{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:VFSWIL663YXGMVMGF5MYI5CAKE","short_pith_number":"pith:VFSWIL66","canonical_record":{"source":{"id":"1911.02671","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-06T23:12:56Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"1ecbd73bf888a4e773547c4b20b82c1634bcbb41552232cabae4c53d3e0bf45b","abstract_canon_sha256":"ce5632d00cff4da4665798cbaa10c801f8c0ecdece371428212801557413ec91"},"schema_version":"1.0"},"canonical_sha256":"a965642fdede2e6655862f598474405139ebe50a679f53a64067db2c7497ad6b","source":{"kind":"arxiv","id":"1911.02671","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.02671","created_at":"2026-07-05T00:17:40Z"},{"alias_kind":"arxiv_version","alias_value":"1911.02671v1","created_at":"2026-07-05T00:17:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.02671","created_at":"2026-07-05T00:17:40Z"},{"alias_kind":"pith_short_12","alias_value":"VFSWIL663YXG","created_at":"2026-07-05T00:17:40Z"},{"alias_kind":"pith_short_16","alias_value":"VFSWIL663YXGMVMG","created_at":"2026-07-05T00:17:40Z"},{"alias_kind":"pith_short_8","alias_value":"VFSWIL66","created_at":"2026-07-05T00:17:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:VFSWIL663YXGMVMGF5MYI5CAKE","target":"record","payload":{"canonical_record":{"source":{"id":"1911.02671","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-06T23:12:56Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"1ecbd73bf888a4e773547c4b20b82c1634bcbb41552232cabae4c53d3e0bf45b","abstract_canon_sha256":"ce5632d00cff4da4665798cbaa10c801f8c0ecdece371428212801557413ec91"},"schema_version":"1.0"},"canonical_sha256":"a965642fdede2e6655862f598474405139ebe50a679f53a64067db2c7497ad6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:17:40.287899Z","signature_b64":"GzpdnToxh27Cg6QyjNKsHB4gJq5h6I42Bsa3Obvqc2NcCvpBF+MmLO/XZCKrFM6y35Nq6O830lWXI1c/KjCtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a965642fdede2e6655862f598474405139ebe50a679f53a64067db2c7497ad6b","last_reissued_at":"2026-07-05T00:17:40.287400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:17:40.287400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.02671","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":"2026-07-05T00:17:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1tbYvVcF20aKNa7CSZ0WHO1g9c1JPDKGEPL0zfwK4DvIwP0Q/WsnTg1A45zw8sHsYK/54JHHY8gPHlIw2mRaBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T13:22:52.084232Z"},"content_sha256":"ea45deb27fa0c44b51971ba1b9f3b9794025e13fab5127ad887c7f45598cab61","schema_version":"1.0","event_id":"sha256:ea45deb27fa0c44b51971ba1b9f3b9794025e13fab5127ad887c7f45598cab61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:VFSWIL663YXGMVMGF5MYI5CAKE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Open Domain Web Keyphrase Extraction Beyond Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Arnold Overwijk, Chenyan Xiong, Chuan Hu, Daniel Campos, Lee Xiong","submitted_at":"2019-11-06T23:12:56Z","abstract_excerpt":"This paper studies keyphrase extraction in real-world scenarios where documents are from diverse domains and have variant content quality. We curate and release OpenKP, a large scale open domain keyphrase extraction dataset with near one hundred thousand web documents and expert keyphrase annotations. To handle the variations of domain and content quality, we develop BLING-KPE, a neural keyphrase extraction model that goes beyond language understanding using visual presentations of documents and weak supervision from search queries. Experimental results on OpenKP confirm the effectiveness of B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.02671","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/1911.02671/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":"2026-07-05T00:17:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yfta+0sq/g9VHFhI4XBc2scJzCwnw4XGmCwJP92YtKf+AOf+dzkJN4TZ96n8/nvTdq+XPIV4JTQ+yET6MFoeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T13:22:52.084601Z"},"content_sha256":"5bc190f8de5f2dcffcf8a0d63cf36546d03f6e82cbe472f0e469b7a350b914c9","schema_version":"1.0","event_id":"sha256:5bc190f8de5f2dcffcf8a0d63cf36546d03f6e82cbe472f0e469b7a350b914c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VFSWIL663YXGMVMGF5MYI5CAKE/bundle.json","state_url":