{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WDWFQB5CTFTSTXIDYAW32CNDXS","short_pith_number":"pith:WDWFQB5C","canonical_record":{"source":{"id":"2411.15004","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T15:26:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"310112ca3e403c002dbb542b4380d4a9e78fc4e95001f9233184dab30e1ca320","abstract_canon_sha256":"89fa7df586bdb58b68de195fef3cbc30a1a527a3b87475a933738665f8d0923a"},"schema_version":"1.0"},"canonical_sha256":"b0ec5807a2996729dd03c02dbd09a3bcb9339d470633aa6720eec8795ede2991","source":{"kind":"arxiv","id":"2411.15004","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15004","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15004v2","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15004","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_12","alias_value":"WDWFQB5CTFTS","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_16","alias_value":"WDWFQB5CTFTSTXID","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_8","alias_value":"WDWFQB5C","created_at":"2026-07-05T09:44:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WDWFQB5CTFTSTXIDYAW32CNDXS","target":"record","payload":{"canonical_record":{"source":{"id":"2411.15004","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T15:26:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"310112ca3e403c002dbb542b4380d4a9e78fc4e95001f9233184dab30e1ca320","abstract_canon_sha256":"89fa7df586bdb58b68de195fef3cbc30a1a527a3b87475a933738665f8d0923a"},"schema_version":"1.0"},"canonical_sha256":"b0ec5807a2996729dd03c02dbd09a3bcb9339d470633aa6720eec8795ede2991","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:36.645122Z","signature_b64":"7Il7+CAPvvcAR81FRk6e9nDjj5zn6TdkdyGVePJe/HG3zSjqxAUXl9XlH0NnHdbEQHx4cKzmc7fFtZ8e4Qk/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0ec5807a2996729dd03c02dbd09a3bcb9339d470633aa6720eec8795ede2991","last_reissued_at":"2026-07-05T09:44:36.644620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:36.644620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.15004","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:44:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DAqfxdy1hKnePii4pCyPnAvVm4uY3d/5pQ63pALnBgbiiBw03LhmdSv1WLwbgdcIRaJ2XYRXHfHl7XomJSduDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:48:02.825743Z"},"content_sha256":"3c42145250e2794d6cb81f8d92ba2f7db729ad136232496d31b02d33f8de392d","schema_version":"1.0","event_id":"sha256:3c42145250e2794d6cb81f8d92ba2f7db729ad136232496d31b02d33f8de392d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WDWFQB5CTFTSTXIDYAW32CNDXS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aaron Podolny, Ameet Talwalkar, Atishay Jain, Ishan Amlekar, Junhong Shen, Mouad Hadji, Zedian Xiao","submitted_at":"2024-11-22T15:26:23Z","abstract_excerpt":"Large Language Model (LLM) agents are rapidly improving to handle increasingly complex web-based tasks. Most of these agents rely on general-purpose, proprietary models like GPT-4 and focus on designing better prompts to improve their planning abilities. However, general-purpose LLMs are not specifically trained to understand specialized web contexts such as HTML, and they often struggle with long-horizon planning. We explore an alternative approach that fine-tunes open-source LLMs using production-scale workflow data collected from over 250 domains corresponding to 6 billion tokens. This simp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15004","kind":"arxiv","version":2},"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/2411.15004/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":"2026-07-05T09:44:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HAcG36x4BnrsUPtif8x/48TiTUSCmJ7Rby8Vjyym41+wHUn9c4p5kuI28BFZn9frBK1BVyfsWVpzeh/ArpMdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:48:02.826680Z"},"content_sha256":"b9c075e541f1b20464e0adb8c499107f3b12e6d78b7943147f7ee636ac8a613d","schema_version":"1.0","event_id":"sha256:b9c075e541f1b20464e0adb8c499107f3b12e6d78b7943147f7ee636ac8a613d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WDWFQB5CTFTSTXIDYAW32CNDXS/bundle.json","state_url":"https://pith.science/pith