{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7XZPVRFY4DOZP3ZXS67X63ET67","short_pith_number":"pith:7XZPVRFY","canonical_record":{"source":{"id":"2406.01623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-01T00:32:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3907f792ca37f984c499d2f6ebe766135a7a5256696adfa7c39885f062f86208","abstract_canon_sha256":"b5c1aaa514fbb3bf1e8282927d34128b1210158a4e0daaa1afecee03b9d6124d"},"schema_version":"1.0"},"canonical_sha256":"fdf2fac4b8e0dd97ef3797bf7f6c93f7c8e44ddf72d7ed0c98f43244d02a722c","source":{"kind":"arxiv","id":"2406.01623","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01623","created_at":"2026-07-05T08:26:45Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01623v1","created_at":"2026-07-05T08:26:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01623","created_at":"2026-07-05T08:26:45Z"},{"alias_kind":"pith_short_12","alias_value":"7XZPVRFY4DOZ","created_at":"2026-07-05T08:26:45Z"},{"alias_kind":"pith_short_16","alias_value":"7XZPVRFY4DOZP3ZX","created_at":"2026-07-05T08:26:45Z"},{"alias_kind":"pith_short_8","alias_value":"7XZPVRFY","created_at":"2026-07-05T08:26:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7XZPVRFY4DOZP3ZXS67X63ET67","target":"record","payload":{"canonical_record":{"source":{"id":"2406.01623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-01T00:32:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3907f792ca37f984c499d2f6ebe766135a7a5256696adfa7c39885f062f86208","abstract_canon_sha256":"b5c1aaa514fbb3bf1e8282927d34128b1210158a4e0daaa1afecee03b9d6124d"},"schema_version":"1.0"},"canonical_sha256":"fdf2fac4b8e0dd97ef3797bf7f6c93f7c8e44ddf72d7ed0c98f43244d02a722c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:45.622940Z","signature_b64":"G0WEk3BlCVBSujhNdqtxACijJvoEeZ7m7qkZUacQWGQphmTFsRoRVmhB5mtD1bcQNG4yp/RFYXylTu4ogKSDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdf2fac4b8e0dd97ef3797bf7f6c93f7c8e44ddf72d7ed0c98f43244d02a722c","last_reissued_at":"2026-07-05T08:26:45.622391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:45.622391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.01623","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":"2026-07-05T08:26:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c9lUh6RjdbmqVsK+Gv52rsFIyn/mjzENJJSr5GnfPbGU+9uEDBWwN8mHucoZp9r3gqyW70S8MGon/JMyeh3qAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:40:53.227512Z"},"content_sha256":"f2f5ec0437f9140fbaa1ad6e65a1e567a126ae30d5c89547938dd00c4bf12b39","schema_version":"1.0","event_id":"sha256:f2f5ec0437f9140fbaa1ad6e65a1e567a126ae30d5c89547938dd00c4bf12b39"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7XZPVRFY4DOZP3ZXS67X63ET67","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WebSuite: Systematically Evaluating Why Web Agents Fail","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Eric Li, Jim Waldo","submitted_at":"2024-06-01T00:32:26Z","abstract_excerpt":"We describe WebSuite, the first diagnostic benchmark for generalist web agents, designed to systematically evaluate why agents fail. Advances in AI have led to the rise of numerous web agents that autonomously operate a browser to complete tasks. However, most existing benchmarks focus on strictly measuring whether an agent can or cannot complete a task, without giving insight on why. In this paper, we 1) develop a taxonomy of web actions to facilitate identifying common failure patterns, and 2) create an extensible benchmark suite to assess agents' performance on our taxonomized actions. This"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01623","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/2406.01623/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":"2026-07-05T08:26:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PTeSA8jpsCWAKd91Q4Oyq6BnfK4S07dQbWgO4D4l7fwpkh0+xUZyOf5D0ESrc/9Ws4lPW7FRY8ioK9k4NFlEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:40:53.228068Z"},"content_sha256":"746f3ebfa286d6aa7719ef98e1fcd0dbfbba409755aafc7cec563b401351f924","schema_version":"1.0","event_id":"sha256:746f3ebfa286d6aa7719ef98e1fcd0dbfbba409755aafc7cec563b401351f924"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7XZPVRFY4DOZP3ZXS67X63ET67/bundle.json","state_url":"https://