{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZPRJ7MG5GMMJDPSTD4YEWNW32N","short_pith_number":"pith:ZPRJ7MG5","canonical_record":{"source":{"id":"2001.04693","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-01-14T10:12:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b4758aa81a67c2e429f120c28beafd0e34ec074b5704553e757abcc1aaafa20b","abstract_canon_sha256":"cb77da822792546bd5520d608fbb10d650e49d0878ab6a686fc0501f64638fed"},"schema_version":"1.0"},"canonical_sha256":"cbe29fb0dd331891be531f304b36dbd36820e43955357c7371ea92275d33138f","source":{"kind":"arxiv","id":"2001.04693","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.04693","created_at":"2026-07-05T00:33:28Z"},{"alias_kind":"arxiv_version","alias_value":"2001.04693v1","created_at":"2026-07-05T00:33:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.04693","created_at":"2026-07-05T00:33:28Z"},{"alias_kind":"pith_short_12","alias_value":"ZPRJ7MG5GMMJ","created_at":"2026-07-05T00:33:28Z"},{"alias_kind":"pith_short_16","alias_value":"ZPRJ7MG5GMMJDPST","created_at":"2026-07-05T00:33:28Z"},{"alias_kind":"pith_short_8","alias_value":"ZPRJ7MG5","created_at":"2026-07-05T00:33:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZPRJ7MG5GMMJDPSTD4YEWNW32N","target":"record","payload":{"canonical_record":{"source":{"id":"2001.04693","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-01-14T10:12:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b4758aa81a67c2e429f120c28beafd0e34ec074b5704553e757abcc1aaafa20b","abstract_canon_sha256":"cb77da822792546bd5520d608fbb10d650e49d0878ab6a686fc0501f64638fed"},"schema_version":"1.0"},"canonical_sha256":"cbe29fb0dd331891be531f304b36dbd36820e43955357c7371ea92275d33138f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:33:28.643128Z","signature_b64":"BkV7ebTi46avQbcshkc8MWj3bCgYkYtQn99NF8U2wm0WpaHIQV+56dymSTeX7d4VMDL0vf8FvxHlvLIIyncFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbe29fb0dd331891be531f304b36dbd36820e43955357c7371ea92275d33138f","last_reissued_at":"2026-07-05T00:33:28.642714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:33:28.642714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.04693","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":"2026-07-05T00:33:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2QKfbNTveel31C4qBeXfNGENMpG8XtYQbUO4gTRzolJ6qU+gRm+F7r7sK3zrdcjAyBV2+/zflRWB3Je6ACA+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T23:02:30.925928Z"},"content_sha256":"0989dfc4d15941cf0ac402ca290bd2ff9d56e3ed1d16b9ac8100998c3b54987d","schema_version":"1.0","event_id":"sha256:0989dfc4d15941cf0ac402ca290bd2ff9d56e3ed1d16b9ac8100998c3b54987d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZPRJ7MG5GMMJDPSTD4YEWNW32N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Balancing the composition of word embeddings across heterogenous data sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"David Lassner, Maximilian Alber, Stephanie Brandl","submitted_at":"2020-01-14T10:12:50Z","abstract_excerpt":"Word embeddings capture semantic relationships based on contextual information and are the basis for a wide variety of natural language processing applications. Notably these relationships are solely learned from the data and subsequently the data composition impacts the semantic of embeddings which arguably can lead to biased word vectors. Given qualitatively different data subsets, we aim to align the influence of single subsets on the resulting word vectors, while retaining their quality. In this regard we propose a criteria to measure the shift towards a single data subset and develop appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.04693","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/2001.04693/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":"2026-07-05T00:33:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZK1vwn2/XOafesDbpUXbjhuPSVAXgZOmjZjHVo5eV9u24/h9ak8tEXUAKyKcAn8HrxA8EcZy60Mk8Nb66XjlBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T23:02:30.926327Z"},"content_sha256":"0ca1bec66d043ea689aff5a86f71c57ef542773edc4a98fba4a0829b2b3d91e6","schema_version":"1.0","event_id":"sha256:0ca1bec66d043ea689aff5a86f71c57ef542773edc4a98fba4a0829b2b3d91e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZPRJ7MG5GMMJDPSTD4YEWNW32N/bundle.json","state_url":"https://pith.science