{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IINZ4ZTTR4VBJWHZ7WNGW3N4JZ","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":"fd3ef9dee320cfc046b15680f4e899971c9828ba6e93b2fcbc3cc1a16573e3f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-12T06:04:27Z","title_canon_sha256":"6c9bc08691aa92cd1365b35f37c17d4f4beef524dbd1f60c887af0bffeba169a"},"schema_version":"1.0","source":{"id":"2608.11692","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11692","created_at":"2026-08-13T01:27:51Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11692v1","created_at":"2026-08-13T01:27:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11692","created_at":"2026-08-13T01:27:51Z"},{"alias_kind":"pith_short_12","alias_value":"IINZ4ZTTR4VB","created_at":"2026-08-13T01:27:51Z"},{"alias_kind":"pith_short_16","alias_value":"IINZ4ZTTR4VBJWHZ","created_at":"2026-08-13T01:27:51Z"},{"alias_kind":"pith_short_8","alias_value":"IINZ4ZTT","created_at":"2026-08-13T01:27:51Z"}],"graph_snapshots":[{"event_id":"sha256:35e5e41fbc47461063083ff38dde5efcdf342c78d9fdb1101166780eed40a305","target":"graph","created_at":"2026-08-13T01:27:51Z","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/2608.11692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous logistics sorting systems (ALSS) are an important industrial application of embodied AI, which requires joint planning over spatially disjoint camera views. We formulate this setting as Joint Multi-Scene Understanding (JMSU). With open-world visual understanding and task-planning capabilities, vision-language models (VLMs) are promising candidates for JMSU. However, directly applying existing VLMs to JMSU is non-trivial due to scarce cross-scene supervision and attention dispersion caused by long visual context in JMSU. To address these challenges, we propose HUGIN, a training frame","authors_text":"Cangtian Zhou, Haotian Wang, Kebin Liu, Ke Ma, Li Liu, Xikai Sun, Xu Wang, Yunhao Liu, Zaishu Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-12T06:04:27Z","title":"HUGIN: Enhancing Vision-Language Planning for Autonomous Logistics Sorting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11692","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:a4778ac930619b4ded6b42a9098015af81b9e00232ecd3652d73002fdfc45cc3","target":"record","created_at":"2026-08-13T01:27:51Z","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":"fd3ef9dee320cfc046b15680f4e899971c9828ba6e93b2fcbc3cc1a16573e3f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-12T06:04:27Z","title_canon_sha256":"6c9bc08691aa92cd1365b35f37c17d4f4beef524dbd1f60c887af0bffeba169a"},"schema_version":"1.0","source":{"id":"2608.11692","kind":"arxiv","version":1}},"canonical_sha256":"421b9e66738f2a14d8f9fd9a6b6dbc4e49d6d6a4f2ee1c544eb9e08ec5145ac9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"421b9e66738f2a14d8f9fd9a6b6dbc4e49d6d6a4f2ee1c544eb9e08ec5145ac9","first_computed_at":"2026-08-13T01:27:51.169166Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T01:27:51.169166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MRLLlCB1Ke5PpXQ1WROB96w3Z4UNJX2S4Dbd7iP9mjPXJ605dFDyVlcWIpY3ivbdJODjKY7Pp0c0Wu/RYh43CA==","signature_status":"signed_v1","signed_at":"2026-08-13T01:27:51.171586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11692","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4778ac930619b4ded6b42a9098015af81b9e00232ecd3652d73002fdfc45cc3","sha256:35e5e41fbc47461063083ff38dde5efcdf342c78d9fdb1101166780eed40a305"],"state_sha256":"057d686c8780f3acafd8dc200806f096bfe8ae2e21e17f8fa93103921e44aeab"}