{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZLMQXMVPQC2QWRLUP5RH353WQW","short_pith_number":"pith:ZLMQXMVP","canonical_record":{"source":{"id":"2103.09813","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.ST","submitted_at":"2021-03-17T17:57:39Z","cross_cats_sorted":["q-fin.CP"],"title_canon_sha256":"4320b8f0a263c71b738b8950ddd1adb884f4b3fa149b1846236b890a04f145b5","abstract_canon_sha256":"1eb6d250cc45681b73173aaeff4653455cf87a3c3366fc7326483a9faf447fff"},"schema_version":"1.0"},"canonical_sha256":"cad90bb2af80b50b45747f627df77685a2a0f469b44e90fc121e94dcef45d6be","source":{"kind":"arxiv","id":"2103.09813","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.09813","created_at":"2026-05-26T01:03:06Z"},{"alias_kind":"arxiv_version","alias_value":"2103.09813v1","created_at":"2026-05-26T01:03:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09813","created_at":"2026-05-26T01:03:06Z"},{"alias_kind":"pith_short_12","alias_value":"ZLMQXMVPQC2Q","created_at":"2026-05-26T01:03:06Z"},{"alias_kind":"pith_short_16","alias_value":"ZLMQXMVPQC2QWRLU","created_at":"2026-05-26T01:03:06Z"},{"alias_kind":"pith_short_8","alias_value":"ZLMQXMVP","created_at":"2026-05-26T01:03:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZLMQXMVPQC2QWRLUP5RH353WQW","target":"record","payload":{"canonical_record":{"source":{"id":"2103.09813","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.ST","submitted_at":"2021-03-17T17:57:39Z","cross_cats_sorted":["q-fin.CP"],"title_canon_sha256":"4320b8f0a263c71b738b8950ddd1adb884f4b3fa149b1846236b890a04f145b5","abstract_canon_sha256":"1eb6d250cc45681b73173aaeff4653455cf87a3c3366fc7326483a9faf447fff"},"schema_version":"1.0"},"canonical_sha256":"cad90bb2af80b50b45747f627df77685a2a0f469b44e90fc121e94dcef45d6be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:06.995668Z","signature_b64":"ak89KPdKy6lTtt02RJ88qtHoMQ6a7Id1/FINVQkYXb+o5I8RnX84Z3EP7siOJykzlPLKuP2ya7pxMJCIoqqOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cad90bb2af80b50b45747f627df77685a2a0f469b44e90fc121e94dcef45d6be","last_reissued_at":"2026-05-26T01:03:06.995113Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:06.995113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.09813","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":"2026-05-26T01:03:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s9cbhBjRfzNLtjY7/ajSruGMgy6panRXTJ1XrCZYXS21nmGwyclVa65txpiXXAAyqmyb2v9tQlIMXu44PEvxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T15:52:44.571211Z"},"content_sha256":"74f08a911ae3e38cb64634c58d5367a1e425d6a694a9c176f8dfc614bc435d1d","schema_version":"1.0","event_id":"sha256:74f08a911ae3e38cb64634c58d5367a1e425d6a694a9c176f8dfc614bc435d1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZLMQXMVPQC2QWRLUP5RH353WQW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Word Embeddings Really Understand Loughran-McDonald's Polarities?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-fin.CP"],"primary_cat":"q-fin.ST","authors_text":"Charles-Albert Lehalle, Mengda Li","submitted_at":"2021-03-17T17:57:39Z","abstract_excerpt":"In this paper we perform a rigorous mathematical analysis of the word2vec model, especially when it is equipped with the Skip-gram learning scheme. Our goal is to explain how embeddings, that are now widely used in NLP (Natural Language Processing), are influenced by the distribution of terms in the documents of the considered corpus. We use a mathematical formulation to shed light on how the decision to use such a model makes implicit assumptions on the structure of the language. We show how Markovian assumptions, that we discuss, lead to a very clear theoretical understanding of the formatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09813","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/2103.09813/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":"2026-05-26T01:03:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yo261Qpa//xZNu72nfaAqsFuVP+rorJ/Fku+ObYPLVD63PzQnzE+OA6EiqZpUzs3evtuhxkITzfv/z/VwTNlAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T15:52:44.571591Z"},"content_sha256":"950faec5e2518faf50049beb731d335b0e0dcac8df68d995bfdc279436887f7f","schema_version":"1.0","event_id":"sha256:950faec5e2518faf50049beb731d335b0e0dcac8df68d995bfdc279436887f7f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLMQXMVPQC2QWRLUP5RH353WQW/bundle.json","state_url":"https://pith.science/pith/ZLMQXMVPQC2QWRLUP5RH353WQW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLMQXMVPQC2QWRLUP5RH353WQW/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":"2026-06-27T15:52:44Z","links":{"resolver":"https://pith.science/pith/ZLMQXMVPQC2QWRLUP5RH353WQW","bundle":"https://pith.science/pith/ZLMQXMVPQC2QWRLUP5RH353WQW/bundle.json","state":"https://pith.science/pith/ZLMQXMVPQC2QWRLUP5RH353WQW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLMQXMVPQC2QWRLUP5RH353WQW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZLMQXMVPQC2QWRLUP5RH353WQW","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":"1eb6d250cc45681b73173aaeff4653455cf87a3c3366fc7326483a9faf447fff","cross_cats_sorted":["q-fin.CP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.ST","submitted_at":"2021-03-17T17:57:39Z","title_canon_sha256":"4320b8f0a263c71b738b8950ddd1adb884f4b3fa149b1846236b890a04f145b5"},"schema_version":"1.0","source":{"id":"2103.09813","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.09813","created_at":"2026-05-26T01:03:06Z"},{"alias_kind":"arxiv_version","alias_value":"2103.09813v1","created_at":"2026-05-26T01:03:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09813","created_at":"2026-05-26T01:03:06Z"},{"alias_kind":"pith_short_12","alias_value":"ZLMQXMVPQC2Q","created_at":"2026-05-26T01:03:06Z"},{"alias_kind":"pith_short_16","alias_value":"ZLMQXMVPQC2QWRLU","created_at":"2026-05-26T01:03:06Z"},{"alias_kind":"pith_short_8","alias_value":"ZLMQXMVP","created_at":"2026-05-26T01:03:06Z"}],"graph_snapshots":[{"event_id":"sha256:950faec5e2518faf50049beb731d335b0e0dcac8df68d995bfdc279436887f7f","target":"graph","created_at":"2026-05-26T01:03:06Z","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/2103.09813/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we perform a rigorous mathematical analysis of the word2vec model, especially when it is equipped with the Skip-gram learning scheme. Our goal is to explain how embeddings, that are now widely used in NLP (Natural Language Processing), are influenced by the distribution of terms in the documents of the considered corpus. We use a mathematical formulation to shed light on how the decision to use such a model makes implicit assumptions on the structure of the language. We show how Markovian assumptions, that we discuss, lead to a very clear theoretical understanding of the formatio","authors_text":"Charles-Albert Lehalle, Mengda Li","cross_cats":["q-fin.CP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.ST","submitted_at":"2021-03-17T17:57:39Z","title":"Do Word Embeddings Really Understand Loughran-McDonald's Polarities?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09813","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":"sha256:74f08a911ae3e38cb64634c58d5367a1e425d6a694a9c176f8dfc614bc435d1d","target":"record","created_at":"2026-05-26T01:03:06Z","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":"1eb6d250cc45681b73173aaeff4653455cf87a3c3366fc7326483a9faf447fff","cross_cats_sorted":["q-fin.CP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.ST","submitted_at":"2021-03-17T17:57:39Z","title_canon_sha256":"4320b8f0a263c71b738b8950ddd1adb884f4b3fa149b1846236b890a04f145b5"},"schema_version":"1.0","source":{"id":"2103.09813","kind":"arxiv","version":1}},"canonical_sha256":"cad90bb2af80b50b45747f627df77685a2a0f469b44e90fc121e94dcef45d6be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cad90bb2af80b50b45747f627df77685a2a0f469b44e90fc121e94dcef45d6be","first_computed_at":"2026-05-26T01:03:06.995113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:06.995113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ak89KPdKy6lTtt02RJ88qtHoMQ6a7Id1/FINVQkYXb+o5I8RnX84Z3EP7siOJykzlPLKuP2ya7pxMJCIoqqOCg==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:06.995668Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.09813","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74f08a911ae3e38cb64634c58d5367a1e425d6a694a9c176f8dfc614bc435d1d","sha256:950faec5e2518faf50049beb731d335b0e0dcac8df68d995bfdc279436887f7f"],"state_sha256":"cc20612fb9b473be346cad34014909bdb0ae5c715520a941dfe5dbbb70dddec4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p5ZFIzNLYZik2RuYO9HofIabDzn1OtlM0TqdYGWY+3jS0jkBf4kEPi0Xm3PxDaMwWb/YhFrMcIb8L2xHsZ99Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T15:52:44.573557Z","bundle_sha256":"84d915729a8f31d676f8ff85b4fab4fc01159896d2dd6ba0bed756f24dcca4b7"}}