{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HQB6U55UMCWKRKA56N6T7RHXJP","short_pith_number":"pith:HQB6U55U","canonical_record":{"source":{"id":"2606.00183","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T14:58:03Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"ae910d9643cf04af5c555b6ab0b03dab1607341c25b35ed695b33ad503ce438e","abstract_canon_sha256":"cdb908e7a42aaade0f4023e706fde6451e14f9b7d29459bc0f48c8437e629a6b"},"schema_version":"1.0"},"canonical_sha256":"3c03ea77b460aca8a81df37d3fc4f74bdd9474ce51323dc3e263ec7e18c42328","source":{"kind":"arxiv","id":"2606.00183","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00183","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00183v1","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00183","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"HQB6U55UMCWK","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"pith_short_16","alias_value":"HQB6U55UMCWKRKA5","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"pith_short_8","alias_value":"HQB6U55U","created_at":"2026-06-02T01:03:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HQB6U55UMCWKRKA56N6T7RHXJP","target":"record","payload":{"canonical_record":{"source":{"id":"2606.00183","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T14:58:03Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"ae910d9643cf04af5c555b6ab0b03dab1607341c25b35ed695b33ad503ce438e","abstract_canon_sha256":"cdb908e7a42aaade0f4023e706fde6451e14f9b7d29459bc0f48c8437e629a6b"},"schema_version":"1.0"},"canonical_sha256":"3c03ea77b460aca8a81df37d3fc4f74bdd9474ce51323dc3e263ec7e18c42328","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:20.787809Z","signature_b64":"wTJZ+QGwBpq+voZAfIgyzVYhKY+c9sq04Y5PBko7Y6h1mtKtfTxtQBvOBV0rON/3SFm3aNxJqBRVt5tyNzBjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c03ea77b460aca8a81df37d3fc4f74bdd9474ce51323dc3e263ec7e18c42328","last_reissued_at":"2026-06-02T01:03:20.787402Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:20.787402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.00183","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZXj9WzuTnZrPqyUAK/UUGiLxyBWkFpTxFX56DlqvScON6xy+U0Rg2laKqIPveshPT6BrAVyh8WvJH5kM13UDAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T02:28:13.431135Z"},"content_sha256":"67db5d08a51749526e006ee25607464439a73c818a361158b2b28d02bc3f26d8","schema_version":"1.0","event_id":"sha256:67db5d08a51749526e006ee25607464439a73c818a361158b2b28d02bc3f26d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HQB6U55UMCWKRKA56N6T7RHXJP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Agentic Transformers Provably Learn to Search via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tong Yang, Yingbin Liang, Yuejie Chi, Yu Huang","submitted_at":"2026-05-29T14:58:03Z","abstract_excerpt":"Tree search is a central abstraction behind many language-agent reasoning and decision-making tasks: agents must explore actions, remember failures, and backtrack toward promising alternatives. Yet, we lack a theoretical understanding of how transformer-based policies acquire such search capabilities from the training dynamics of reinforcement learning (RL). We study this question in a stochastic $k$-ary tree environment, where an agentic transformer observes only its trajectory history through interaction and receives a terminal reward for reaching a hidden leaf goal node. We first construct "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00183","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/2606.00183/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":"2026-06-02T01:03:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cKUXhEY4s5qt0/f8qTHyzjKLA2XtZBfH1JrnmsT2zi8FhB2UJA8F3eOWvLzdOzuYXE3dyL7tijvRujmhvORACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T02:28:13.431528Z"},"content_sha256":"dcc6711c4acb5912dab26ee4fc91fc1bc3c4776b0e0537ab9aacec5b38c24eef","schema_version":"1.0","event_id":"sha256:dcc6711c4acb5912dab26ee4fc91fc1bc3c4776b0e0537ab9aacec5b38c24eef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HQB6U55UMCWKRKA56N6T7RHXJP/bundle.json","state_url":"https://pith.science/pith/HQB6U55UMCWKRKA56N6