{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QYBYCGDN6X5SOVZWNI3D36M6O3","short_pith_number":"pith:QYBYCGDN","canonical_record":{"source":{"id":"2203.15349","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-29T08:44:57Z","cross_cats_sorted":[],"title_canon_sha256":"b8c6136e7b7cfe84d4fddda6514c4ad62ce56ce844583174e25e6a394b9705d0","abstract_canon_sha256":"820da13eec221a81b5384261ed4ae8d6ffc53b19c6e0dbebf4baa6ee54bdccfb"},"schema_version":"1.0"},"canonical_sha256":"860381186df5fb2757366a363df99e76ff65159ed4ccf8fdfc64c123c2a22664","source":{"kind":"arxiv","id":"2203.15349","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.15349","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"arxiv_version","alias_value":"2203.15349v2","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15349","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"pith_short_12","alias_value":"QYBYCGDN6X5S","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"pith_short_16","alias_value":"QYBYCGDN6X5SOVZW","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"pith_short_8","alias_value":"QYBYCGDN","created_at":"2026-07-05T04:10:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QYBYCGDN6X5SOVZWNI3D36M6O3","target":"record","payload":{"canonical_record":{"source":{"id":"2203.15349","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-29T08:44:57Z","cross_cats_sorted":[],"title_canon_sha256":"b8c6136e7b7cfe84d4fddda6514c4ad62ce56ce844583174e25e6a394b9705d0","abstract_canon_sha256":"820da13eec221a81b5384261ed4ae8d6ffc53b19c6e0dbebf4baa6ee54bdccfb"},"schema_version":"1.0"},"canonical_sha256":"860381186df5fb2757366a363df99e76ff65159ed4ccf8fdfc64c123c2a22664","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:40.881992Z","signature_b64":"UZ5M5gro/WN5V4v4O29msvN5XogQ+NJRgy5BCarKQRF524S4/Z4AoeUEXyALbCFw/+lClOMhlCq/nenirtuyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"860381186df5fb2757366a363df99e76ff65159ed4ccf8fdfc64c123c2a22664","last_reissued_at":"2026-07-05T04:10:40.881531Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:40.881531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.15349","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:10:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7NIUkwoob54Il07cTI/jJRBlPO2UEfUhRw1xp2l3diZnBh4i+ZKnIytctXiTjBONrhq9G5Z3nfiPTLON02sVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:31:17.955355Z"},"content_sha256":"5b1ddf955bf91d569db1e8d826714a087cb534a53d91f27d3712397fe6c0a7f7","schema_version":"1.0","event_id":"sha256:5b1ddf955bf91d569db1e8d826714a087cb534a53d91f27d3712397fe6c0a7f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QYBYCGDN6X5SOVZWNI3D36M6O3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LDKP: A Dataset for Identifying Keyphrases from Long Scientific Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amardeep Kumar, Anish Acharya, Debanjan Mahata, Dibya Gautam, Navneet Agarwal, Rajiv Ratn Shah, Swapnil Parekh, Yaman Kumar Singla","submitted_at":"2022-03-29T08:44:57Z","abstract_excerpt":"Identifying keyphrases (KPs) from text documents is a fundamental task in natural language processing and information retrieval. Vast majority of the benchmark datasets for this task are from the scientific domain containing only the document title and abstract information. This limits keyphrase extraction (KPE) and keyphrase generation (KPG) algorithms to identify keyphrases from human-written summaries that are often very short (approx 8 sentences). This presents three challenges for real-world applications: human-written summaries are unavailable for most documents, the documents are almost"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15349","kind":"arxiv","version":2},"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/2203.15349/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":"2026-07-05T04:10:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6+cBmnLFi74vTotGVVW/5kBqasni95uZFi5Y1GVpZJ1AWyPPRg49QdBzin/wMVqxU/Jk2djSCpiyf9rVKT1WAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:31:17.956131Z"},"content_sha256":"e558ce9c5cb58eb05b4a99263e81625d96315ae7769ffbab96e69fb89c114d1d","schema_version":"1.0","event_id":"sha256:e558ce9c5cb58eb05b4a99263e81625d96315ae7769ffbab96e69fb89c114d1d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QYBYCGDN6X5SOVZWNI3D36M6O3/bundle.json","state_url":"https://pith.science/pith