{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IUGFP2LJFD3ZRXCFCTTRDTPDMY","short_pith_number":"pith:IUGFP2LJ","canonical_record":{"source":{"id":"2507.23589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-31T14:25:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4a0f35e832476c4ad10f3f2cb2eba0cf0858a5a9a5f3bf251fb7b709bb90bcd3","abstract_canon_sha256":"76af78c8e06e9d9476ec2cc75906005210c7fb706a238a03580f73d26862e753"},"schema_version":"1.0"},"canonical_sha256":"450c57e96928f798dc4514e711cde36626fe79859b1dfa36b5326759986d6c1f","source":{"kind":"arxiv","id":"2507.23589","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23589","created_at":"2026-07-05T11:46:27Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23589v1","created_at":"2026-07-05T11:46:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23589","created_at":"2026-07-05T11:46:27Z"},{"alias_kind":"pith_short_12","alias_value":"IUGFP2LJFD3Z","created_at":"2026-07-05T11:46:27Z"},{"alias_kind":"pith_short_16","alias_value":"IUGFP2LJFD3ZRXCF","created_at":"2026-07-05T11:46:27Z"},{"alias_kind":"pith_short_8","alias_value":"IUGFP2LJ","created_at":"2026-07-05T11:46:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IUGFP2LJFD3ZRXCFCTTRDTPDMY","target":"record","payload":{"canonical_record":{"source":{"id":"2507.23589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-31T14:25:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4a0f35e832476c4ad10f3f2cb2eba0cf0858a5a9a5f3bf251fb7b709bb90bcd3","abstract_canon_sha256":"76af78c8e06e9d9476ec2cc75906005210c7fb706a238a03580f73d26862e753"},"schema_version":"1.0"},"canonical_sha256":"450c57e96928f798dc4514e711cde36626fe79859b1dfa36b5326759986d6c1f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:27.325886Z","signature_b64":"E9FsAvp2bZrMq2/aajuS5Ab72FY6adhzDGYQBAwhLToAlmbXZPyi3lEqSYIKyCTUCHOUAn92NzxxYQ2WZFrvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"450c57e96928f798dc4514e711cde36626fe79859b1dfa36b5326759986d6c1f","last_reissued_at":"2026-07-05T11:46:27.325307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:27.325307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.23589","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":"2026-07-05T11:46:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oht4y/KdXPXfeiQ1T0sd7V2WFAYbiLRjS2x3eGKt6aqWIJat/ma7X+pt2jk5jftGgkvAOUR4pxHmooIYJBXFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:26:18.162788Z"},"content_sha256":"9548416fa3a6e9b47c0bf4e7ba8c7c80fb5ee53a14ffdd1b51df07c69aa3ed54","schema_version":"1.0","event_id":"sha256:9548416fa3a6e9b47c0bf4e7ba8c7c80fb5ee53a14ffdd1b51df07c69aa3ed54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IUGFP2LJFD3ZRXCFCTTRDTPDMY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Kai Goebel, Patrik Zips","submitted_at":"2025-07-31T14:25:54Z","abstract_excerpt":"Recent advancements in Large Language Models have sparked interest in their potential for robotic task planning. While these models demonstrate strong generative capabilities, their effectiveness in producing structured and executable plans remains uncertain. This paper presents a systematic evaluation of a broad spectrum of current state of the art language models, each directly prompted using Planning Domain Definition Language domain and problem files, and compares their planning performance with the Fast Downward planner across a variety of benchmarks. In addition to measuring success rate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23589","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/2507.23589/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":"2026-07-05T11:46:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"osl/24QuuRQAq/oMXuM0vrj7kvoiC0K0E1aB2HDgDOMYMqI5OZzb5pczP1HSu0kjk7iB64hBQp7j99PC0RYrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:26:18.163305Z"},"content_sha256":"947090e5ef46b3b4756bf73b84bb1697f63b069020e3b32a4e1a28e00efc866b","schema_version":"1.0","event_id":"sha256:947090e5ef46b3b4756bf73b84bb1697f63b069020e3b32a4e1a28e00efc866b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IUGFP2LJFD3ZRXCFCTTRDTPDMY/bundle.json","state_url":"https://pith.science/pith/IUGFP2LJFD3ZRXCFCTTRDTPDMY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IUGFP2LJFD3ZRXCFCTTRDTPDMY/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":"2026-08-07T23:26:18Z","links":{"resolver":"https://pith.science/pith/IUGFP2LJFD3ZRXCFCTTRDTPDMY","bundle":"https://pith.science/pith/IUGFP2LJFD3ZRXCFCTTRDTPDMY/bundle.json","state":"https://pith.science/pith/IUGFP2LJFD3ZRXCFCTTRDTPDMY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IUGFP2LJFD3ZRXCFCTTRDTPDMY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IUGFP2LJFD3ZRXCFCTTRDTPDMY","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":"76af78c8e06e9d9476ec2cc75906005210c7fb706a238a03580f73d26862e753","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-31T14:25:54Z","title_canon_sha256":"4a0f35e832476c4ad10f3f2cb2eba0cf0858a5a9a5f3bf251fb7b709bb90bcd3"},"schema_version":"1.0","source":{"id":"2507.23589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23589","created_at":"2026-07-05T11:46:27Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23589v1","created_at":"2026-07-05T11:46:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23589","created_at":"2026-07-05T11:46:27Z"},{"alias_kind":"pith_short_12","alias_value":"IUGFP2LJFD3Z","created_at":"2026-07-05T11:46:27Z"},{"alias_kind":"pith_short_16","alias_value":"IUGFP2LJFD3ZRXCF","created_at":"2026-07-05T11:46:27Z"},{"alias_kind":"pith_short_8","alias_value":"IUGFP2LJ","created_at":"2026-07-05T11:46:27Z"}],"graph_snapshots":[{"event_id":"sha256:947090e5ef46b3b4756bf73b84bb1697f63b069020e3b32a4e1a28e00efc866b","target":"graph","created_at":"2026-07-05T11:46:27Z","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/2507.23589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Language Models have sparked interest in their potential for robotic task planning. While these models demonstrate strong generative capabilities, their effectiveness in producing structured and executable plans remains uncertain. This paper presents a systematic evaluation of a broad spectrum of current state of the art language models, each directly prompted using Planning Domain Definition Language domain and problem files, and compares their planning performance with the Fast Downward planner across a variety of benchmarks. In addition to measuring success rate","authors_text":"Kai Goebel, Patrik Zips","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-31T14:25:54Z","title":"Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23589","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":"sha256:9548416fa3a6e9b47c0bf4e7ba8c7c80fb5ee53a14ffdd1b51df07c69aa3ed54","target":"record","created_at":"2026-07-05T11:46:27Z","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":"76af78c8e06e9d9476ec2cc75906005210c7fb706a238a03580f73d26862e753","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-31T14:25:54Z","title_canon_sha256":"4a0f35e832476c4ad10f3f2cb2eba0cf0858a5a9a5f3bf251fb7b709bb90bcd3"},"schema_version":"1.0","source":{"id":"2507.23589","kind":"arxiv","version":1}},"canonical_sha256":"450c57e96928f798dc4514e711cde36626fe79859b1dfa36b5326759986d6c1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"450c57e96928f798dc4514e711cde36626fe79859b1dfa36b5326759986d6c1f","first_computed_at":"2026-07-05T11:46:27.325307Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:27.325307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E9FsAvp2bZrMq2/aajuS5Ab72FY6adhzDGYQBAwhLToAlmbXZPyi3lEqSYIKyCTUCHOUAn92NzxxYQ2WZFrvCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:27.325886Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.23589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9548416fa3a6e9b47c0bf4e7ba8c7c80fb5ee53a14ffdd1b51df07c69aa3ed54","sha256:947090e5ef46b3b4756bf73b84bb1697f63b069020e3b32a4e1a28e00efc866b"],"state_sha256":"71baa22e31cd03339fc1f04576d3a7ed97c2af8ef583669e1886256ae7fad368"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i/BZbXKrp0XRnwqAluxpox0+CKZ/xTvOS2ggiTqCeUqTA4HpgMEAQtCI4jFaLh6k3DSLI5S2+Se9pySdTiirDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:26:18.168518Z","bundle_sha256":"96c3d8f0c7516841d7530ba7ebc15a35654a24ac577be8d190d68b14700687fd"}}