{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DR66YTSO5VEJDFPGIUHBQA5JRX","short_pith_number":"pith:DR66YTSO","canonical_record":{"source":{"id":"2106.03399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-06-07T08:01:03Z","cross_cats_sorted":[],"title_canon_sha256":"2c0fc692f4abae29fad9c6849182c9a89b2c3817f4889bfb40d1ddd19d2a633b","abstract_canon_sha256":"9e86b468d898bd98ed670f5a655cda14acfbdb883cdcea27418ece0df3990a48"},"schema_version":"1.0"},"canonical_sha256":"1c7dec4e4eed489195e6450e1803a98dd5f0c1cb2a4beebcd6e93ee26064cee6","source":{"kind":"arxiv","id":"2106.03399","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03399","created_at":"2026-07-05T02:46:49Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03399v1","created_at":"2026-07-05T02:46:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03399","created_at":"2026-07-05T02:46:49Z"},{"alias_kind":"pith_short_12","alias_value":"DR66YTSO5VEJ","created_at":"2026-07-05T02:46:49Z"},{"alias_kind":"pith_short_16","alias_value":"DR66YTSO5VEJDFPG","created_at":"2026-07-05T02:46:49Z"},{"alias_kind":"pith_short_8","alias_value":"DR66YTSO","created_at":"2026-07-05T02:46:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DR66YTSO5VEJDFPGIUHBQA5JRX","target":"record","payload":{"canonical_record":{"source":{"id":"2106.03399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-06-07T08:01:03Z","cross_cats_sorted":[],"title_canon_sha256":"2c0fc692f4abae29fad9c6849182c9a89b2c3817f4889bfb40d1ddd19d2a633b","abstract_canon_sha256":"9e86b468d898bd98ed670f5a655cda14acfbdb883cdcea27418ece0df3990a48"},"schema_version":"1.0"},"canonical_sha256":"1c7dec4e4eed489195e6450e1803a98dd5f0c1cb2a4beebcd6e93ee26064cee6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:49.144981Z","signature_b64":"FqAhSNEbDj9DOWLE7GERaEINIzHCLPD9nCtt6cBY9TMGJ+jMpQFhAjiRKoARKc1NVKsSaBn4IeMMcfcoPI4HCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c7dec4e4eed489195e6450e1803a98dd5f0c1cb2a4beebcd6e93ee26064cee6","last_reissued_at":"2026-07-05T02:46:49.144637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:49.144637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.03399","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":"2026-07-05T02:46:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lzUIqaLXljNMw/Yin54mbAPKCMIrKZMkOySE65XR3HnargEdV9YyNPyeXbSwPeoyfJwDVMx0tc/m7UCero3WDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:27:13.468851Z"},"content_sha256":"71f843660632fe9859956dd4eb314359d50425fccd2ce82e232f45caf123f57f","schema_version":"1.0","event_id":"sha256:71f843660632fe9859956dd4eb314359d50425fccd2ce82e232f45caf123f57f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DR66YTSO5VEJDFPGIUHBQA5JRX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scientific Dataset Discovery via Topic-level Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Basmah Altaf, Shichao Pei, Xiangliang Zhang","submitted_at":"2021-06-07T08:01:03Z","abstract_excerpt":"Data intensive research requires the support of appropriate datasets. However, it is often time-consuming to discover usable datasets matching a specific research topic. We formulate the dataset discovery problem on an attributed heterogeneous graph, which is composed of paper-paper citation, paper-dataset citation, and also paper content. We propose to characterize both paper and dataset nodes by their commonly shared latent topics, rather than learning user and item representations via canonical graph embedding models, because the usage of datasets and the themes of research projects can be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03399","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/2106.03399/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":"2026-07-05T02:46:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IKfuBROUYjVxGas+e/dwDJxhwcX3L6iy7b5FTfXAqI0anqNnwlfoGghwK//WBFUpraWYT9vjACwlZySyjTOsAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:27:13.469424Z"},"content_sha256":"35ac7fb4b3d87f28acabbc73f7e876229f7e53d0ba1ac43819d7c95feb6097bf","schema_version":"1.0","event_id":"sha256:35ac7fb4b3d87f28acabbc73f7e876229f7e53d0ba1ac43819d7c95feb6097bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DR66YTSO5VEJDFPGIUHBQA5JRX/bundle.json","state_url":"https://pith.science/pith