{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5JRNNL5WISIGHXSIPRC6PINGXM","short_pith_number":"pith:5JRNNL5W","canonical_record":{"source":{"id":"2504.12682","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-17T06:16:40Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"43de65f28dd1bcf4d190fc5065f755ae91b14c1414ab629c33b8a7e036e6f570","abstract_canon_sha256":"10b3592b54d26eb62cc8f4996b516a262e04791f40fb61c245ffe3697581b923"},"schema_version":"1.0"},"canonical_sha256":"ea62d6afb6449063de487c45e7a1a6bb32e1bbd3de207849babdb89fb50f47b6","source":{"kind":"arxiv","id":"2504.12682","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12682","created_at":"2026-07-05T10:50:20Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12682v1","created_at":"2026-07-05T10:50:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12682","created_at":"2026-07-05T10:50:20Z"},{"alias_kind":"pith_short_12","alias_value":"5JRNNL5WISIG","created_at":"2026-07-05T10:50:20Z"},{"alias_kind":"pith_short_16","alias_value":"5JRNNL5WISIGHXSI","created_at":"2026-07-05T10:50:20Z"},{"alias_kind":"pith_short_8","alias_value":"5JRNNL5W","created_at":"2026-07-05T10:50:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5JRNNL5WISIGHXSIPRC6PINGXM","target":"record","payload":{"canonical_record":{"source":{"id":"2504.12682","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-17T06:16:40Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"43de65f28dd1bcf4d190fc5065f755ae91b14c1414ab629c33b8a7e036e6f570","abstract_canon_sha256":"10b3592b54d26eb62cc8f4996b516a262e04791f40fb61c245ffe3697581b923"},"schema_version":"1.0"},"canonical_sha256":"ea62d6afb6449063de487c45e7a1a6bb32e1bbd3de207849babdb89fb50f47b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:20.585364Z","signature_b64":"Gnp7ShC2U9v0l01ThxkUnRfV9w261sqfg/2k1p3QNKCPGLzQGj4XUGFGJNvCZOYC6FeoqoUFoLZxqllMqOS8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea62d6afb6449063de487c45e7a1a6bb32e1bbd3de207849babdb89fb50f47b6","last_reissued_at":"2026-07-05T10:50:20.584848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:20.584848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.12682","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":"2026-07-05T10:50:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bC5+s6igEdBrU6qn5tgB89c1Y5TAbeQp9+Z4oX3owNjMswqzoygEqZn7nDhstb/qhIVw9n7rRKT2wkd/J4uYBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:14:35.533803Z"},"content_sha256":"5342739a4c491f661c5418faae85584fbb609b28291144dbb905057b66d55719","schema_version":"1.0","event_id":"sha256:5342739a4c491f661c5418faae85584fbb609b28291144dbb905057b66d55719"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5JRNNL5WISIGHXSIPRC6PINGXM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WebLists: Extracting Structured Information From Complex Interactive Websites Using Executable LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Artem Harutyunyan, Arth Bohra, Danil Melkozerov, Gabriel Maher, Giovanni Campagna, Manvel Saroyan, Pascal Weinberger, Vahe Karufanyan","submitted_at":"2025-04-17T06:16:40Z","abstract_excerpt":"Most recent web agent research has focused on navigation and transaction tasks, with little emphasis on extracting structured data at scale. We present WebLists, a benchmark of 200 data-extraction tasks across four common business and enterprise use-cases. Each task requires an agent to navigate to a webpage, configure it appropriately, and extract complete datasets with well-defined schemas. We show that both LLMs with search capabilities and SOTA web agents struggle with these tasks, with a recall of 3% and 31%, respectively, despite higher performance on question-answering tasks.\n  To addre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12682","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/2504.12682/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":"2026-07-05T10:50:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V56iyWRzmXgc1Hm3MLO/KGbeJTysuk0Yq7qrthAWZCludpAlXp1XU1FbzvSLTkKOaxmADx6LzUSkS2WM/OCZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:14:35.534196Z"},"content_sha256":"169b68d73970c3be321406ee1b05c9020691cff3bde285e4109136da5dfc9cec","schema_version":"1.0","event_id":"sha256:169b68d73970c3be321406ee1b05c9020691cff3bde285e4109136da5dfc9cec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5JRNNL5WISIGHXSIPRC6PINGXM/bundle.json","state_url":"https://pith