{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:D6OZN2BGCBOAZUVSRWQI6OCIJT","short_pith_number":"pith:D6OZN2BG","canonical_record":{"source":{"id":"2607.08894","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-09T19:34:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eb6929a350348aef39761f6363edcbb073003cedfe87811f02753eb405f3f33f","abstract_canon_sha256":"089d92dd77f09abe51aae8e8978ed507163fd545c5d6c37a85b0fe116cee996a"},"schema_version":"1.0"},"canonical_sha256":"1f9d96e826105c0cd2b28da08f38484ce6df2f485c74e07ed5d48c7a889238e1","source":{"kind":"arxiv","id":"2607.08894","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08894","created_at":"2026-07-13T00:17:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08894v1","created_at":"2026-07-13T00:17:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08894","created_at":"2026-07-13T00:17:25Z"},{"alias_kind":"pith_short_12","alias_value":"D6OZN2BGCBOA","created_at":"2026-07-13T00:17:25Z"},{"alias_kind":"pith_short_16","alias_value":"D6OZN2BGCBOAZUVS","created_at":"2026-07-13T00:17:25Z"},{"alias_kind":"pith_short_8","alias_value":"D6OZN2BG","created_at":"2026-07-13T00:17:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:D6OZN2BGCBOAZUVSRWQI6OCIJT","target":"record","payload":{"canonical_record":{"source":{"id":"2607.08894","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-09T19:34:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eb6929a350348aef39761f6363edcbb073003cedfe87811f02753eb405f3f33f","abstract_canon_sha256":"089d92dd77f09abe51aae8e8978ed507163fd545c5d6c37a85b0fe116cee996a"},"schema_version":"1.0"},"canonical_sha256":"1f9d96e826105c0cd2b28da08f38484ce6df2f485c74e07ed5d48c7a889238e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T00:17:25.359709Z","signature_b64":"Vlrn5mhjDv9+q4OpF4X6oaFN26BFT8yF48jI8d/SSmjbVxK1Jb9Ukd/c0W6b1vizs8ucLv8nsy2bgu2zD684Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f9d96e826105c0cd2b28da08f38484ce6df2f485c74e07ed5d48c7a889238e1","last_reissued_at":"2026-07-13T00:17:25.358564Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T00:17:25.358564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.08894","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":"2026-07-13T00:17:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NnNpOMWSqBoRjx0aXkrWh+JzLV16tnh/c3oR6wAhIQb344Am1mgGL/EDzJSdhEcjEQ3QxHCGnbanpbohocGXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:56:30.409848Z"},"content_sha256":"f216fa0d2d6f5006e93c93bac540d56283f243e9314c20aa073bc457e0611b87","schema_version":"1.0","event_id":"sha256:f216fa0d2d6f5006e93c93bac540d56283f243e9314c20aa073bc457e0611b87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:D6OZN2BGCBOAZUVSRWQI6OCIJT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Dymitr Nowicki, Maureese Williams","submitted_at":"2026-07-09T19:34:29Z","abstract_excerpt":"Large Language Model (LLM) agents have shown promise in multi-step planning tasks, but existing approaches like LATS (Language Agent Tree Search) and ReAct rely heavily on LLM inference during planning, leading to high computational costs and stochastic behavior. We present \\textbf{GATS} (Graph-Augmented Tree Search), a planning framework that combines systematic UCB1-based tree search with a layered world model to eliminate LLM calls during inference while achieving superior planning performance. Our three-layer world model integrates: (L1) exact symbolic action matching, (L2) statistics lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08894","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/2607.08894/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":"2026-07-13T00:17:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gMrso8eozrXPi3iDcuVXUwf70I1M/UGK32UZ2+OkScyPF1s3DXnYMZfu9+5D5eEEOyZIzEUPCtQQXfBiay6xCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:56:30.410380Z"},"content_sha256":"bd658d1de5d780d1c49a3c50884764d8a1984db2832e87d131e273633349af32","schema_version":"1.0","event_id":"sha256:bd658d1de5d780d1c49a3c50884764d8a1984db2832e87d131e273633349af32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D6OZN2BGCBOAZUVSRWQI6OCIJT/bundle.json","state_url":"https://pith.science/pith/