/QYBYCGDN6X5SOVZWNI3D36M6O3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QYBYCGDN6X5SOVZWNI3D36M6O3/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":"2026-08-10T00:31:17Z","links":{"resolver":"https://pith.science/pith/QYBYCGDN6X5SOVZWNI3D36M6O3","bundle":"https://pith.science/pith/QYBYCGDN6X5SOVZWNI3D36M6O3/bundle.json","state":"https://pith.science/pith/QYBYCGDN6X5SOVZWNI3D36M6O3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QYBYCGDN6X5SOVZWNI3D36M6O3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QYBYCGDN6X5SOVZWNI3D36M6O3","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":"820da13eec221a81b5384261ed4ae8d6ffc53b19c6e0dbebf4baa6ee54bdccfb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-29T08:44:57Z","title_canon_sha256":"b8c6136e7b7cfe84d4fddda6514c4ad62ce56ce844583174e25e6a394b9705d0"},"schema_version":"1.0","source":{"id":"2203.15349","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.15349","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"arxiv_version","alias_value":"2203.15349v2","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15349","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"pith_short_12","alias_value":"QYBYCGDN6X5S","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"pith_short_16","alias_value":"QYBYCGDN6X5SOVZW","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"pith_short_8","alias_value":"QYBYCGDN","created_at":"2026-07-05T04:10:40Z"}],"graph_snapshots":[{"event_id":"sha256:e558ce9c5cb58eb05b4a99263e81625d96315ae7769ffbab96e69fb89c114d1d","target":"graph","created_at":"2026-07-05T04:10:40Z","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/2203.15349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Identifying keyphrases (KPs) from text documents is a fundamental task in natural language processing and information retrieval. Vast majority of the benchmark datasets for this task are from the scientific domain containing only the document title and abstract information. This limits keyphrase extraction (KPE) and keyphrase generation (KPG) algorithms to identify keyphrases from human-written summaries that are often very short (approx 8 sentences). This presents three challenges for real-world applications: human-written summaries are unavailable for most documents, the documents are almost","authors_text":"Amardeep Kumar, Anish Acharya, Debanjan Mahata, Dibya Gautam, Navneet Agarwal, Rajiv Ratn Shah, Swapnil Parekh, Yaman Kumar Singla","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-29T08:44:57Z","title":"LDKP: A Dataset for Identifying Keyphrases from Long Scientific Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15349","kind":"arxiv","version":2},"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":"sha256:5b1ddf955bf91d569db1e8d826714a087cb534a53d91f27d3712397fe6c0a7f7","target":"record","created_at":"2026-07-05T04:10:40Z","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":"820da13eec221a81b5384261ed4ae8d6ffc53b19c6e0dbebf4baa6ee54bdccfb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-29T08:44:57Z","title_canon_sha256":"b8c6136e7b7cfe84d4fddda6514c4ad62ce56ce844583174e25e6a394b9705d0"},"schema_version":"1.0","source":{"id":"2203.15349","kind":"arxiv","version":2}},"canonical_sha256":"860381186df5fb2757366a363df99e76ff65159ed4ccf8fdfc64c123c2a22664","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"860381186df5fb2757366a363df99e76ff65159ed4ccf8fdfc64c123c2a22664","first_computed_at":"2026-07-05T04:10:40.881531Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:40.881531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UZ5M5gro/WN5V4v4O29msvN5XogQ+NJRgy5BCarKQRF524S4/Z4AoeUEXyALbCFw/+lClOMhlCq/nenirtuyBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:40.881992Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.15349","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b1ddf955bf91d569db1e8d826714a087cb534a53d91f27d3712397fe6c0a7f7","sha256:e558ce9c5cb58eb05b4a99263e81625d96315ae7769ffbab96e69fb89c114d1d"],"state_sha256":"ba2a5356b4057547084817300d9a34cf55f413e9e4f36275f4e1439bfcc9e948"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fs+tVCPPABC7/4D3iGL+xG8K9QKmVKDwE4pQ/iSeBeRH9Gi/fBEx3H3pEc/2APJbHOfwRX2rUTNTk7yfrupuDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:31:17.962157Z","bundle_sha256":"d83c9948eabb2f2a7f6869819a97d5f9d04197be3cac50044bd0eee00a1ce512"}}