{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EQWLRQYMRUPFS4KJGFZVGM247D","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":"b4d0db21bf900b36037cdd67e71cb0bbb313470c8197f8e8cced64b2cfe73502","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-08T17:22:54Z","title_canon_sha256":"cc635af1a9f45ca110d27edc47511eaba70be6c0f98b8bd6f75e285217ea6697"},"schema_version":"1.0","source":{"id":"2511.06077","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.06077","created_at":"2026-05-20T01:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2511.06077v3","created_at":"2026-05-20T01:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.06077","created_at":"2026-05-20T01:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"EQWLRQYMRUPF","created_at":"2026-05-20T01:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"EQWLRQYMRUPFS4KJ","created_at":"2026-05-20T01:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"EQWLRQYM","created_at":"2026-05-20T01:05:01Z"}],"graph_snapshots":[{"event_id":"sha256:b309194616f4dac79225b4b713d07a2314d51b2db89a3518167718512fd784c1","target":"graph","created_at":"2026-05-20T01:05:01Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Deployed at full traffic on Douyin, our system delivers significant improvements on key engagement metrics while meeting production latency, demonstrating a practical path to scaling end-to-end long-sequence recommendation to the 10k regime."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the length-extrapolative training strategy (train on shorter windows, infer on 10k) generalizes without performance loss and that stacked target-to-history cross attention captures the necessary preference signals from long histories."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Douyin deploys stacked target-to-history cross attention and request-level batching to scale end-to-end recommendation modeling to 10k-length histories, observing scaling-law gains and live engagement improvements."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Stacked cross-attention and shared batching let recommendation models process 10,000-length user histories at production speed."}],"snapshot_sha256":"6c9fe21bb1b197fced8f030413e920a1b111de53a1a18b417aeedf10f682fe5d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7a41d85a461f01b63038805dbe2e9b71b94ca760b6a1a14637201f6949c8c6cd"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2511.06077/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Short-video recommenders such as Douyin must exploit extremely long user behavior histories without breaking latency or cost budgets. We present an end-to-end industrial recommender system that scales long-sequence recommendation modeling to 10K-length histories in production. First, we introduce Stacked Target-to-History Cross Attention (STCA), which replaces history self-attention with stacked cross-attention from the target to the history, reducing complexity from quadratic to linear in sequence length and enabling efficient end-to-end training over long user behavior sequences. Second, we ","authors_text":"Beichuan Zhang, Bo Sun, Feng Zhang, Hangyu Wang, Jia-Qi Yang, Jinan Ni, Lin Guan, Qiwei Chen, Xiaowen Li, Xiao Yang, Xuanyuan Luo, Yi Cheng, Yuhang Qi, Zhifang Fan, Zhishan Zhao","cross_cats":["cs.IR"],"headline":"Stacked cross-attention and shared batching let recommendation models process 10,000-length user histories at production speed.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-08T17:22:54Z","title":"Make It Long, Keep It Fast: End-to-End 10K Long User Behavior Sequence Modeling for Billion-Scale Douyin Recommendation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.06077","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-17T23:25:16.351949Z","id":"0d78b2d3-d76d-4426-bce8-7c5512172294","model_set":{"reader":"grok-4.3"},"one_line_summary":"Douyin deploys stacked target-to-history cross attention and request-level batching to scale end-to-end recommendation modeling to 10k-length histories, observing scaling-law gains and live engagement improvements.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Stacked cross-attention and shared batching let recommendation models process 10,000-length user histories at production speed.","strongest_claim":"Deployed at full traffic on Douyin, our system delivers significant improvements on key engagement metrics while meeting production latency, demonstrating a practical path to scaling end-to-end long-sequence recommendation to the 10k regime.","weakest_assumption":"That the length-extrapolative training strategy (train on shorter windows, infer on 10k) generalizes without performance loss and that stacked target-to-history cross attention captures the necessary preference signals from long histories."}},"verdict_id":"0d78b2d3-d76d-4426-bce8-7c5512172294"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bd26d18de90b4f2a7913cbcd13622d7c6820190d1efa95aab2bc0a9f10c32fa3","target":"record","created_at":"2026-05-20T01:05:01Z","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":"b4d0db21bf900b36037cdd67e71cb0bbb313470c8197f8e8cced64b2cfe73502","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-08T17:22:54Z","title_canon_sha256":"cc635af1a9f45ca110d27edc47511eaba70be6c0f98b8bd6f75e285217ea6697"},"schema_version":"1.0","source":{"id":"2511.06077","kind":"arxiv","version":3}},"canonical_sha256":"242cb8c30c8d1e597149317353335cf8c7c5156c744806cde9937756293981e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"242cb8c30c8d1e597149317353335cf8c7c5156c744806cde9937756293981e5","first_computed_at":"2026-05-20T01:05:01.391006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:01.391006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SyVS9GJKTl2XsUIqRzog6+8pRqhmeeia6CvE9csszQ4B6HdPL2kFD+cpPLNXAKZcvY9V3ftgrEmlUIEZhWj8Aw==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:01.391858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.06077","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd26d18de90b4f2a7913cbcd13622d7c6820190d1efa95aab2bc0a9f10c32fa3","sha256:b309194616f4dac79225b4b713d07a2314d51b2db89a3518167718512fd784c1"],"state_sha256":"27c6690c8ca79d9a4dc1ea340af067d2bce5eb233f6037321e5488be94763f46"}