/pith/ZPRJ7MG5GMMJDPSTD4YEWNW32N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZPRJ7MG5GMMJDPSTD4YEWNW32N/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":"2026-07-15T23:02:30Z","links":{"resolver":"https://pith.science/pith/ZPRJ7MG5GMMJDPSTD4YEWNW32N","bundle":"https://pith.science/pith/ZPRJ7MG5GMMJDPSTD4YEWNW32N/bundle.json","state":"https://pith.science/pith/ZPRJ7MG5GMMJDPSTD4YEWNW32N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZPRJ7MG5GMMJDPSTD4YEWNW32N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZPRJ7MG5GMMJDPSTD4YEWNW32N","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":"cb77da822792546bd5520d608fbb10d650e49d0878ab6a686fc0501f64638fed","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-01-14T10:12:50Z","title_canon_sha256":"b4758aa81a67c2e429f120c28beafd0e34ec074b5704553e757abcc1aaafa20b"},"schema_version":"1.0","source":{"id":"2001.04693","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.04693","created_at":"2026-07-05T00:33:28Z"},{"alias_kind":"arxiv_version","alias_value":"2001.04693v1","created_at":"2026-07-05T00:33:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.04693","created_at":"2026-07-05T00:33:28Z"},{"alias_kind":"pith_short_12","alias_value":"ZPRJ7MG5GMMJ","created_at":"2026-07-05T00:33:28Z"},{"alias_kind":"pith_short_16","alias_value":"ZPRJ7MG5GMMJDPST","created_at":"2026-07-05T00:33:28Z"},{"alias_kind":"pith_short_8","alias_value":"ZPRJ7MG5","created_at":"2026-07-05T00:33:28Z"}],"graph_snapshots":[{"event_id":"sha256:0ca1bec66d043ea689aff5a86f71c57ef542773edc4a98fba4a0829b2b3d91e6","target":"graph","created_at":"2026-07-05T00:33:28Z","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/2001.04693/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Word embeddings capture semantic relationships based on contextual information and are the basis for a wide variety of natural language processing applications. Notably these relationships are solely learned from the data and subsequently the data composition impacts the semantic of embeddings which arguably can lead to biased word vectors. Given qualitatively different data subsets, we aim to align the influence of single subsets on the resulting word vectors, while retaining their quality. In this regard we propose a criteria to measure the shift towards a single data subset and develop appr","authors_text":"David Lassner, Maximilian Alber, Stephanie Brandl","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-01-14T10:12:50Z","title":"Balancing the composition of word embeddings across heterogenous data sets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.04693","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":"sha256:0989dfc4d15941cf0ac402ca290bd2ff9d56e3ed1d16b9ac8100998c3b54987d","target":"record","created_at":"2026-07-05T00:33:28Z","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":"cb77da822792546bd5520d608fbb10d650e49d0878ab6a686fc0501f64638fed","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-01-14T10:12:50Z","title_canon_sha256":"b4758aa81a67c2e429f120c28beafd0e34ec074b5704553e757abcc1aaafa20b"},"schema_version":"1.0","source":{"id":"2001.04693","kind":"arxiv","version":1}},"canonical_sha256":"cbe29fb0dd331891be531f304b36dbd36820e43955357c7371ea92275d33138f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbe29fb0dd331891be531f304b36dbd36820e43955357c7371ea92275d33138f","first_computed_at":"2026-07-05T00:33:28.642714Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:33:28.642714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BkV7ebTi46avQbcshkc8MWj3bCgYkYtQn99NF8U2wm0WpaHIQV+56dymSTeX7d4VMDL0vf8FvxHlvLIIyncFBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:33:28.643128Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.04693","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0989dfc4d15941cf0ac402ca290bd2ff9d56e3ed1d16b9ac8100998c3b54987d","sha256:0ca1bec66d043ea689aff5a86f71c57ef542773edc4a98fba4a0829b2b3d91e6"],"state_sha256":"7d5fef563eefaeaff04728e39d22745bdb030bf27801f599b7b5907ac22b0ba5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XmFqXm+4xHLUcgRLnEoUaLNgUrFhoBuj5L5AtmL1403mIhw4dxIoAtFsx/Jnf8cJjIWbZwEq1YbC/hWja98VDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-15T23:02:30.928515Z","bundle_sha256":"48c8f8b68c3cd495721f820d88a4601b79cf5b3da5f228d9e015c1acbaf86116"}}