{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ARS2ZHRXB3UJNYSHTIZ4VD73YF","short_pith_number":"pith:ARS2ZHRX","canonical_record":{"source":{"id":"2104.07162","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2021-04-14T23:23:33Z","cross_cats_sorted":[],"title_canon_sha256":"3e707a9d8fb8ce873477a38cdba849f6d94f9ad512144d1d46dccf8c6e50896a","abstract_canon_sha256":"2cadd39e9713ce5e8084793f04f44a7e834bef54f0770e578f46668fc41ab8ad"},"schema_version":"1.0"},"canonical_sha256":"0465ac9e370ee896e2479a33ca8ffbc1738a05311603c7db2a15862176e9bf96","source":{"kind":"arxiv","id":"2104.07162","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.07162","created_at":"2026-07-05T02:32:18Z"},{"alias_kind":"arxiv_version","alias_value":"2104.07162v1","created_at":"2026-07-05T02:32:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07162","created_at":"2026-07-05T02:32:18Z"},{"alias_kind":"pith_short_12","alias_value":"ARS2ZHRXB3UJ","created_at":"2026-07-05T02:32:18Z"},{"alias_kind":"pith_short_16","alias_value":"ARS2ZHRXB3UJNYSH","created_at":"2026-07-05T02:32:18Z"},{"alias_kind":"pith_short_8","alias_value":"ARS2ZHRX","created_at":"2026-07-05T02:32:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ARS2ZHRXB3UJNYSHTIZ4VD73YF","target":"record","payload":{"canonical_record":{"source":{"id":"2104.07162","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2021-04-14T23:23:33Z","cross_cats_sorted":[],"title_canon_sha256":"3e707a9d8fb8ce873477a38cdba849f6d94f9ad512144d1d46dccf8c6e50896a","abstract_canon_sha256":"2cadd39e9713ce5e8084793f04f44a7e834bef54f0770e578f46668fc41ab8ad"},"schema_version":"1.0"},"canonical_sha256":"0465ac9e370ee896e2479a33ca8ffbc1738a05311603c7db2a15862176e9bf96","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:18.506900Z","signature_b64":"VlcaBs1XPQFtTJdnyhbLAIq6+mbab46gvOQF1Fw0ouGyZJTy+1Q1MSeeuQow3IccwhsUmkZnQVD783qk85CSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0465ac9e370ee896e2479a33ca8ffbc1738a05311603c7db2a15862176e9bf96","last_reissued_at":"2026-07-05T02:32:18.506436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:18.506436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.07162","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":"2026-07-05T02:32:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L+s5JFmWzzv24tDE6ImrfU4wGTWLS8BzzXfhNHr+dFnsUvl8vAW7BlZ593VUabmeZiIKNxLYvkXL9eSU8Ga8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:47:49.622969Z"},"content_sha256":"5895b7542947dba92a788b4bdde14ea4b4bd935d71a98c396638cbc4b4d9be3b","schema_version":"1.0","event_id":"sha256:5895b7542947dba92a788b4bdde14ea4b4bd935d71a98c396638cbc4b4d9be3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ARS2ZHRXB3UJNYSHTIZ4VD73YF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Web Question Answering with Neurosymbolic Program Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.PL","authors_text":"Aaron Lamoreaux, Greg Durrett, Isil Dillig, Osbert Bastani, Qiaochu Chen, Xinyu Wang","submitted_at":"2021-04-14T23:23:33Z","abstract_excerpt":"In this paper, we propose a new technique based on program synthesis for extracting information from webpages. Given a natural language query and a few labeled webpages, our method synthesizes a program that can be used to extract similar types of information from other unlabeled webpages. To handle websites with diverse structure, our approach employs a neurosymbolic DSL that incorporates both neural NLP models as well as standard language constructs for tree navigation and string manipulation. We also propose an optimal synthesis algorithm that generates all DSL programs that achieve optimal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07162","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/2104.07162/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":"2026-07-05T02:32:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EHV9Ubf1tBLGsSyPVK8vIS2OhocM5k+psKwyhetM+6PZjT74Qniuebr144tunza0QCzYVj9Sy+CSyFbifTdRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:47:49.623361Z"},"content_sha256":"8e21a30b166f072dfc26b565fd79678132dc6bc7cfe2011a468b647e917ae9f0","schema_version":"1.0","event_id":"sha256:8e21a30b166f072dfc26b565fd79678132dc6bc7cfe2011a468b647e917ae9f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ARS2ZHRXB3UJNYSHTIZ4VD73YF/bundle.json","state