.science/pith/5JRNNL5WISIGHXSIPRC6PINGXM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5JRNNL5WISIGHXSIPRC6PINGXM/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":"2026-07-09T06:14:35Z","links":{"resolver":"https://pith.science/pith/5JRNNL5WISIGHXSIPRC6PINGXM","bundle":"https://pith.science/pith/5JRNNL5WISIGHXSIPRC6PINGXM/bundle.json","state":"https://pith.science/pith/5JRNNL5WISIGHXSIPRC6PINGXM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5JRNNL5WISIGHXSIPRC6PINGXM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5JRNNL5WISIGHXSIPRC6PINGXM","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":"10b3592b54d26eb62cc8f4996b516a262e04791f40fb61c245ffe3697581b923","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-17T06:16:40Z","title_canon_sha256":"43de65f28dd1bcf4d190fc5065f755ae91b14c1414ab629c33b8a7e036e6f570"},"schema_version":"1.0","source":{"id":"2504.12682","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12682","created_at":"2026-07-05T10:50:20Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12682v1","created_at":"2026-07-05T10:50:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12682","created_at":"2026-07-05T10:50:20Z"},{"alias_kind":"pith_short_12","alias_value":"5JRNNL5WISIG","created_at":"2026-07-05T10:50:20Z"},{"alias_kind":"pith_short_16","alias_value":"5JRNNL5WISIGHXSI","created_at":"2026-07-05T10:50:20Z"},{"alias_kind":"pith_short_8","alias_value":"5JRNNL5W","created_at":"2026-07-05T10:50:20Z"}],"graph_snapshots":[{"event_id":"sha256:169b68d73970c3be321406ee1b05c9020691cff3bde285e4109136da5dfc9cec","target":"graph","created_at":"2026-07-05T10:50:20Z","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/2504.12682/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most recent web agent research has focused on navigation and transaction tasks, with little emphasis on extracting structured data at scale. We present WebLists, a benchmark of 200 data-extraction tasks across four common business and enterprise use-cases. Each task requires an agent to navigate to a webpage, configure it appropriately, and extract complete datasets with well-defined schemas. We show that both LLMs with search capabilities and SOTA web agents struggle with these tasks, with a recall of 3% and 31%, respectively, despite higher performance on question-answering tasks.\n  To addre","authors_text":"Artem Harutyunyan, Arth Bohra, Danil Melkozerov, Gabriel Maher, Giovanni Campagna, Manvel Saroyan, Pascal Weinberger, Vahe Karufanyan","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-17T06:16:40Z","title":"WebLists: Extracting Structured Information From Complex Interactive Websites Using Executable LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12682","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":"sha256:5342739a4c491f661c5418faae85584fbb609b28291144dbb905057b66d55719","target":"record","created_at":"2026-07-05T10:50:20Z","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":"10b3592b54d26eb62cc8f4996b516a262e04791f40fb61c245ffe3697581b923","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-17T06:16:40Z","title_canon_sha256":"43de65f28dd1bcf4d190fc5065f755ae91b14c1414ab629c33b8a7e036e6f570"},"schema_version":"1.0","source":{"id":"2504.12682","kind":"arxiv","version":1}},"canonical_sha256":"ea62d6afb6449063de487c45e7a1a6bb32e1bbd3de207849babdb89fb50f47b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea62d6afb6449063de487c45e7a1a6bb32e1bbd3de207849babdb89fb50f47b6","first_computed_at":"2026-07-05T10:50:20.584848Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:20.584848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gnp7ShC2U9v0l01ThxkUnRfV9w261sqfg/2k1p3QNKCPGLzQGj4XUGFGJNvCZOYC6FeoqoUFoLZxqllMqOS8Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:20.585364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12682","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5342739a4c491f661c5418faae85584fbb609b28291144dbb905057b66d55719","sha256:169b68d73970c3be321406ee1b05c9020691cff3bde285e4109136da5dfc9cec"],"state_sha256":"d63742b3d395118d6d0d3d40a7f495246269b848cc48db7f0fd14d1f0b3ba8af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"16p1iAgrx+WTtVojqs5wDG2+0/dXqgY/QcqtTc0tJ/zQWKSbYf0pviI+c21BNyufbGvC00pUZ23PUFh/QiOPAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:14:35.536874Z","bundle_sha256":"3ae309954e5b8952b4fb6deaf624d600605287ccf122347cca0b4ec342a72dd1"}}