{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IINZ4ZTTR4VBJWHZ7WNGW3N4JZ","short_pith_number":"pith:IINZ4ZTT","schema_version":"1.0","canonical_sha256":"421b9e66738f2a14d8f9fd9a6b6dbc4e49d6d6a4f2ee1c544eb9e08ec5145ac9","source":{"kind":"arxiv","id":"2608.11692","version":1},"attestation_state":"computed","paper":{"title":"HUGIN: Enhancing Vision-Language Planning for Autonomous Logistics Sorting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cangtian Zhou, Haotian Wang, Kebin Liu, Ke Ma, Li Liu, Xikai Sun, Xu Wang, Yunhao Liu, Zaishu Chen","submitted_at":"2026-08-12T06:04:27Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.11692","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-12T06:04:27Z","cross_cats_sorted":[],"title_canon_sha256":"6c9bc08691aa92cd1365b35f37c17d4f4beef524dbd1f60c887af0bffeba169a","abstract_canon_sha256":"fd3ef9dee320cfc046b15680f4e899971c9828ba6e93b2fcbc3cc1a16573e3f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:27:51.171586Z","signature_b64":"MRLLlCB1Ke5PpXQ1WROB96w3Z4UNJX2S4Dbd7iP9mjPXJ605dFDyVlcWIpY3ivbdJODjKY7Pp0c0Wu/RYh43CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"421b9e66738f2a14d8f9fd9a6b6dbc4e49d6d6a4f2ee1c544eb9e08ec5145ac9","last_reissued_at":"2026-08-13T01:27:51.169166Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:27:51.169166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HUGIN: Enhancing Vision-Language Planning for Autonomous Logistics Sorting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cangtian Zhou, Haotian Wang, Kebin Liu, Ke Ma, Li Liu, Xikai Sun, Xu Wang, Yunhao Liu, Zaishu Chen","submitted_at":"2026-08-12T06:04:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11692","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/2608.11692/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.11692","created_at":"2026-08-13T01:27:51.170369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.11692v1","created_at":"2026-08-13T01:27:51.170369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11692","created_at":"2026-08-13T01:27:51.170369+00:00"},{"alias_kind":"pith_short_12","alias_value":"IINZ4ZTTR4VB","created_at":"2026-08-13T01:27:51.170369+00:00"},{"alias_kind":"pith_short_16","alias_value":"IINZ4ZTTR4VBJWHZ","created_at":"2026-08-13T01:27:51.170369+00:00"},{"alias_kind":"pith_short_8","alias_value":"IINZ4ZTT","created_at":"2026-08-13T01:27:51.170369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IINZ4ZTTR4VBJWHZ7WNGW3N4JZ","json":"https://pith.science/pith/IINZ4ZTTR4VBJWHZ7WNGW3N4JZ.json","graph_json":"https://pith.science/api/pith-number/IINZ4ZTTR4VBJWHZ7WNGW3N4JZ/graph.json","events_json":"https://pith.science/api/pith-number/IINZ4ZTTR4VBJWHZ7WNGW3N4JZ/events.json","paper":"https://pith.science/paper/IINZ4ZTT"},"agent_actions":{"view_html":"https://pith.science/pith/IINZ4ZTTR4VBJWHZ7WNGW3N4JZ","download_json":"https://pith.science/pith/IINZ4ZTTR4VBJWHZ7WNGW3N4JZ.json","view_paper":"https://pith.science/paper/IINZ4ZTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.11692&json=true","fetch_graph":"https://pith.science/api/pith-number/IINZ4ZTTR4VBJWHZ7WNGW3N4JZ/graph.json","fetch_events":"https://pith.science/api/pith-number/IINZ4ZTTR4VBJWHZ7WNGW3N4JZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IINZ4ZTTR4VBJWHZ7WNGW3N4JZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IINZ4ZTTR4VBJWHZ7WNGW3N4JZ/action/storage_attestation","attest_author":"https://pith.science/pith/IINZ4ZTTR4VBJWHZ7WNGW3N4JZ/action/author_attestation","sign_citation":"https://pith.science/pith/IINZ4ZTTR4VBJWHZ7WNGW3N4JZ/action/citation_signature","submit_replication":"https://pith.science/pith/IINZ4ZTTR4VBJWHZ7WNGW3N4JZ/action/replication_record"}},"created_at":"2026-08-13T01:27:51.170369+00:00","updated_at":"2026-08-13T01:27:51.170369+00:00"}