{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:336X6RFRX3FMARKTU6OAGNO2LK","short_pith_number":"pith:336X6RFR","canonical_record":{"source":{"id":"2207.09068","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-19T04:45:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"375b79a6885e084d62dc97ec524fed88e15dc29dd2b77e1fdd91a6dc22b1699a","abstract_canon_sha256":"1b1f815b3a47b83959c95df9221ab589bbe18953c7d3df8671c886e1d5c3f943"},"schema_version":"1.0"},"canonical_sha256":"defd7f44b1becac04553a79c0335da5aa7cdbd04bf94ad54eb15ebb8ef853b80","source":{"kind":"arxiv","id":"2207.09068","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.09068","created_at":"2026-07-05T05:38:08Z"},{"alias_kind":"arxiv_version","alias_value":"2207.09068v5","created_at":"2026-07-05T05:38:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.09068","created_at":"2026-07-05T05:38:08Z"},{"alias_kind":"pith_short_12","alias_value":"336X6RFRX3FM","created_at":"2026-07-05T05:38:08Z"},{"alias_kind":"pith_short_16","alias_value":"336X6RFRX3FMARKT","created_at":"2026-07-05T05:38:08Z"},{"alias_kind":"pith_short_8","alias_value":"336X6RFR","created_at":"2026-07-05T05:38:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:336X6RFRX3FMARKTU6OAGNO2LK","target":"record","payload":{"canonical_record":{"source":{"id":"2207.09068","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-19T04:45:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"375b79a6885e084d62dc97ec524fed88e15dc29dd2b77e1fdd91a6dc22b1699a","abstract_canon_sha256":"1b1f815b3a47b83959c95df9221ab589bbe18953c7d3df8671c886e1d5c3f943"},"schema_version":"1.0"},"canonical_sha256":"defd7f44b1becac04553a79c0335da5aa7cdbd04bf94ad54eb15ebb8ef853b80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:08.842283Z","signature_b64":"wAzqalVAuOjJ+JcbZHejunSixvC7zHukl6czaWFHAu/vqEmdjT9tS+/4f3P0HjifPcoYoap6Gj9a3s2wP+RgAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"defd7f44b1becac04553a79c0335da5aa7cdbd04bf94ad54eb15ebb8ef853b80","last_reissued_at":"2026-07-05T05:38:08.841859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:08.841859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.09068","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:38:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"INRUBkktXC6stD3M3+OEP7NncVtrkhKtk3ztkmT6BUtXjWXNJPXvSpL7YQr7tJI4E39qYKpgdioL3x5fQTu2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:14:58.476029Z"},"content_sha256":"7f32c3f0dc4acb552efc36ecf7194bc1bb77cc44c97101038a5017bb178dce5f","schema_version":"1.0","event_id":"sha256:7f32c3f0dc4acb552efc36ecf7194bc1bb77cc44c97101038a5017bb178dce5f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:336X6RFRX3FMARKTU6OAGNO2LK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anh Nguyen, Seunghyun Yoon, Thang M. Pham, Trung Bui","submitted_at":"2022-07-19T04:45:41Z","abstract_excerpt":"While contextualized word embeddings have been a de-facto standard, learning contextualized phrase embeddings is less explored and being hindered by the lack of a human-annotated benchmark that tests machine understanding of phrase semantics given a context sentence or paragraph (instead of phrases alone). To fill this gap, we propose PiC -- a dataset of ~28K of noun phrases accompanied by their contextual Wikipedia pages and a suite of three tasks for training and evaluating phrase embeddings. Training on PiC improves ranking models' accuracy and remarkably pushes span-selection (SS) models ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.09068","kind":"arxiv","version":5},"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/2207.09068/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":"2026-07-05T05:38:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ShKsAWsyGiRunpAWaxrdlzAo7h5/tdpyz4kTmODD1x4i4v+wNfDwCETP8L+NMDxGNNwEcOiAySmdgZH3XFckCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:14:58.476553Z"},"content_sha256":"821639619e5046581d317decd8b42c94e454702ce2581888358fe48b30666001","schema_version":"1.0","event_id":"sha256:821639619e5046581d317decd8b42c94e454702ce2581888358fe48b30666001"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/336X6RFRX3FMARKTU6OAGNO2LK/bundle.json","state_url":"https://pith.science/pith/336X6RFRX3FMARKTU6OAGNO