"https://pith.science/pith/VFSWIL663YXGMVMGF5MYI5CAKE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VFSWIL663YXGMVMGF5MYI5CAKE/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":"2026-07-17T13:22:52Z","links":{"resolver":"https://pith.science/pith/VFSWIL663YXGMVMGF5MYI5CAKE","bundle":"https://pith.science/pith/VFSWIL663YXGMVMGF5MYI5CAKE/bundle.json","state":"https://pith.science/pith/VFSWIL663YXGMVMGF5MYI5CAKE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VFSWIL663YXGMVMGF5MYI5CAKE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VFSWIL663YXGMVMGF5MYI5CAKE","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":"ce5632d00cff4da4665798cbaa10c801f8c0ecdece371428212801557413ec91","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-06T23:12:56Z","title_canon_sha256":"1ecbd73bf888a4e773547c4b20b82c1634bcbb41552232cabae4c53d3e0bf45b"},"schema_version":"1.0","source":{"id":"1911.02671","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.02671","created_at":"2026-07-05T00:17:40Z"},{"alias_kind":"arxiv_version","alias_value":"1911.02671v1","created_at":"2026-07-05T00:17:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.02671","created_at":"2026-07-05T00:17:40Z"},{"alias_kind":"pith_short_12","alias_value":"VFSWIL663YXG","created_at":"2026-07-05T00:17:40Z"},{"alias_kind":"pith_short_16","alias_value":"VFSWIL663YXGMVMG","created_at":"2026-07-05T00:17:40Z"},{"alias_kind":"pith_short_8","alias_value":"VFSWIL66","created_at":"2026-07-05T00:17:40Z"}],"graph_snapshots":[{"event_id":"sha256:5bc190f8de5f2dcffcf8a0d63cf36546d03f6e82cbe472f0e469b7a350b914c9","target":"graph","created_at":"2026-07-05T00:17:40Z","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/1911.02671/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies keyphrase extraction in real-world scenarios where documents are from diverse domains and have variant content quality. We curate and release OpenKP, a large scale open domain keyphrase extraction dataset with near one hundred thousand web documents and expert keyphrase annotations. To handle the variations of domain and content quality, we develop BLING-KPE, a neural keyphrase extraction model that goes beyond language understanding using visual presentations of documents and weak supervision from search queries. Experimental results on OpenKP confirm the effectiveness of B","authors_text":"Arnold Overwijk, Chenyan Xiong, Chuan Hu, Daniel Campos, Lee Xiong","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-06T23:12:56Z","title":"Open Domain Web Keyphrase Extraction Beyond Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.02671","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:ea45deb27fa0c44b51971ba1b9f3b9794025e13fab5127ad887c7f45598cab61","target":"record","created_at":"2026-07-05T00:17:40Z","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":"ce5632d00cff4da4665798cbaa10c801f8c0ecdece371428212801557413ec91","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-06T23:12:56Z","title_canon_sha256":"1ecbd73bf888a4e773547c4b20b82c1634bcbb41552232cabae4c53d3e0bf45b"},"schema_version":"1.0","source":{"id":"1911.02671","kind":"arxiv","version":1}},"canonical_sha256":"a965642fdede2e6655862f598474405139ebe50a679f53a64067db2c7497ad6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a965642fdede2e6655862f598474405139ebe50a679f53a64067db2c7497ad6b","first_computed_at":"2026-07-05T00:17:40.287400Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:17:40.287400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GzpdnToxh27Cg6QyjNKsHB4gJq5h6I42Bsa3Obvqc2NcCvpBF+MmLO/XZCKrFM6y35Nq6O830lWXI1c/KjCtCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:17:40.287899Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.02671","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea45deb27fa0c44b51971ba1b9f3b9794025e13fab5127ad887c7f45598cab61","sha256:5bc190f8de5f2dcffcf8a0d63cf36546d03f6e82cbe472f0e469b7a350b914c9"],"state_sha256":"4ac78c2ecc791023d3aca8293eaf6da8dd65157fe049b7b69f8185e1fda4612f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YXzU2ei8uDSwyGn1OMVm2h4O7hw9OBKJOlj/i0tDnAF3gwJmcbBAPBCOFKpve2DtSranQGVeaoUi+YJ2b74vDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T13:22:52.086680Z","bundle_sha256":"072e854c7564471457ec196c15f0946a01afe4c7b076c3973ca820556227c90f"}}