{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L7OG4TFH73TE6JXMAR7TTODNQI","short_pith_number":"pith:L7OG4TFH","schema_version":"1.0","canonical_sha256":"5fdc6e4ca7fee64f26ec047f39b86d821919b1289c73d8c1c25355ba945d1b8e","source":{"kind":"arxiv","id":"2608.01672","version":1},"attestation_state":"computed","paper":{"title":"Learning What to Remember: Test-Time Training via Context Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hengyu Fu, Jason D. Lee, Rui-Jie Zhu, Wenhao Chai, Xingyu Dang, Zixin Wen, Zixuan Wang","submitted_at":"2026-08-03T04:06:06Z","abstract_excerpt":"Effective long-context modeling is not merely about retaining more of the past, but about preserving the information that may prove relevant later. Test-time training (TTT) is an appealing approach that performs online parameter updates for long-context modeling, yet existing TTT methods only optimize either reconstruction or online adaptation objectives without considering the future utility of retained information. In this work, we propose \\textbf{T}est-\\textbf{T}ime \\textbf{C}ontext \\textbf{D}istillation (TTCD), a TTT framework that introduces a self-supervised objective for allocating limi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.01672","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T04:06:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ccf278df13e13280cb6134499694ecbe43c848caa3b98fc58e6b7ec030670a05","abstract_canon_sha256":"3cf552e04026904af04001fdc2cec9adf08eb897b593d32636769603ed83811d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:06:23.369646Z","signature_b64":"4AyEIlDYXE1DY1choroWD/xIvxOTZgyLpFh+Xyb0lXKThu9UcKHKN6hxxCYZHvYm1gui7xk6hf3JzoFoQ29lCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fdc6e4ca7fee64f26ec047f39b86d821919b1289c73d8c1c25355ba945d1b8e","last_reissued_at":"2026-08-04T02:06:23.368047Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:06:23.368047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning What to Remember: Test-Time Training via Context Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hengyu Fu, Jason D. Lee, Rui-Jie Zhu, Wenhao Chai, Xingyu Dang, Zixin Wen, Zixuan Wang","submitted_at":"2026-08-03T04:06:06Z","abstract_excerpt":"Effective long-context modeling is not merely about retaining more of the past, but about preserving the information that may prove relevant later. Test-time training (TTT) is an appealing approach that performs online parameter updates for long-context modeling, yet existing TTT methods only optimize either reconstruction or online adaptation objectives without considering the future utility of retained information. In this work, we propose \\textbf{T}est-\\textbf{T}ime \\textbf{C}ontext \\textbf{D}istillation (TTCD), a TTT framework that introduces a self-supervised objective for allocating limi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01672","kind":"arxiv","version":1},"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/2608.01672/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.01672","created_at":"2026-08-04T02:06:23.369523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01672v1","created_at":"2026-08-04T02:06:23.369523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01672","created_at":"2026-08-04T02:06:23.369523+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7OG4TFH73TE","created_at":"2026-08-04T02:06:23.369523+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7OG4TFH73TE6JXM","created_at":"2026-08-04T02:06:23.369523+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7OG4TFH","created_at":"2026-08-04T02:06:23.369523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7OG4TFH73TE6JXMAR7TTODNQI","json":"https://pith.science/pith/L7OG4TFH73TE6JXMAR7TTODNQI.json","graph_json":"https://pith.science/api/pith-number/L7OG4TFH73TE6JXMAR7TTODNQI/graph.json","events_json":"https://pith.science/api/pith-number/L7OG4TFH73TE6JXMAR7TTODNQI/events.json","paper":"https://pith.science/paper/L7OG4TFH"},"agent_actions":{"view_html":"https://pith.science/pith/L7OG4TFH73TE6JXMAR7TTODNQI","download_json":"https://pith.science/pith/L7OG4TFH73TE6JXMAR7TTODNQI.json","view_paper":"https://pith.science/paper/L7OG4TFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01672&json=true","fetch_graph":"https://pith.science/api/pith-number/L7OG4TFH73TE6JXMAR7TTODNQI/graph.json","fetch_events":"https://pith.science/api/pith-number/L7OG4TFH73TE6JXMAR7TTODNQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7OG4TFH73TE6JXMAR7TTODNQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7OG4TFH73TE6JXMAR7TTODNQI/action/storage_attestation","attest_author":"https://pith.science/pith/L7OG4TFH73TE6JXMAR7TTODNQI/action/author_attestation","sign_citation":"https://pith.science/pith/L7OG4TFH73TE6JXMAR7TTODNQI/action/citation_signature","submit_replication":"https://pith.science/pith/L7OG4TFH73TE6JXMAR7TTODNQI/action/replication_record"}},"created_at":"2026-08-04T02:06:23.369523+00:00","updated_at":"2026-08-04T02:06:23.369523+00:00"}