2LK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/336X6RFRX3FMARKTU6OAGNO2LK/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":"2026-08-04T07:14:58Z","links":{"resolver":"https://pith.science/pith/336X6RFRX3FMARKTU6OAGNO2LK","bundle":"https://pith.science/pith/336X6RFRX3FMARKTU6OAGNO2LK/bundle.json","state":"https://pith.science/pith/336X6RFRX3FMARKTU6OAGNO2LK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/336X6RFRX3FMARKTU6OAGNO2LK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:336X6RFRX3FMARKTU6OAGNO2LK","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":"1b1f815b3a47b83959c95df9221ab589bbe18953c7d3df8671c886e1d5c3f943","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-19T04:45:41Z","title_canon_sha256":"375b79a6885e084d62dc97ec524fed88e15dc29dd2b77e1fdd91a6dc22b1699a"},"schema_version":"1.0","source":{"id":"2207.09068","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.09068","created_at":"2026-07-05T05:38:08Z"},{"alias_kind":"arxiv_version","alias_value":"2207.09068v5","created_at":"2026-07-05T05:38:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.09068","created_at":"2026-07-05T05:38:08Z"},{"alias_kind":"pith_short_12","alias_value":"336X6RFRX3FM","created_at":"2026-07-05T05:38:08Z"},{"alias_kind":"pith_short_16","alias_value":"336X6RFRX3FMARKT","created_at":"2026-07-05T05:38:08Z"},{"alias_kind":"pith_short_8","alias_value":"336X6RFR","created_at":"2026-07-05T05:38:08Z"}],"graph_snapshots":[{"event_id":"sha256:821639619e5046581d317decd8b42c94e454702ce2581888358fe48b30666001","target":"graph","created_at":"2026-07-05T05:38:08Z","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/2207.09068/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While contextualized word embeddings have been a de-facto standard, learning contextualized phrase embeddings is less explored and being hindered by the lack of a human-annotated benchmark that tests machine understanding of phrase semantics given a context sentence or paragraph (instead of phrases alone). To fill this gap, we propose PiC -- a dataset of ~28K of noun phrases accompanied by their contextual Wikipedia pages and a suite of three tasks for training and evaluating phrase embeddings. Training on PiC improves ranking models' accuracy and remarkably pushes span-selection (SS) models (","authors_text":"Anh Nguyen, Seunghyun Yoon, Thang M. Pham, Trung Bui","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-19T04:45:41Z","title":"PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.09068","kind":"arxiv","version":5},"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":"sha256:7f32c3f0dc4acb552efc36ecf7194bc1bb77cc44c97101038a5017bb178dce5f","target":"record","created_at":"2026-07-05T05:38:08Z","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":"1b1f815b3a47b83959c95df9221ab589bbe18953c7d3df8671c886e1d5c3f943","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-19T04:45:41Z","title_canon_sha256":"375b79a6885e084d62dc97ec524fed88e15dc29dd2b77e1fdd91a6dc22b1699a"},"schema_version":"1.0","source":{"id":"2207.09068","kind":"arxiv","version":5}},"canonical_sha256":"defd7f44b1becac04553a79c0335da5aa7cdbd04bf94ad54eb15ebb8ef853b80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"defd7f44b1becac04553a79c0335da5aa7cdbd04bf94ad54eb15ebb8ef853b80","first_computed_at":"2026-07-05T05:38:08.841859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:08.841859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wAzqalVAuOjJ+JcbZHejunSixvC7zHukl6czaWFHAu/vqEmdjT9tS+/4f3P0HjifPcoYoap6Gj9a3s2wP+RgAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:08.842283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.09068","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f32c3f0dc4acb552efc36ecf7194bc1bb77cc44c97101038a5017bb178dce5f","sha256:821639619e5046581d317decd8b42c94e454702ce2581888358fe48b30666001"],"state_sha256":"47f44f969bdbbe09d93886a299de18da3b66cff03ffef0ac6330ea5288c4ae13"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E826AycbaOCkBgFJTB+Jzn7uxDOG97jCgHGDIfI6Rm3EaVJb7FX8nyRhWfzuHbijFycdlah5WjS1ZUykVXapCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:14:58.481499Z","bundle_sha256":"984d6bdcb65887264efc9a7aed8ea2fdc879711b7293e13bf2c8cda18fb7eaf0"}}