T7RHXJP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HQB6U55UMCWKRKA56N6T7RHXJP/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":"2026-06-03T02:28:13Z","links":{"resolver":"https://pith.science/pith/HQB6U55UMCWKRKA56N6T7RHXJP","bundle":"https://pith.science/pith/HQB6U55UMCWKRKA56N6T7RHXJP/bundle.json","state":"https://pith.science/pith/HQB6U55UMCWKRKA56N6T7RHXJP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HQB6U55UMCWKRKA56N6T7RHXJP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HQB6U55UMCWKRKA56N6T7RHXJP","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":"cdb908e7a42aaade0f4023e706fde6451e14f9b7d29459bc0f48c8437e629a6b","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T14:58:03Z","title_canon_sha256":"ae910d9643cf04af5c555b6ab0b03dab1607341c25b35ed695b33ad503ce438e"},"schema_version":"1.0","source":{"id":"2606.00183","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00183","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00183v1","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00183","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"HQB6U55UMCWK","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"pith_short_16","alias_value":"HQB6U55UMCWKRKA5","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"pith_short_8","alias_value":"HQB6U55U","created_at":"2026-06-02T01:03:20Z"}],"graph_snapshots":[{"event_id":"sha256:dcc6711c4acb5912dab26ee4fc91fc1bc3c4776b0e0537ab9aacec5b38c24eef","target":"graph","created_at":"2026-06-02T01:03:20Z","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/2606.00183/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tree search is a central abstraction behind many language-agent reasoning and decision-making tasks: agents must explore actions, remember failures, and backtrack toward promising alternatives. Yet, we lack a theoretical understanding of how transformer-based policies acquire such search capabilities from the training dynamics of reinforcement learning (RL). We study this question in a stochastic $k$-ary tree environment, where an agentic transformer observes only its trajectory history through interaction and receives a terminal reward for reaching a hidden leaf goal node. We first construct ","authors_text":"Tong Yang, Yingbin Liang, Yuejie Chi, Yu Huang","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T14:58:03Z","title":"Agentic Transformers Provably Learn to Search via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00183","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":"sha256:67db5d08a51749526e006ee25607464439a73c818a361158b2b28d02bc3f26d8","target":"record","created_at":"2026-06-02T01:03:20Z","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":"cdb908e7a42aaade0f4023e706fde6451e14f9b7d29459bc0f48c8437e629a6b","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T14:58:03Z","title_canon_sha256":"ae910d9643cf04af5c555b6ab0b03dab1607341c25b35ed695b33ad503ce438e"},"schema_version":"1.0","source":{"id":"2606.00183","kind":"arxiv","version":1}},"canonical_sha256":"3c03ea77b460aca8a81df37d3fc4f74bdd9474ce51323dc3e263ec7e18c42328","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c03ea77b460aca8a81df37d3fc4f74bdd9474ce51323dc3e263ec7e18c42328","first_computed_at":"2026-06-02T01:03:20.787402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:20.787402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wTJZ+QGwBpq+voZAfIgyzVYhKY+c9sq04Y5PBko7Y6h1mtKtfTxtQBvOBV0rON/3SFm3aNxJqBRVt5tyNzBjCg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:20.787809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00183","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67db5d08a51749526e006ee25607464439a73c818a361158b2b28d02bc3f26d8","sha256:dcc6711c4acb5912dab26ee4fc91fc1bc3c4776b0e0537ab9aacec5b38c24eef"],"state_sha256":"ccec9c2e422211d5f0459bf2ef883d478190f8851d41c4603ef033a8ed6b14d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NUdbFfqBeKb4o4Cdsbufk5EHAXOHXla8yPJ5YqSTt8Pg9m/gjtnvbWdfmwHngb7OS3a6SI42rbTStPIOIV6bDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T02:28:13.433604Z","bundle_sha256":"591d2aa309465ad7d854454db5477473fbd2030521391886b864f04bc1eb3375"}}