{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XR5VXYCE3VPCB5XCPSSOZ6XSLX","short_pith_number":"pith:XR5VXYCE","canonical_record":{"source":{"id":"2412.09605","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T18:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"0462bc4c1902e5ecc14e078af5e2481d64513951b3ea47afd0b8516c001f613f","abstract_canon_sha256":"bb05b9f323c9a4809e854511652b19558ee0ecb2a334745f58d287a584acbc77"},"schema_version":"1.0"},"canonical_sha256":"bc7b5be044dd5e20f6e27ca4ecfaf25dd064d57a291ac84a7c2a13190d32866d","source":{"kind":"arxiv","id":"2412.09605","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09605","created_at":"2026-07-05T10:22:54Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09605v2","created_at":"2026-07-05T10:22:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09605","created_at":"2026-07-05T10:22:54Z"},{"alias_kind":"pith_short_12","alias_value":"XR5VXYCE3VPC","created_at":"2026-07-05T10:22:54Z"},{"alias_kind":"pith_short_16","alias_value":"XR5VXYCE3VPCB5XC","created_at":"2026-07-05T10:22:54Z"},{"alias_kind":"pith_short_8","alias_value":"XR5VXYCE","created_at":"2026-07-05T10:22:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XR5VXYCE3VPCB5XCPSSOZ6XSLX","target":"record","payload":{"canonical_record":{"source":{"id":"2412.09605","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T18:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"0462bc4c1902e5ecc14e078af5e2481d64513951b3ea47afd0b8516c001f613f","abstract_canon_sha256":"bb05b9f323c9a4809e854511652b19558ee0ecb2a334745f58d287a584acbc77"},"schema_version":"1.0"},"canonical_sha256":"bc7b5be044dd5e20f6e27ca4ecfaf25dd064d57a291ac84a7c2a13190d32866d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:54.815960Z","signature_b64":"PSho6hdxk55pdswrk+BIdBcVSMdpxfBUAx4ig1dwlMeQEMqYQ/yBDjjrJUEwSpgbxQwKs11KCBzuq9YCfeagDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc7b5be044dd5e20f6e27ca4ecfaf25dd064d57a291ac84a7c2a13190d32866d","last_reissued_at":"2026-07-05T10:22:54.815384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:54.815384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.09605","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":"2026-07-05T10:22:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+jlumTzRskbaq0duTXpxNKOPai16SZ2CmPrqINhVdOhcCgfDalKPG1+VgV8HunodW7bM/t9Rtc2Xwx/uvRiGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T02:14:05.083270Z"},"content_sha256":"7242a49b619fdce6c4e77417d155400a957db80115cbaa2f4be077e377250fa4","schema_version":"1.0","event_id":"sha256:7242a49b619fdce6c4e77417d155400a957db80115cbaa2f4be077e377250fa4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XR5VXYCE3VPCB5XCPSSOZ6XSLX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Dunjie Lu, Junli Wang, Tao Yu, Yiheng Xu, Yuchen Mao, Zekun Wang, Zhennan Shen","submitted_at":"2024-12-12T18:59:27Z","abstract_excerpt":"Graphical User Interface (GUI) agents can automate complex tasks across digital environments, but their development is hindered by the scarcity of high-quality trajectory data for training. Existing approaches rely on expensive human annotation, making them unsustainable at scale. We propose AgentTrek, a scalable data synthesis pipeline that generates web agent trajectories by leveraging publicly available tutorials. Our three-stage method: (1) automatically harvests and filters tutorial-like texts from the internet using a specialized classification model, (2) transforms these texts into stru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09605","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/2412.09605/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":"2026-07-05T10:22:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uw0bXWCa8e0GgLT1fDjNJ8i7ZNyXv89BU98SKmqASdINBhmM3Z0MXwgRUGUWTxy65TMxV9xvnrLqPjFDlPxUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T02:14:05.083675Z"},"content_sha256":"895b31826c3fb543a08a0cf0826a2888c8b2237266fda2800e0a8e86218f6a69","schema_version":"1.0","event_id":"sha256:895b31826c3fb543a08a0cf0826a2888c8b2237266fda2800e0a8e86218f6a69"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XR5VXYCE3VPCB5XCPSSOZ6XSLX/bundle.json","state_url":"https://pith.science/pith/XR5VXYCE3VPCB5XCPSSOZ6XSLX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XR5VXYCE3VPCB5XCPSSOZ6XSLX/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":"2026-07-24T02:14:05Z","links":{"resolver":"https://pith.science/pith/XR5VXYCE3VPCB5XCPSSOZ6XSLX","bundle":"https://pith.science/pith/XR5VXYCE3VPCB5XCPSSOZ6XSLX/bundle.json","state":"https://pith.science/pith/XR5VXYCE3VPCB5XCPSSOZ6XSLX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XR5VXYCE3VPCB5XCPSSOZ6XSLX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XR5VXYCE3VPCB5XCPSSOZ6XSLX","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":"bb05b9f323c9a4809e854511652b19558ee0ecb2a334745f58d287a584acbc77","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T18:59:27Z","title_canon_sha256":"0462bc4c1902e5ecc14e078af5e2481d64513951b3ea47afd0b8516c001f613f"},"schema_version":"1.0","source":{"id":"2412.09605","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09605","created_at":"2026-07-05T10:22:54Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09605v2","created_at":"2026-07-05T10:22:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09605","created_at":"2026-07-05T10:22:54Z"},{"alias_kind":"pith_short_12","alias_value":"XR5VXYCE3VPC","created_at":"2026-07-05T10:22:54Z"},{"alias_kind":"pith_short_16","alias_value":"XR5VXYCE3VPCB5XC","created_at":"2026-07-05T10:22:54Z"},{"alias_kind":"pith_short_8","alias_value":"XR5VXYCE","created_at":"2026-07-05T10:22:54Z"}],"graph_snapshots":[{"event_id":"sha256:895b31826c3fb543a08a0cf0826a2888c8b2237266fda2800e0a8e86218f6a69","target":"graph","created_at":"2026-07-05T10:22:54Z","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/2412.09605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graphical User Interface (GUI) agents can automate complex tasks across digital environments, but their development is hindered by the scarcity of high-quality trajectory data for training. Existing approaches rely on expensive human annotation, making them unsustainable at scale. We propose AgentTrek, a scalable data synthesis pipeline that generates web agent trajectories by leveraging publicly available tutorials. Our three-stage method: (1) automatically harvests and filters tutorial-like texts from the internet using a specialized classification model, (2) transforms these texts into stru","authors_text":"Caiming Xiong, Dunjie Lu, Junli Wang, Tao Yu, Yiheng Xu, Yuchen Mao, Zekun Wang, Zhennan Shen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T18:59:27Z","title":"AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09605","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":"sha256:7242a49b619fdce6c4e77417d155400a957db80115cbaa2f4be077e377250fa4","target":"record","created_at":"2026-07-05T10:22:54Z","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":"bb05b9f323c9a4809e854511652b19558ee0ecb2a334745f58d287a584acbc77","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T18:59:27Z","title_canon_sha256":"0462bc4c1902e5ecc14e078af5e2481d64513951b3ea47afd0b8516c001f613f"},"schema_version":"1.0","source":{"id":"2412.09605","kind":"arxiv","version":2}},"canonical_sha256":"bc7b5be044dd5e20f6e27ca4ecfaf25dd064d57a291ac84a7c2a13190d32866d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc7b5be044dd5e20f6e27ca4ecfaf25dd064d57a291ac84a7c2a13190d32866d","first_computed_at":"2026-07-05T10:22:54.815384Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:54.815384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PSho6hdxk55pdswrk+BIdBcVSMdpxfBUAx4ig1dwlMeQEMqYQ/yBDjjrJUEwSpgbxQwKs11KCBzuq9YCfeagDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:54.815960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09605","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7242a49b619fdce6c4e77417d155400a957db80115cbaa2f4be077e377250fa4","sha256:895b31826c3fb543a08a0cf0826a2888c8b2237266fda2800e0a8e86218f6a69"],"state_sha256":"5727da4764774b9fd3ecbea6eeddfdde8da3cf180dd5c2a89d420dffb43ffe02"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dKyyovLQynAtdspTsHzfwZiB0+Yb2u++qA4mNjYCEsXqVNOPdZA1QOFi0Zetvef+5K6p/nTBNPIgbbzusGbXAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T02:14:05.085978Z","bundle_sha256":"c7bcd948de2e14a020b0ab74047df9abd7ef0186c7cb2ce4a6ab6f40e40f9b2a"}}