{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CJ63KDV7Q2YXDHYCK4YVBCTC7M","short_pith_number":"pith:CJ63KDV7","canonical_record":{"source":{"id":"2204.05021","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-04-11T11:40:22Z","cross_cats_sorted":["cs.IR","cs.PL"],"title_canon_sha256":"d45907c0dfc455a786e070bfe4a7cc5a99ef987443ac555d2aa015fe1195b477","abstract_canon_sha256":"ff97b7308a36505cbdc21680524030439e7b126298222283aaf871974ea864de"},"schema_version":"1.0"},"canonical_sha256":"127db50ebf86b1719f025731508a62fb0e05eaeadeed17b888e617777c9dd3eb","source":{"kind":"arxiv","id":"2204.05021","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.05021","created_at":"2026-07-05T04:13:16Z"},{"alias_kind":"arxiv_version","alias_value":"2204.05021v1","created_at":"2026-07-05T04:13:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05021","created_at":"2026-07-05T04:13:16Z"},{"alias_kind":"pith_short_12","alias_value":"CJ63KDV7Q2YX","created_at":"2026-07-05T04:13:16Z"},{"alias_kind":"pith_short_16","alias_value":"CJ63KDV7Q2YXDHYC","created_at":"2026-07-05T04:13:16Z"},{"alias_kind":"pith_short_8","alias_value":"CJ63KDV7","created_at":"2026-07-05T04:13:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CJ63KDV7Q2YXDHYCK4YVBCTC7M","target":"record","payload":{"canonical_record":{"source":{"id":"2204.05021","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-04-11T11:40:22Z","cross_cats_sorted":["cs.IR","cs.PL"],"title_canon_sha256":"d45907c0dfc455a786e070bfe4a7cc5a99ef987443ac555d2aa015fe1195b477","abstract_canon_sha256":"ff97b7308a36505cbdc21680524030439e7b126298222283aaf871974ea864de"},"schema_version":"1.0"},"canonical_sha256":"127db50ebf86b1719f025731508a62fb0e05eaeadeed17b888e617777c9dd3eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:16.675617Z","signature_b64":"3w+PF25xKzJRMYSRIz1jxUVLUYfIUh1TOnKj7TkI2uo2qmQWjV9b+OtbydOP/rapyq6dOIFqFrZoIdYYMWGUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"127db50ebf86b1719f025731508a62fb0e05eaeadeed17b888e617777c9dd3eb","last_reissued_at":"2026-07-05T04:13:16.675199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:16.675199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.05021","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":"2026-07-05T04:13:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gALn/oA2HeefFT0bjziN89SFQ3YeZ3D4J4IAidoELn1jm/IIXA8V/Ckl0PGYBrOHTalGjxm4A1DD00tGeZJBAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T13:25:43.151374Z"},"content_sha256":"56af61e9b95e4b89d01f3a0663869c0704a79965c865501ff93f01fc177be7b6","schema_version":"1.0","event_id":"sha256:56af61e9b95e4b89d01f3a0663869c0704a79965c865501ff93f01fc177be7b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CJ63KDV7Q2YXDHYCK4YVBCTC7M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Landmarks and Regions: A Robust Approach to Data Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.PL"],"primary_cat":"cs.SE","authors_text":"Anirudh Khatry, Arjun Radhakrishna, Arun Iyer, Lincy Pattanaik, Mohammad Raza, Sriram Rajamani, Suresh Parthasarathy","submitted_at":"2022-04-11T11:40:22Z","abstract_excerpt":"We propose a new approach to extracting data items or field values from semi-structured documents. Examples of such problems include extracting passenger name, departure time and departure airport from a travel itinerary, or extracting price of an item from a purchase receipt. Traditional approaches to data extraction use machine learning or program synthesis to process the whole document to extract the desired fields. Such approaches are not robust to format changes in the document, and the extraction process typically fails even if changes are made to parts of the document that are unrelated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05021","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/2204.05021/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":"2026-07-05T04:13:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ToAY73bLF0oFh23ztAHUBp/lUwVZ8ckpseRtRvdC3WFVmlq1GdOhslYA/cbdnGbaUQ0f12UMCQoCehBT6LLfCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T13:25:43.151739Z"},"content_sha256":"e3ca6820221b0cdb6d9cab45b20e65c7d79e1bfdf9ddf0309193fa616a4c1281","schema_version":"1.0","event_id":"sha256:e3ca6820221b0cdb6d9cab45b20e65c7d79e1bfdf9ddf0309193fa616a4c1281"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CJ63KDV7Q2YXDHYCK4YVBCTC7M/bundle.json","state_url":"https://pith.science/pith/