{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DQ5LY2ERDHU4BLSEBSGO3NC64T","short_pith_number":"pith:DQ5LY2ER","canonical_record":{"source":{"id":"1804.04635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-04-12T17:19:36Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"ad8540cdca0281a116126c204624dfdc584787d212ecfaf892fe36370c2689ea","abstract_canon_sha256":"fb7e66b5eeb458a281bc02b577bb49283845285c2129eb9a8c568b6bc2089ef3"},"schema_version":"1.0"},"canonical_sha256":"1c3abc689119e9c0ae440c8cedb45ee4c6050a980c5519e3acec158f829b1507","source":{"kind":"arxiv","id":"1804.04635","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.04635","created_at":"2026-05-18T00:18:36Z"},{"alias_kind":"arxiv_version","alias_value":"1804.04635v1","created_at":"2026-05-18T00:18:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.04635","created_at":"2026-05-18T00:18:36Z"},{"alias_kind":"pith_short_12","alias_value":"DQ5LY2ERDHU4","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DQ5LY2ERDHU4BLSE","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DQ5LY2ER","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DQ5LY2ERDHU4BLSEBSGO3NC64T","target":"record","payload":{"canonical_record":{"source":{"id":"1804.04635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-04-12T17:19:36Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"ad8540cdca0281a116126c204624dfdc584787d212ecfaf892fe36370c2689ea","abstract_canon_sha256":"fb7e66b5eeb458a281bc02b577bb49283845285c2129eb9a8c568b6bc2089ef3"},"schema_version":"1.0"},"canonical_sha256":"1c3abc689119e9c0ae440c8cedb45ee4c6050a980c5519e3acec158f829b1507","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:36.661267Z","signature_b64":"4+BJxg3fppHKcr4wRGTLCSikPByZcnFA9xOrvakq/C0K1lHTy/LdO2eH6ZBjplWnmO0kKxooSKIZXdVoDkRvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c3abc689119e9c0ae440c8cedb45ee4c6050a980c5519e3acec158f829b1507","last_reissued_at":"2026-05-18T00:18:36.660661Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:36.660661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.04635","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":"2026-05-18T00:18:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LOA8zw8hnSVgQuHdXWhv7MsB8CfrQaNN9o1XhkP4ZhHfGYNVSXVCg2qypREnthp/RBMOYTBPhuqKE3ZD4F+4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T12:14:01.232992Z"},"content_sha256":"ed6aa9b49ba61f7ac04d8bcdf6e5668c402e439ff8b9e3dd145fe097682acd2a","schema_version":"1.0","event_id":"sha256:ed6aa9b49ba61f7ac04d8bcdf6e5668c402e439ff8b9e3dd145fe097682acd2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DQ5LY2ERDHU4BLSEBSGO3NC64T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CERES: Distantly Supervised Relation Extraction from the Semi-Structured Web","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Arash Einolghozati, Colin Lockard, Prashant Shiralkar, Xin Luna Dong","submitted_at":"2018-04-12T17:19:36Z","abstract_excerpt":"The web contains countless semi-structured websites, which can be a rich source of information for populating knowledge bases. Existing methods for extracting relations from the DOM trees of semi-structured webpages can achieve high precision and recall only when manual annotations for each website are available. Although there have been efforts to learn extractors from automatically-generated labels, these methods are not sufficiently robust to succeed in settings with complex schemas and information-rich websites.\n  In this paper we present a new method for automatic extraction from semi-str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.04635","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":""},"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":"2026-05-18T00:18:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fp0t679u32YhCw0XUtodX4UMxS0NHP5mzp6VmL6EUXl9T+lKyVm5pcdyKRfciM9evwhx1YaiomH88fB656vPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T12:14:01.233357Z"},"content_sha256":"eebccae4f576a18c5c2dfcf8005033cda2b87c13edb26dd07761af5bcd009cbd","schema_version":"1.0","event_id":"sha256:eebccae4f576a18c5c2dfcf8005033cda2b87c13edb26dd07761af5bcd009cbd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DQ5LY2ERDHU4BLSEBSGO3NC64T/bundle.json","state_url":"https