/DR66YTSO5VEJDFPGIUHBQA5JRX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DR66YTSO5VEJDFPGIUHBQA5JRX/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":"2026-08-11T21:27:13Z","links":{"resolver":"https://pith.science/pith/DR66YTSO5VEJDFPGIUHBQA5JRX","bundle":"https://pith.science/pith/DR66YTSO5VEJDFPGIUHBQA5JRX/bundle.json","state":"https://pith.science/pith/DR66YTSO5VEJDFPGIUHBQA5JRX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DR66YTSO5VEJDFPGIUHBQA5JRX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DR66YTSO5VEJDFPGIUHBQA5JRX","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":"9e86b468d898bd98ed670f5a655cda14acfbdb883cdcea27418ece0df3990a48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-06-07T08:01:03Z","title_canon_sha256":"2c0fc692f4abae29fad9c6849182c9a89b2c3817f4889bfb40d1ddd19d2a633b"},"schema_version":"1.0","source":{"id":"2106.03399","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03399","created_at":"2026-07-05T02:46:49Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03399v1","created_at":"2026-07-05T02:46:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03399","created_at":"2026-07-05T02:46:49Z"},{"alias_kind":"pith_short_12","alias_value":"DR66YTSO5VEJ","created_at":"2026-07-05T02:46:49Z"},{"alias_kind":"pith_short_16","alias_value":"DR66YTSO5VEJDFPG","created_at":"2026-07-05T02:46:49Z"},{"alias_kind":"pith_short_8","alias_value":"DR66YTSO","created_at":"2026-07-05T02:46:49Z"}],"graph_snapshots":[{"event_id":"sha256:35ac7fb4b3d87f28acabbc73f7e876229f7e53d0ba1ac43819d7c95feb6097bf","target":"graph","created_at":"2026-07-05T02:46:49Z","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/2106.03399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data intensive research requires the support of appropriate datasets. However, it is often time-consuming to discover usable datasets matching a specific research topic. We formulate the dataset discovery problem on an attributed heterogeneous graph, which is composed of paper-paper citation, paper-dataset citation, and also paper content. We propose to characterize both paper and dataset nodes by their commonly shared latent topics, rather than learning user and item representations via canonical graph embedding models, because the usage of datasets and the themes of research projects can be ","authors_text":"Basmah Altaf, Shichao Pei, Xiangliang Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-06-07T08:01:03Z","title":"Scientific Dataset Discovery via Topic-level Recommendation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03399","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":"sha256:71f843660632fe9859956dd4eb314359d50425fccd2ce82e232f45caf123f57f","target":"record","created_at":"2026-07-05T02:46:49Z","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":"9e86b468d898bd98ed670f5a655cda14acfbdb883cdcea27418ece0df3990a48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-06-07T08:01:03Z","title_canon_sha256":"2c0fc692f4abae29fad9c6849182c9a89b2c3817f4889bfb40d1ddd19d2a633b"},"schema_version":"1.0","source":{"id":"2106.03399","kind":"arxiv","version":1}},"canonical_sha256":"1c7dec4e4eed489195e6450e1803a98dd5f0c1cb2a4beebcd6e93ee26064cee6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c7dec4e4eed489195e6450e1803a98dd5f0c1cb2a4beebcd6e93ee26064cee6","first_computed_at":"2026-07-05T02:46:49.144637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:49.144637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FqAhSNEbDj9DOWLE7GERaEINIzHCLPD9nCtt6cBY9TMGJ+jMpQFhAjiRKoARKc1NVKsSaBn4IeMMcfcoPI4HCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:49.144981Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.03399","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71f843660632fe9859956dd4eb314359d50425fccd2ce82e232f45caf123f57f","sha256:35ac7fb4b3d87f28acabbc73f7e876229f7e53d0ba1ac43819d7c95feb6097bf"],"state_sha256":"4d797b4e959c5d7d303db322e977eb8e9a78d90cb929d8db2962dca7bc0ffada"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8bWXV3+N8iy+YUOOX9UVtmrBTA72eH7XpUwIkzdgkM0ku/N4F9MzLk6hKJEoealE1Ex6OIxocpo8hWp7WuwCDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T21:27:13.472957Z","bundle_sha256":"c91a896875d624b443cf9f76706bb8885bf3037f317992d75859caa6dfa9f351"}}