/WDWFQB5CTFTSTXIDYAW32CNDXS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WDWFQB5CTFTSTXIDYAW32CNDXS/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":"2026-08-09T04:48:02Z","links":{"resolver":"https://pith.science/pith/WDWFQB5CTFTSTXIDYAW32CNDXS","bundle":"https://pith.science/pith/WDWFQB5CTFTSTXIDYAW32CNDXS/bundle.json","state":"https://pith.science/pith/WDWFQB5CTFTSTXIDYAW32CNDXS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WDWFQB5CTFTSTXIDYAW32CNDXS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WDWFQB5CTFTSTXIDYAW32CNDXS","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":"89fa7df586bdb58b68de195fef3cbc30a1a527a3b87475a933738665f8d0923a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T15:26:23Z","title_canon_sha256":"310112ca3e403c002dbb542b4380d4a9e78fc4e95001f9233184dab30e1ca320"},"schema_version":"1.0","source":{"id":"2411.15004","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15004","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15004v2","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15004","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_12","alias_value":"WDWFQB5CTFTS","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_16","alias_value":"WDWFQB5CTFTSTXID","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_8","alias_value":"WDWFQB5C","created_at":"2026-07-05T09:44:36Z"}],"graph_snapshots":[{"event_id":"sha256:b9c075e541f1b20464e0adb8c499107f3b12e6d78b7943147f7ee636ac8a613d","target":"graph","created_at":"2026-07-05T09:44:36Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.15004/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM) agents are rapidly improving to handle increasingly complex web-based tasks. Most of these agents rely on general-purpose, proprietary models like GPT-4 and focus on designing better prompts to improve their planning abilities. However, general-purpose LLMs are not specifically trained to understand specialized web contexts such as HTML, and they often struggle with long-horizon planning. We explore an alternative approach that fine-tunes open-source LLMs using production-scale workflow data collected from over 250 domains corresponding to 6 billion tokens. This simp","authors_text":"Aaron Podolny, Ameet Talwalkar, Atishay Jain, Ishan Amlekar, Junhong Shen, Mouad Hadji, Zedian Xiao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T15:26:23Z","title":"ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15004","kind":"arxiv","version":2},"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":"sha256:3c42145250e2794d6cb81f8d92ba2f7db729ad136232496d31b02d33f8de392d","target":"record","created_at":"2026-07-05T09:44:36Z","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":"89fa7df586bdb58b68de195fef3cbc30a1a527a3b87475a933738665f8d0923a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T15:26:23Z","title_canon_sha256":"310112ca3e403c002dbb542b4380d4a9e78fc4e95001f9233184dab30e1ca320"},"schema_version":"1.0","source":{"id":"2411.15004","kind":"arxiv","version":2}},"canonical_sha256":"b0ec5807a2996729dd03c02dbd09a3bcb9339d470633aa6720eec8795ede2991","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0ec5807a2996729dd03c02dbd09a3bcb9339d470633aa6720eec8795ede2991","first_computed_at":"2026-07-05T09:44:36.644620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:36.644620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Il7+CAPvvcAR81FRk6e9nDjj5zn6TdkdyGVePJe/HG3zSjqxAUXl9XlH0NnHdbEQHx4cKzmc7fFtZ8e4Qk/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:36.645122Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15004","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c42145250e2794d6cb81f8d92ba2f7db729ad136232496d31b02d33f8de392d","sha256:b9c075e541f1b20464e0adb8c499107f3b12e6d78b7943147f7ee636ac8a613d"],"state_sha256":"2bbe06474507ae3b4f6d1ff8cb0ee88b085c73778d831a51d4042aa92af01903"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GSs3yj6UHmfxoZHCLV0cO5bWPuyts7Ge6yK0mQOcJuecK3ec3hgrDnEHKSGMaVXAlTk93iKZnYyQXIsv+josDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:48:02.864397Z","bundle_sha256":"0744b419604c94a71e89993ad7b08a0df6055b319559a800a89206483a19bfb2"}}