{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EDSDDNC5XDA2MRS7FO4HOLCLDN","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":"c9d1733c5e0e43604cb8b318d416521eaf147a6359592453adff64aa61c2f2db","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T18:54:05Z","title_canon_sha256":"924396e19f7db63a085677ce7e9a1ced988b2c6bf4356b85ed5a39f0b0014556"},"schema_version":"1.0","source":{"id":"2502.06776","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06776","created_at":"2026-07-05T11:07:20Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06776v2","created_at":"2026-07-05T11:07:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06776","created_at":"2026-07-05T11:07:20Z"},{"alias_kind":"pith_short_12","alias_value":"EDSDDNC5XDA2","created_at":"2026-07-05T11:07:20Z"},{"alias_kind":"pith_short_16","alias_value":"EDSDDNC5XDA2MRS7","created_at":"2026-07-05T11:07:20Z"},{"alias_kind":"pith_short_8","alias_value":"EDSDDNC5","created_at":"2026-07-05T11:07:20Z"}],"graph_snapshots":[{"event_id":"sha256:4c12ddcd65290bb688c06caa35b25288af8be820b65150b6787a32dc06f85722","target":"graph","created_at":"2026-07-05T11:07:20Z","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/2502.06776/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The predominant approach for training web navigation agents is to gather human demonstrations for a set of popular websites and hand-written tasks, but it is becoming clear that human data is an inefficient resource. We develop a pipeline to facilitate internet-scale training for agents without laborious human annotations. In the first stage, an LLM annotates 150k sites with agentic tasks. In the next stage, LLM agents complete tasks and produce trajectories. In the final stage, an LLM filters trajectories by judging their success. Language models are powerful data curation tools, identifying ","authors_text":"Brandon Trabucco, Gunnar Sigurdsson, Robinson Piramuthu, Ruslan Salakhutdinov","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T18:54:05Z","title":"InSTA: Towards Internet-Scale Training For Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06776","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":"sha256:7b1acd096e80f0ef2278bc4e8b7b0099c21e8e9640fa5a912249f9705f3557c4","target":"record","created_at":"2026-07-05T11:07:20Z","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":"c9d1733c5e0e43604cb8b318d416521eaf147a6359592453adff64aa61c2f2db","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T18:54:05Z","title_canon_sha256":"924396e19f7db63a085677ce7e9a1ced988b2c6bf4356b85ed5a39f0b0014556"},"schema_version":"1.0","source":{"id":"2502.06776","kind":"arxiv","version":2}},"canonical_sha256":"20e431b45db8c1a6465f2bb8772c4b1b7b08e786785e81eff46c698cea19d14f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20e431b45db8c1a6465f2bb8772c4b1b7b08e786785e81eff46c698cea19d14f","first_computed_at":"2026-07-05T11:07:20.249293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:20.249293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DjQKrVHqoXr3ti08GU5PvxnGNN0MzaYdwOUURs1S0AA3+npvi6Bq5CNfXSXnR2mfXn9NreO2mqA3zztH3FOdCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:20.249766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06776","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b1acd096e80f0ef2278bc4e8b7b0099c21e8e9640fa5a912249f9705f3557c4","sha256:4c12ddcd65290bb688c06caa35b25288af8be820b65150b6787a32dc06f85722"],"state_sha256":"8d8c0a7ed8554b8e59ba94bb5ff077461dad627c5a5d3091b24bfd0b1634baf3"}