D6OZN2BGCBOAZUVSRWQI6OCIJT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D6OZN2BGCBOAZUVSRWQI6OCIJT/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":"2026-08-14T19:56:30Z","links":{"resolver":"https://pith.science/pith/D6OZN2BGCBOAZUVSRWQI6OCIJT","bundle":"https://pith.science/pith/D6OZN2BGCBOAZUVSRWQI6OCIJT/bundle.json","state":"https://pith.science/pith/D6OZN2BGCBOAZUVSRWQI6OCIJT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D6OZN2BGCBOAZUVSRWQI6OCIJT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D6OZN2BGCBOAZUVSRWQI6OCIJT","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":"089d92dd77f09abe51aae8e8978ed507163fd545c5d6c37a85b0fe116cee996a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-09T19:34:29Z","title_canon_sha256":"eb6929a350348aef39761f6363edcbb073003cedfe87811f02753eb405f3f33f"},"schema_version":"1.0","source":{"id":"2607.08894","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08894","created_at":"2026-07-13T00:17:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08894v1","created_at":"2026-07-13T00:17:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08894","created_at":"2026-07-13T00:17:25Z"},{"alias_kind":"pith_short_12","alias_value":"D6OZN2BGCBOA","created_at":"2026-07-13T00:17:25Z"},{"alias_kind":"pith_short_16","alias_value":"D6OZN2BGCBOAZUVS","created_at":"2026-07-13T00:17:25Z"},{"alias_kind":"pith_short_8","alias_value":"D6OZN2BG","created_at":"2026-07-13T00:17:25Z"}],"graph_snapshots":[{"event_id":"sha256:bd658d1de5d780d1c49a3c50884764d8a1984db2832e87d131e273633349af32","target":"graph","created_at":"2026-07-13T00:17:25Z","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/2607.08894/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM) agents have shown promise in multi-step planning tasks, but existing approaches like LATS (Language Agent Tree Search) and ReAct rely heavily on LLM inference during planning, leading to high computational costs and stochastic behavior. We present \\textbf{GATS} (Graph-Augmented Tree Search), a planning framework that combines systematic UCB1-based tree search with a layered world model to eliminate LLM calls during inference while achieving superior planning performance. Our three-layer world model integrates: (L1) exact symbolic action matching, (L2) statistics lear","authors_text":"Dymitr Nowicki, Maureese Williams","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-09T19:34:29Z","title":"GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08894","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:f216fa0d2d6f5006e93c93bac540d56283f243e9314c20aa073bc457e0611b87","target":"record","created_at":"2026-07-13T00:17:25Z","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":"089d92dd77f09abe51aae8e8978ed507163fd545c5d6c37a85b0fe116cee996a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-09T19:34:29Z","title_canon_sha256":"eb6929a350348aef39761f6363edcbb073003cedfe87811f02753eb405f3f33f"},"schema_version":"1.0","source":{"id":"2607.08894","kind":"arxiv","version":1}},"canonical_sha256":"1f9d96e826105c0cd2b28da08f38484ce6df2f485c74e07ed5d48c7a889238e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f9d96e826105c0cd2b28da08f38484ce6df2f485c74e07ed5d48c7a889238e1","first_computed_at":"2026-07-13T00:17:25.358564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T00:17:25.358564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vlrn5mhjDv9+q4OpF4X6oaFN26BFT8yF48jI8d/SSmjbVxK1Jb9Ukd/c0W6b1vizs8ucLv8nsy2bgu2zD684Dw==","signature_status":"signed_v1","signed_at":"2026-07-13T00:17:25.359709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08894","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f216fa0d2d6f5006e93c93bac540d56283f243e9314c20aa073bc457e0611b87","sha256:bd658d1de5d780d1c49a3c50884764d8a1984db2832e87d131e273633349af32"],"state_sha256":"5eca9d080c70774b8653899fd247a1f172d4ba6dc5f08d74b7c5e825abf4488c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"re2IbG3dMe/ydXYDPhqi0WrfXHrhKZBvL1nWgkX7O1I/yLoJthWrR1Kp1jik/rVM1McUByXbU8ZBUL1ERRelCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:56:30.413815Z","bundle_sha256":"aeb9afa59d36c4f38e44be84375a580ddc2fa6d704b4c8576b3b3978471f8d31"}}