{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:U55VRNHNZ2A3X3M5GYL6JIAUEX","short_pith_number":"pith:U55VRNHN","canonical_record":{"source":{"id":"2604.00830","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-01T12:41:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ec55d33803e67dd8ab7a32c70983f0e043951054d3af161b87484ef82731fc24","abstract_canon_sha256":"9ef0953ba291c14cee32a1b5769374b919482a59d1c5f9b7385fb57e9cfef86a"},"schema_version":"1.0"},"canonical_sha256":"a77b58b4edce81bbed9d3617e4a01425d2a9ddcacd1beef1da2db965e768aba6","source":{"kind":"arxiv","id":"2604.00830","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.00830","created_at":"2026-07-16T01:22:39Z"},{"alias_kind":"arxiv_version","alias_value":"2604.00830v3","created_at":"2026-07-16T01:22:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.00830","created_at":"2026-07-16T01:22:39Z"},{"alias_kind":"pith_short_12","alias_value":"U55VRNHNZ2A3","created_at":"2026-07-16T01:22:39Z"},{"alias_kind":"pith_short_16","alias_value":"U55VRNHNZ2A3X3M5","created_at":"2026-07-16T01:22:39Z"},{"alias_kind":"pith_short_8","alias_value":"U55VRNHN","created_at":"2026-07-16T01:22:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:U55VRNHNZ2A3X3M5GYL6JIAUEX","target":"record","payload":{"canonical_record":{"source":{"id":"2604.00830","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-01T12:41:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ec55d33803e67dd8ab7a32c70983f0e043951054d3af161b87484ef82731fc24","abstract_canon_sha256":"9ef0953ba291c14cee32a1b5769374b919482a59d1c5f9b7385fb57e9cfef86a"},"schema_version":"1.0"},"canonical_sha256":"a77b58b4edce81bbed9d3617e4a01425d2a9ddcacd1beef1da2db965e768aba6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:22:39.242553Z","signature_b64":"MWEeBE/exYWZw7lAmGJpSFsJgzcLR2Ck32+cP0l76IH6tJFP4TqkoZJaLxKyKEcyD222a6LalaD4tVXmI5coBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a77b58b4edce81bbed9d3617e4a01425d2a9ddcacd1beef1da2db965e768aba6","last_reissued_at":"2026-07-16T01:22:39.241612Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:22:39.241612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.00830","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-16T01:22:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VJFygl3sMJ+uO5ET5Pwy0FP0E3Bv4atawj8XShVAnaVeLQDuxMvRcoDJFzyzSqm75i4JyaVojvwwR0d0VweTBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T02:07:42.695961Z"},"content_sha256":"16e86975b63b76b5de97f0a0d73b1b3e9dfc0c87786cd6acc5b521cf7f689037","schema_version":"1.0","event_id":"sha256:16e86975b63b76b5de97f0a0d73b1b3e9dfc0c87786cd6acc5b521cf7f689037"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:U55VRNHNZ2A3X3M5GYL6JIAUEX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bryan Hooi, Hui Chen, Qian Wang, Yibo Li, Zhanzhi Lou","submitted_at":"2026-04-01T12:41:01Z","abstract_excerpt":"Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time. At the core of TTL is an adaptation policy that updates the actor policy based on experience from previous episodes, thereby improving future behavior. Existing methods rely on fixed, hand-crafted adaptation policies rather than optimizing them for downstream improvement. We argue that optimal adaptation policies should be learned from task environments, not hand-engineered based on human intuition. To achieve this, we introduce Meta-TTL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.00830","kind":"arxiv","version":3},"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/2604.00830/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-16T01:22:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y88P2+vLCCpZ8C1AB+oEm2XzRg2ZOg9Woiap9H7FPt0LXLOvYYH5CceKTF97l7SfsnviSJmGnqOCwHGeze+yBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T02:07:42.696492Z"},"content_sha256":"4f63704784d9c241666ce350321c96aa9ad8299ef92de39bbe26c345f1aa060c","schema_version":"1.0","event_id":"sha256:4f63704784d9c241666ce350321c96aa9ad8299ef92de39bbe26c345f1aa060c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U55VRNHNZ2A3X3M5GYL6JIAUEX/bundle.json","state_url":"https://pith.science