ba9a6b003003b","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2026-07-19T18:37:49Z","title_canon_sha256":"1992af78d3ffff0a3efb2c18819e5885be5ad294ddb3c24b9abca7529fbb4b65"},"schema_version":"1.0","source":{"id":"2607.17378","kind":"arxiv","version":1}},"canonical_sha256":"4974e6c3a9b64a763d85b476c4e78d25bd679137b5ed8ad1f7df90cee4541a48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4974e6c3a9b64a763d85b476c4e78d25bd679137b5ed8ad1f7df90cee4541a48","first_computed_at":"2026-07-21T01:21:30.256828Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:30.256828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oLUF/KYxlw83el5GOJK3qNv29FSM0G1XrrbTvBXcNBGBR5dAivBhKZtBKRoAnVJ4zebgagAccLNwLqeq9ZWGBg==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:30.257636Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.17378","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:868b0ef4c06b745b5f83d95f3dae74dc54e81ee4c88058619bee6fddee802873","sha256:7b26bf2b0e4e8b08cb47ec445e55be50c7a6e9211dac4a9d64ae71b0f64aeb01"],"state_sha256":"a0b62f1b22351702fd0cc19cb3b5f467bf44a43f52bcc7fc57701cd85f58da68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oYVVVmj7e1215MhAMcvkb6hMH3LJQe5vuT8v91Gza6iAwF+ibl9ssbgC26dUYqEzLwAzIFSlSl5yVlQIzRdyBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:58:10.933092Z","bundle_sha256":"2b8d04bc279f8ae3a09d88347bec849e2558ff36e5d77fa09e8e0b94f2d316cd"}}