://pith.science/pith/DQ5LY2ERDHU4BLSEBSGO3NC64T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DQ5LY2ERDHU4BLSEBSGO3NC64T/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":"2026-06-09T12:14:01Z","links":{"resolver":"https://pith.science/pith/DQ5LY2ERDHU4BLSEBSGO3NC64T","bundle":"https://pith.science/pith/DQ5LY2ERDHU4BLSEBSGO3NC64T/bundle.json","state":"https://pith.science/pith/DQ5LY2ERDHU4BLSEBSGO3NC64T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DQ5LY2ERDHU4BLSEBSGO3NC64T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DQ5LY2ERDHU4BLSEBSGO3NC64T","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":"fb7e66b5eeb458a281bc02b577bb49283845285c2129eb9a8c568b6bc2089ef3","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-04-12T17:19:36Z","title_canon_sha256":"ad8540cdca0281a116126c204624dfdc584787d212ecfaf892fe36370c2689ea"},"schema_version":"1.0","source":{"id":"1804.04635","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.04635","created_at":"2026-05-18T00:18:36Z"},{"alias_kind":"arxiv_version","alias_value":"1804.04635v1","created_at":"2026-05-18T00:18:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.04635","created_at":"2026-05-18T00:18:36Z"},{"alias_kind":"pith_short_12","alias_value":"DQ5LY2ERDHU4","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DQ5LY2ERDHU4BLSE","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DQ5LY2ER","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:eebccae4f576a18c5c2dfcf8005033cda2b87c13edb26dd07761af5bcd009cbd","target":"graph","created_at":"2026-05-18T00:18:36Z","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"},"paper":{"abstract_excerpt":"The web contains countless semi-structured websites, which can be a rich source of information for populating knowledge bases. Existing methods for extracting relations from the DOM trees of semi-structured webpages can achieve high precision and recall only when manual annotations for each website are available. Although there have been efforts to learn extractors from automatically-generated labels, these methods are not sufficiently robust to succeed in settings with complex schemas and information-rich websites.\n  In this paper we present a new method for automatic extraction from semi-str","authors_text":"Arash Einolghozati, Colin Lockard, Prashant Shiralkar, Xin Luna Dong","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-04-12T17:19:36Z","title":"CERES: Distantly Supervised Relation Extraction from the Semi-Structured Web"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.04635","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:ed6aa9b49ba61f7ac04d8bcdf6e5668c402e439ff8b9e3dd145fe097682acd2a","target":"record","created_at":"2026-05-18T00:18:36Z","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":"fb7e66b5eeb458a281bc02b577bb49283845285c2129eb9a8c568b6bc2089ef3","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-04-12T17:19:36Z","title_canon_sha256":"ad8540cdca0281a116126c204624dfdc584787d212ecfaf892fe36370c2689ea"},"schema_version":"1.0","source":{"id":"1804.04635","kind":"arxiv","version":1}},"canonical_sha256":"1c3abc689119e9c0ae440c8cedb45ee4c6050a980c5519e3acec158f829b1507","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c3abc689119e9c0ae440c8cedb45ee4c6050a980c5519e3acec158f829b1507","first_computed_at":"2026-05-18T00:18:36.660661Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:36.660661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4+BJxg3fppHKcr4wRGTLCSikPByZcnFA9xOrvakq/C0K1lHTy/LdO2eH6ZBjplWnmO0kKxooSKIZXdVoDkRvDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:36.661267Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.04635","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed6aa9b49ba61f7ac04d8bcdf6e5668c402e439ff8b9e3dd145fe097682acd2a","sha256:eebccae4f576a18c5c2dfcf8005033cda2b87c13edb26dd07761af5bcd009cbd"],"state_sha256":"550a1ef021f2ed5a2d03f0b039247687fa5e989c9350b0d0757d6a5a0c0c6cdc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3eYTo4obmX4FjF3cz+5mofbFDreADBFtcG+SsRRhFxdWFfPCZtIjtA6z+hD+BFraLGIhrD4RcRQ2rR3DynCgDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T12:14:01.235344Z","bundle_sha256":"a084b9556a77ee1c5c58f1ee1782c1e484a8d058acad53dfa68cf8f10d5a0203"}}