/pith/U55VRNHNZ2A3X3M5GYL6JIAUEX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U55VRNHNZ2A3X3M5GYL6JIAUEX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T02:07:42Z","links":{"resolver":"https://pith.science/pith/U55VRNHNZ2A3X3M5GYL6JIAUEX","bundle":"https://pith.science/pith/U55VRNHNZ2A3X3M5GYL6JIAUEX/bundle.json","state":"https://pith.science/pith/U55VRNHNZ2A3X3M5GYL6JIAUEX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U55VRNHNZ2A3X3M5GYL6JIAUEX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:U55VRNHNZ2A3X3M5GYL6JIAUEX","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":"9ef0953ba291c14cee32a1b5769374b919482a59d1c5f9b7385fb57e9cfef86a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-01T12:41:01Z","title_canon_sha256":"ec55d33803e67dd8ab7a32c70983f0e043951054d3af161b87484ef82731fc24"},"schema_version":"1.0","source":{"id":"2604.00830","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.00830","created_at":"2026-07-16T01:22:39Z"},{"alias_kind":"arxiv_version","alias_value":"2604.00830v3","created_at":"2026-07-16T01:22:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.00830","created_at":"2026-07-16T01:22:39Z"},{"alias_kind":"pith_short_12","alias_value":"U55VRNHNZ2A3","created_at":"2026-07-16T01:22:39Z"},{"alias_kind":"pith_short_16","alias_value":"U55VRNHNZ2A3X3M5","created_at":"2026-07-16T01:22:39Z"},{"alias_kind":"pith_short_8","alias_value":"U55VRNHN","created_at":"2026-07-16T01:22:39Z"}],"graph_snapshots":[{"event_id":"sha256:4f63704784d9c241666ce350321c96aa9ad8299ef92de39bbe26c345f1aa060c","target":"graph","created_at":"2026-07-16T01:22:39Z","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/2604.00830/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time. At the core of TTL is an adaptation policy that updates the actor policy based on experience from previous episodes, thereby improving future behavior. Existing methods rely on fixed, hand-crafted adaptation policies rather than optimizing them for downstream improvement. We argue that optimal adaptation policies should be learned from task environments, not hand-engineered based on human intuition. To achieve this, we introduce Meta-TTL","authors_text":"Bryan Hooi, Hui Chen, Qian Wang, Yibo Li, Zhanzhi Lou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-01T12:41:01Z","title":"Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.00830","kind":"arxiv","version":3},"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":"sha256:16e86975b63b76b5de97f0a0d73b1b3e9dfc0c87786cd6acc5b521cf7f689037","target":"record","created_at":"2026-07-16T01:22:39Z","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":"9ef0953ba291c14cee32a1b5769374b919482a59d1c5f9b7385fb57e9cfef86a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-01T12:41:01Z","title_canon_sha256":"ec55d33803e67dd8ab7a32c70983f0e043951054d3af161b87484ef82731fc24"},"schema_version":"1.0","source":{"id":"2604.00830","kind":"arxiv","version":3}},"canonical_sha256":"a77b58b4edce81bbed9d3617e4a01425d2a9ddcacd1beef1da2db965e768aba6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a77b58b4edce81bbed9d3617e4a01425d2a9ddcacd1beef1da2db965e768aba6","first_computed_at":"2026-07-16T01:22:39.241612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T01:22:39.241612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MWEeBE/exYWZw7lAmGJpSFsJgzcLR2Ck32+cP0l76IH6tJFP4TqkoZJaLxKyKEcyD222a6LalaD4tVXmI5coBw==","signature_status":"signed_v1","signed_at":"2026-07-16T01:22:39.242553Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.00830","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16e86975b63b76b5de97f0a0d73b1b3e9dfc0c87786cd6acc5b521cf7f689037","sha256:4f63704784d9c241666ce350321c96aa9ad8299ef92de39bbe26c345f1aa060c"],"state_sha256":"ae9658a79261e368b10ee6f394f84998cbdfbf43607dc0f8631d411ebc21f427"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tXQBYGfqy9fTJP1vSX8b5uRfrD2kMO25cQaS7VZGI1r8LxIAKN1uJrVS0+p+hYhImch7SN8sM5vyKMMJdrHrCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T02:07:42.701792Z","bundle_sha256":"22beab4f299e2ef178b7a032739a5055eb3f3abcfbbc7c266e26cf1573e58b40"}}