_url":"https://pith.science/pith/ARS2ZHRXB3UJNYSHTIZ4VD73YF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ARS2ZHRXB3UJNYSHTIZ4VD73YF/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":"2026-07-06T20:47:49Z","links":{"resolver":"https://pith.science/pith/ARS2ZHRXB3UJNYSHTIZ4VD73YF","bundle":"https://pith.science/pith/ARS2ZHRXB3UJNYSHTIZ4VD73YF/bundle.json","state":"https://pith.science/pith/ARS2ZHRXB3UJNYSHTIZ4VD73YF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ARS2ZHRXB3UJNYSHTIZ4VD73YF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ARS2ZHRXB3UJNYSHTIZ4VD73YF","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":"2cadd39e9713ce5e8084793f04f44a7e834bef54f0770e578f46668fc41ab8ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2021-04-14T23:23:33Z","title_canon_sha256":"3e707a9d8fb8ce873477a38cdba849f6d94f9ad512144d1d46dccf8c6e50896a"},"schema_version":"1.0","source":{"id":"2104.07162","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.07162","created_at":"2026-07-05T02:32:18Z"},{"alias_kind":"arxiv_version","alias_value":"2104.07162v1","created_at":"2026-07-05T02:32:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07162","created_at":"2026-07-05T02:32:18Z"},{"alias_kind":"pith_short_12","alias_value":"ARS2ZHRXB3UJ","created_at":"2026-07-05T02:32:18Z"},{"alias_kind":"pith_short_16","alias_value":"ARS2ZHRXB3UJNYSH","created_at":"2026-07-05T02:32:18Z"},{"alias_kind":"pith_short_8","alias_value":"ARS2ZHRX","created_at":"2026-07-05T02:32:18Z"}],"graph_snapshots":[{"event_id":"sha256:8e21a30b166f072dfc26b565fd79678132dc6bc7cfe2011a468b647e917ae9f0","target":"graph","created_at":"2026-07-05T02:32:18Z","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/2104.07162/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a new technique based on program synthesis for extracting information from webpages. Given a natural language query and a few labeled webpages, our method synthesizes a program that can be used to extract similar types of information from other unlabeled webpages. To handle websites with diverse structure, our approach employs a neurosymbolic DSL that incorporates both neural NLP models as well as standard language constructs for tree navigation and string manipulation. We also propose an optimal synthesis algorithm that generates all DSL programs that achieve optimal","authors_text":"Aaron Lamoreaux, Greg Durrett, Isil Dillig, Osbert Bastani, Qiaochu Chen, Xinyu Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2021-04-14T23:23:33Z","title":"Web Question Answering with Neurosymbolic Program Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07162","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":"sha256:5895b7542947dba92a788b4bdde14ea4b4bd935d71a98c396638cbc4b4d9be3b","target":"record","created_at":"2026-07-05T02:32:18Z","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":"2cadd39e9713ce5e8084793f04f44a7e834bef54f0770e578f46668fc41ab8ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2021-04-14T23:23:33Z","title_canon_sha256":"3e707a9d8fb8ce873477a38cdba849f6d94f9ad512144d1d46dccf8c6e50896a"},"schema_version":"1.0","source":{"id":"2104.07162","kind":"arxiv","version":1}},"canonical_sha256":"0465ac9e370ee896e2479a33ca8ffbc1738a05311603c7db2a15862176e9bf96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0465ac9e370ee896e2479a33ca8ffbc1738a05311603c7db2a15862176e9bf96","first_computed_at":"2026-07-05T02:32:18.506436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:18.506436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VlcaBs1XPQFtTJdnyhbLAIq6+mbab46gvOQF1Fw0ouGyZJTy+1Q1MSeeuQow3IccwhsUmkZnQVD783qk85CSAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:18.506900Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.07162","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5895b7542947dba92a788b4bdde14ea4b4bd935d71a98c396638cbc4b4d9be3b","sha256:8e21a30b166f072dfc26b565fd79678132dc6bc7cfe2011a468b647e917ae9f0"],"state_sha256":"11ccd692cb4b49fbdccc7839cb7364c9b681fde16e2c7fb45026511c0de6f480"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1+GD6iurgN7bZPVhHWfk1caWNKYhfUH0LD7UtxlFI6MLu12zUgo+MA7bhJDI41LeZDQO0GlM1E/u9rbZANclDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:47:49.625341Z","bundle_sha256":"a87324eedc8394ea053c467d59af6184db8f7640fe211fcca984ded5a72d51e1"}}