{"schema_version":"newruntime-reader-dossiers-v1","type":"reader_dossier","id":"reader:bytespider","slug":"bytespider","name":"Bytespider","kind":"ai_training","kind_label":"AI model crawlers","operator":{"name":"ByteDance","url":"https://www.bytedance.com/"},"docs_url":null,"robots_tokens":["Bytespider"],"purpose":"ByteDance crawler described by secondary sources as an AI data scraper, allegedly used to build training data for ByteDance LLMs such as Doubao. No operator documentation was opened.","feeds":["model_training"],"respects_robots":"unknown","robots_note":"Secondary source lists it as expected to follow robots.txt, but ByteDance publishes no verification method; compliance unconfirmed.","verification":{"method":"none_published","url":null},"why_it_matters":{"text":"Training read for Chinese-market models; heavy bursty traffic with no attribution back to New Runtime.","kind":"new_runtime_interpretation"},"confidence":"medium","researched_at":"2026-10-23","sources":["https://knownagents.com/agents/bytespider"],"icon_url":"https://newruntime.com/readers/icons/bytedance.png","matching":{"aliases":["bytespider"],"rule":"Reduce each agent_days label to a token: for labels starting with Mozilla/ take the product after 'compatible;', else a versioned crawler token such as 'FooBot/1.0' (a truncated 'Mozilla/5.0 (Linux; Android 7.0;) AppleWebKit/537.36 (KHTML, like Gecko) Mobile' prefix logged before 23 Oct 2026 is PetalBot; anything else is unidentified-android, unidentified-linux-chrome or unidentified-browser); otherwise take the text before the first '/', '(' or ';' and drop a trailing ' token probe'. Lowercase it. A dossier owns the tokens in its aliases."},"observed_baseline":{"as_of":"2026-10-23T08:01:01.990Z","window_first_day":"2026-07-23","window_last_day":"2026-10-23","observed_days":93,"note":"Refreshed daily in production from the live aggregates (dated by as_of). For current numbers aggregate live_sources.history agent_days by matching.aliases.","total_requests":29,"first_seen":"2026-09-11T21:41:07.461Z","last_seen":"2026-10-21T16:34:04.082Z","days_active":4,"recency":"returning","categories":["other_bot"],"label_variants":1,"journeys":null},"identity_note":"A family name is what a client claims in its user agent. It is verified only when its request came from the operator's published IP ranges or passed forward-confirmed reverse DNS, as reported per family in /crawler-journeys.json. Anyone can claim any name.","privacy":{"scope":"family-level aggregates only","ip_addresses":"not_output","raw_user_agents":"not_output (labels are sanitized; URLs inside them are redacted)","visitor_ids":"not_output","query_strings":"not_output"},"live_sources":{"history":"https://newruntime.com/bot-traffic-history.json","latest":"https://newruntime.com/bot-traffic-latest.json","machine_consumption":"https://newruntime.com/machine-consumption.json","crawler_journeys":"https://newruntime.com/crawler-journeys.json"},"routes":{"html":"https://newruntime.com/readers/bytespider/","markdown":"https://newruntime.com/readers/bytespider.md","json":"https://newruntime.com/readers/bytespider.json","index":"https://newruntime.com/readers.json","index_html":"https://newruntime.com/readers/"}}