{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YNXGBHPAZPK2VGCS7TO2Y4CMM7","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":"61f0217094fa38a883c8b9ae368c71f24fd61359504784eecddf137b62d2233b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T03:07:17Z","title_canon_sha256":"8dc6d06ac7318c08e1052c963d238d300b36ff87a4115c812671379eb956e7cd"},"schema_version":"1.0","source":{"id":"2607.00368","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00368","created_at":"2026-07-02T01:17:41Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00368v1","created_at":"2026-07-02T01:17:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00368","created_at":"2026-07-02T01:17:41Z"},{"alias_kind":"pith_short_12","alias_value":"YNXGBHPAZPK2","created_at":"2026-07-02T01:17:41Z"},{"alias_kind":"pith_short_16","alias_value":"YNXGBHPAZPK2VGCS","created_at":"2026-07-02T01:17:41Z"},{"alias_kind":"pith_short_8","alias_value":"YNXGBHPA","created_at":"2026-07-02T01:17:41Z"}],"graph_snapshots":[{"event_id":"sha256:8e524fc74d2ea7af2cf048c89611dac22c7c9a53a6b6de8e844381635c4b602c","target":"graph","created_at":"2026-07-02T01:17:41Z","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/2607.00368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model test-time training (TTT) is often evaluated through local proxy metrics: models are updated on recent tokens, retrieved context, target-domain data, or verifiable task attempts, and then judged by perplexity, future-token loss, long-context performance, or reward. These metrics are well matched to claims about stream adaptation, domain adaptation, context compression, and reward-backed test-time improvement. They are weaker evidence, however, for a capability that TTT results are increasingly used to motivate: deployed assistant memory, personalization, or sparse post-depl","authors_text":"Guangyi Chen, Kun Zhang, Lingjing Kong, Shaoan Xie, Xiangchen Song, Xinshuai Dong, Zhenhao Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T03:07:17Z","title":"Beyond Perplexity: A Behavioral Evaluation Framework for Deployment-Memory Claims in LLM Test-Time Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00368","kind":"arxiv","version":1},"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":"sha256:85756c25ab834cb8f3a33c89790d78abee2a4f32c6f705327b3e743b9fb1ffa3","target":"record","created_at":"2026-07-02T01:17:41Z","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":"61f0217094fa38a883c8b9ae368c71f24fd61359504784eecddf137b62d2233b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T03:07:17Z","title_canon_sha256":"8dc6d06ac7318c08e1052c963d238d300b36ff87a4115c812671379eb956e7cd"},"schema_version":"1.0","source":{"id":"2607.00368","kind":"arxiv","version":1}},"canonical_sha256":"c36e609de0cbd5aa9852fcddac704c67d2f40b130d7d0eb84a22b2f094cee008","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c36e609de0cbd5aa9852fcddac704c67d2f40b130d7d0eb84a22b2f094cee008","first_computed_at":"2026-07-02T01:17:41.396247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:17:41.396247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BDq6+yTcUe4VcY3rLqPloz8PQZk8qtRlsHr0YCb82N+IQLPuQT+5i9VDgf8Vz8VbBrcLCDaZplbNokYF5SWUCQ==","signature_status":"signed_v1","signed_at":"2026-07-02T01:17:41.396632Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.00368","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85756c25ab834cb8f3a33c89790d78abee2a4f32c6f705327b3e743b9fb1ffa3","sha256:8e524fc74d2ea7af2cf048c89611dac22c7c9a53a6b6de8e844381635c4b602c"],"state_sha256":"03a8d71ffc9c4c19df38c850505f452ffe8f414fb92a70813412840e6c9946f1"}