pith.science/pith/7XZPVRFY4DOZP3ZXS67X63ET67/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7XZPVRFY4DOZP3ZXS67X63ET67/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":"2026-08-05T04:40:53Z","links":{"resolver":"https://pith.science/pith/7XZPVRFY4DOZP3ZXS67X63ET67","bundle":"https://pith.science/pith/7XZPVRFY4DOZP3ZXS67X63ET67/bundle.json","state":"https://pith.science/pith/7XZPVRFY4DOZP3ZXS67X63ET67/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7XZPVRFY4DOZP3ZXS67X63ET67/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7XZPVRFY4DOZP3ZXS67X63ET67","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":"b5c1aaa514fbb3bf1e8282927d34128b1210158a4e0daaa1afecee03b9d6124d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-01T00:32:26Z","title_canon_sha256":"3907f792ca37f984c499d2f6ebe766135a7a5256696adfa7c39885f062f86208"},"schema_version":"1.0","source":{"id":"2406.01623","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01623","created_at":"2026-07-05T08:26:45Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01623v1","created_at":"2026-07-05T08:26:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01623","created_at":"2026-07-05T08:26:45Z"},{"alias_kind":"pith_short_12","alias_value":"7XZPVRFY4DOZ","created_at":"2026-07-05T08:26:45Z"},{"alias_kind":"pith_short_16","alias_value":"7XZPVRFY4DOZP3ZX","created_at":"2026-07-05T08:26:45Z"},{"alias_kind":"pith_short_8","alias_value":"7XZPVRFY","created_at":"2026-07-05T08:26:45Z"}],"graph_snapshots":[{"event_id":"sha256:746f3ebfa286d6aa7719ef98e1fcd0dbfbba409755aafc7cec563b401351f924","target":"graph","created_at":"2026-07-05T08:26:45Z","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/2406.01623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We describe WebSuite, the first diagnostic benchmark for generalist web agents, designed to systematically evaluate why agents fail. Advances in AI have led to the rise of numerous web agents that autonomously operate a browser to complete tasks. However, most existing benchmarks focus on strictly measuring whether an agent can or cannot complete a task, without giving insight on why. In this paper, we 1) develop a taxonomy of web actions to facilitate identifying common failure patterns, and 2) create an extensible benchmark suite to assess agents' performance on our taxonomized actions. This","authors_text":"Eric Li, Jim Waldo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-01T00:32:26Z","title":"WebSuite: Systematically Evaluating Why Web Agents Fail"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01623","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:f2f5ec0437f9140fbaa1ad6e65a1e567a126ae30d5c89547938dd00c4bf12b39","target":"record","created_at":"2026-07-05T08:26:45Z","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":"b5c1aaa514fbb3bf1e8282927d34128b1210158a4e0daaa1afecee03b9d6124d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-01T00:32:26Z","title_canon_sha256":"3907f792ca37f984c499d2f6ebe766135a7a5256696adfa7c39885f062f86208"},"schema_version":"1.0","source":{"id":"2406.01623","kind":"arxiv","version":1}},"canonical_sha256":"fdf2fac4b8e0dd97ef3797bf7f6c93f7c8e44ddf72d7ed0c98f43244d02a722c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdf2fac4b8e0dd97ef3797bf7f6c93f7c8e44ddf72d7ed0c98f43244d02a722c","first_computed_at":"2026-07-05T08:26:45.622391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:45.622391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G0WEk3BlCVBSujhNdqtxACijJvoEeZ7m7qkZUacQWGQphmTFsRoRVmhB5mtD1bcQNG4yp/RFYXylTu4ogKSDCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:45.622940Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01623","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2f5ec0437f9140fbaa1ad6e65a1e567a126ae30d5c89547938dd00c4bf12b39","sha256:746f3ebfa286d6aa7719ef98e1fcd0dbfbba409755aafc7cec563b401351f924"],"state_sha256":"648c2005069b4b195276e8d35c8c35e8fc8bfba493a506cc8004837ec389d7f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sY/4rDkwRoJ0WrGcIgyAAHdDZXmZbNOpq8E53Z7XkaNcg6wtv+ebkpA/GgKx2jq5OyizIFV7OJbxvhdsVUwxBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:40:53.233048Z","bundle_sha256":"2b96f1b958c2cbd24352811c156c00ae78a18893e7c6ab92702e9f14f3432f46"}}