{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:REY6EJHYIN4UZEEMRMIZSGW55V","short_pith_number":"pith:REY6EJHY","canonical_record":{"source":{"id":"2407.01863","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T00:24:01Z","cross_cats_sorted":[],"title_canon_sha256":"5776ef4e213e818b0b1d2352f4fec005c8c208c84c649a409ec10e91c4a556eb","abstract_canon_sha256":"0efbe7f48ccd6899c695d70a7b9c8f5cf4dbf01ce5f0c1fd497aeb0859fffdb8"},"schema_version":"1.0"},"canonical_sha256":"8931e224f843794c908c8b11991added4d10f23c794782275e9a460729c2db32","source":{"kind":"arxiv","id":"2407.01863","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01863","created_at":"2026-07-05T08:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01863v1","created_at":"2026-07-05T08:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01863","created_at":"2026-07-05T08:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"REY6EJHYIN4U","created_at":"2026-07-05T08:39:06Z"},{"alias_kind":"pith_short_16","alias_value":"REY6EJHYIN4UZEEM","created_at":"2026-07-05T08:39:06Z"},{"alias_kind":"pith_short_8","alias_value":"REY6EJHY","created_at":"2026-07-05T08:39:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:REY6EJHYIN4UZEEMRMIZSGW55V","target":"record","payload":{"canonical_record":{"source":{"id":"2407.01863","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T00:24:01Z","cross_cats_sorted":[],"title_canon_sha256":"5776ef4e213e818b0b1d2352f4fec005c8c208c84c649a409ec10e91c4a556eb","abstract_canon_sha256":"0efbe7f48ccd6899c695d70a7b9c8f5cf4dbf01ce5f0c1fd497aeb0859fffdb8"},"schema_version":"1.0"},"canonical_sha256":"8931e224f843794c908c8b11991added4d10f23c794782275e9a460729c2db32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:06.459561Z","signature_b64":"5636s+SYh+b3u0jv8qYbtcfSGrX+ITmAWe1RbSgKk8Awd9WqN23i3IqVFert08gurNeIZddbqBhskVd3L9BUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8931e224f843794c908c8b11991added4d10f23c794782275e9a460729c2db32","last_reissued_at":"2026-07-05T08:39:06.459038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:06.459038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.01863","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":"2026-07-05T08:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FG6V2Z5mBFakbuTBqYJq6S0jOTklD6k4yP/BVp2Qfsojs+2FAUcofXITr+slmCqjLR1E0FC/y2r2HXygWcE4CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:37:14.178084Z"},"content_sha256":"08e40ad31adaad28ab6786eedf2df9b872a170b33d2e7f80d0d82037733f379d","schema_version":"1.0","event_id":"sha256:08e40ad31adaad28ab6786eedf2df9b872a170b33d2e7f80d0d82037733f379d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:REY6EJHYIN4UZEEMRMIZSGW55V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Handong Zhao, Michael Saxon, Qiucheng Wu, Shiyu Chang, Trung Bui, William Yang Wang, Yang Zhang","submitted_at":"2024-07-02T00:24:01Z","abstract_excerpt":"Vision language models (VLMs) are an exciting emerging class of language models (LMs) that have merged classic LM capabilities with those of image processing systems. However, the ways that these capabilities combine are not always intuitive and warrant direct investigation. One understudied capability in VLMs is visual spatial planning -- the ability to comprehend the spatial arrangements of objects and devise action plans to achieve desired outcomes in visual scenes. In our study, we introduce VSP, a benchmark that 1) evaluates the spatial planning capability in these models in general, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01863","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/2407.01863/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":"2026-07-05T08:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ps/7gCm5B8GsXloARgBrjyZzRAExIjzhMUaxePbF68TLK+T8noIwsU383BOhdnHwerj7ODPonhVX+BezSqFjBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:37:14.178631Z"},"content_sha256":"cef3fd0ebf16d63ed3ce684b34a9f1bf43e230d120e8a75f759d2495e6946264","schema_version":"1.0","event_id":"sha256:cef3fd0ebf16d63ed3ce684b34a9f1bf43e230d120e8a75f759d2495e6946264"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/REY6EJHYIN4UZEEMRMIZSGW55V/bundle.json","state_url":"https://pith.science/pith/REY6EJHYIN4UZEEMRMIZSGW55V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/REY6EJHYIN4UZEEMRMIZSGW55V/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":"2026-08-22T23:37:14Z","links":{"resolver":"https://pith.science/pith/REY6EJHYIN4UZEEMRMIZSGW55V","bundle":"https://pith.science/pith/REY6EJHYIN4UZEEMRMIZSGW55V/bundle.json","state":"https://pith.science/pith/REY6EJHYIN4UZEEMRMIZSGW55V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/REY6EJHYIN4UZEEMRMIZSGW55V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:REY6EJHYIN4UZEEMRMIZSGW55V","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":"0efbe7f48ccd6899c695d70a7b9c8f5cf4dbf01ce5f0c1fd497aeb0859fffdb8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T00:24:01Z","title_canon_sha256":"5776ef4e213e818b0b1d2352f4fec005c8c208c84c649a409ec10e91c4a556eb"},"schema_version":"1.0","source":{"id":"2407.01863","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01863","created_at":"2026-07-05T08:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01863v1","created_at":"2026-07-05T08:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01863","created_at":"2026-07-05T08:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"REY6EJHYIN4U","created_at":"2026-07-05T08:39:06Z"},{"alias_kind":"pith_short_16","alias_value":"REY6EJHYIN4UZEEM","created_at":"2026-07-05T08:39:06Z"},{"alias_kind":"pith_short_8","alias_value":"REY6EJHY","created_at":"2026-07-05T08:39:06Z"}],"graph_snapshots":[{"event_id":"sha256:cef3fd0ebf16d63ed3ce684b34a9f1bf43e230d120e8a75f759d2495e6946264","target":"graph","created_at":"2026-07-05T08:39:06Z","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/2407.01863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision language models (VLMs) are an exciting emerging class of language models (LMs) that have merged classic LM capabilities with those of image processing systems. However, the ways that these capabilities combine are not always intuitive and warrant direct investigation. One understudied capability in VLMs is visual spatial planning -- the ability to comprehend the spatial arrangements of objects and devise action plans to achieve desired outcomes in visual scenes. In our study, we introduce VSP, a benchmark that 1) evaluates the spatial planning capability in these models in general, and ","authors_text":"Handong Zhao, Michael Saxon, Qiucheng Wu, Shiyu Chang, Trung Bui, William Yang Wang, Yang Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T00:24:01Z","title":"VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01863","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":"sha256:08e40ad31adaad28ab6786eedf2df9b872a170b33d2e7f80d0d82037733f379d","target":"record","created_at":"2026-07-05T08:39:06Z","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":"0efbe7f48ccd6899c695d70a7b9c8f5cf4dbf01ce5f0c1fd497aeb0859fffdb8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T00:24:01Z","title_canon_sha256":"5776ef4e213e818b0b1d2352f4fec005c8c208c84c649a409ec10e91c4a556eb"},"schema_version":"1.0","source":{"id":"2407.01863","kind":"arxiv","version":1}},"canonical_sha256":"8931e224f843794c908c8b11991added4d10f23c794782275e9a460729c2db32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8931e224f843794c908c8b11991added4d10f23c794782275e9a460729c2db32","first_computed_at":"2026-07-05T08:39:06.459038Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:06.459038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5636s+SYh+b3u0jv8qYbtcfSGrX+ITmAWe1RbSgKk8Awd9WqN23i3IqVFert08gurNeIZddbqBhskVd3L9BUDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:06.459561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01863","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08e40ad31adaad28ab6786eedf2df9b872a170b33d2e7f80d0d82037733f379d","sha256:cef3fd0ebf16d63ed3ce684b34a9f1bf43e230d120e8a75f759d2495e6946264"],"state_sha256":"f4f797b0c136c841191781247e84e1f9e187ad98b78f4d6dd4f256a367ecd71e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MONcSrfUd2OSgZaj2jpCa+Fj4aF9PBWcK/XZ/FX0J8LEHogSLLnkgBMQNiimAr7q1DwvCme/NNd1WcnCny1SBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T23:37:14.182454Z","bundle_sha256":"550125f8b83f6892d956b2805517693260e51bbe81d1d0d21f9dae5f04252ae6"}}