CJ63KDV7Q2YXDHYCK4YVBCTC7M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CJ63KDV7Q2YXDHYCK4YVBCTC7M/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":"2026-07-24T13:25:43Z","links":{"resolver":"https://pith.science/pith/CJ63KDV7Q2YXDHYCK4YVBCTC7M","bundle":"https://pith.science/pith/CJ63KDV7Q2YXDHYCK4YVBCTC7M/bundle.json","state":"https://pith.science/pith/CJ63KDV7Q2YXDHYCK4YVBCTC7M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CJ63KDV7Q2YXDHYCK4YVBCTC7M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CJ63KDV7Q2YXDHYCK4YVBCTC7M","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":"ff97b7308a36505cbdc21680524030439e7b126298222283aaf871974ea864de","cross_cats_sorted":["cs.IR","cs.PL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-04-11T11:40:22Z","title_canon_sha256":"d45907c0dfc455a786e070bfe4a7cc5a99ef987443ac555d2aa015fe1195b477"},"schema_version":"1.0","source":{"id":"2204.05021","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.05021","created_at":"2026-07-05T04:13:16Z"},{"alias_kind":"arxiv_version","alias_value":"2204.05021v1","created_at":"2026-07-05T04:13:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05021","created_at":"2026-07-05T04:13:16Z"},{"alias_kind":"pith_short_12","alias_value":"CJ63KDV7Q2YX","created_at":"2026-07-05T04:13:16Z"},{"alias_kind":"pith_short_16","alias_value":"CJ63KDV7Q2YXDHYC","created_at":"2026-07-05T04:13:16Z"},{"alias_kind":"pith_short_8","alias_value":"CJ63KDV7","created_at":"2026-07-05T04:13:16Z"}],"graph_snapshots":[{"event_id":"sha256:e3ca6820221b0cdb6d9cab45b20e65c7d79e1bfdf9ddf0309193fa616a4c1281","target":"graph","created_at":"2026-07-05T04:13:16Z","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/2204.05021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a new approach to extracting data items or field values from semi-structured documents. Examples of such problems include extracting passenger name, departure time and departure airport from a travel itinerary, or extracting price of an item from a purchase receipt. Traditional approaches to data extraction use machine learning or program synthesis to process the whole document to extract the desired fields. Such approaches are not robust to format changes in the document, and the extraction process typically fails even if changes are made to parts of the document that are unrelated","authors_text":"Anirudh Khatry, Arjun Radhakrishna, Arun Iyer, Lincy Pattanaik, Mohammad Raza, Sriram Rajamani, Suresh Parthasarathy","cross_cats":["cs.IR","cs.PL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-04-11T11:40:22Z","title":"Landmarks and Regions: A Robust Approach to Data Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05021","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":"sha256:56af61e9b95e4b89d01f3a0663869c0704a79965c865501ff93f01fc177be7b6","target":"record","created_at":"2026-07-05T04:13:16Z","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":"ff97b7308a36505cbdc21680524030439e7b126298222283aaf871974ea864de","cross_cats_sorted":["cs.IR","cs.PL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-04-11T11:40:22Z","title_canon_sha256":"d45907c0dfc455a786e070bfe4a7cc5a99ef987443ac555d2aa015fe1195b477"},"schema_version":"1.0","source":{"id":"2204.05021","kind":"arxiv","version":1}},"canonical_sha256":"127db50ebf86b1719f025731508a62fb0e05eaeadeed17b888e617777c9dd3eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"127db50ebf86b1719f025731508a62fb0e05eaeadeed17b888e617777c9dd3eb","first_computed_at":"2026-07-05T04:13:16.675199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:13:16.675199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3w+PF25xKzJRMYSRIz1jxUVLUYfIUh1TOnKj7TkI2uo2qmQWjV9b+OtbydOP/rapyq6dOIFqFrZoIdYYMWGUAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:13:16.675617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.05021","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56af61e9b95e4b89d01f3a0663869c0704a79965c865501ff93f01fc177be7b6","sha256:e3ca6820221b0cdb6d9cab45b20e65c7d79e1bfdf9ddf0309193fa616a4c1281"],"state_sha256":"f6d6357ac57cacd7d6890684231ec291e61a73b6d8887c97a078b3eef7c9f3b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+4ZlsnPxAopLyUlMy14SmSiq4vkpbCKQXiDHLhjO488aSymWdZ9vBvrvvynFDjL3klbyy09LDkj075BfqO88AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T13:25:43.153802Z","bundle_sha256":"008e0f8769a5a766b4371bef57e8c94820ec7c5e256e0bb55f4c10ac9f1d23a0"}}