{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NX3VW23TLUYQ7LDNLPAJGQUMYF","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":"2ebe52d0beed5ebb0273e1540e0c18d7b60aae9ddae4d1da81fbb5096ae7aa80","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-04-12T03:09:44Z","title_canon_sha256":"f9df4a0442c5866e1f58b9ecce9ea10256ed2be905ecb74482c27e26ef8f850e"},"schema_version":"1.0","source":{"id":"2604.10432","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.10432","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2604.10432v3","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.10432","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"NX3VW23TLUYQ","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"NX3VW23TLUYQ7LDN","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"NX3VW23T","created_at":"2026-06-01T01:02:39Z"}],"graph_snapshots":[{"event_id":"sha256:b5ca29225fe53b5364b6b3eaf2555a62d377ad7c1ee4fbc27e9d9f51d9dfde28","target":"graph","created_at":"2026-06-01T01:02:39Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"AnySlot significantly outperforms flat VLA baselines and previous modular grounding methods in zero-shot slot-level placement."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That generating a reliable scene marker from language instructions is always possible and that the goal-conditioned policy can consistently achieve the required sub-centimeter spatial accuracy without additional fine-tuning or domain-specific data."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"AnySlot decouples language grounding from low-level control by inserting an explicit visual goal image, yielding better zero-shot performance on precise slot placement tasks than flat VLA policies."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"AnySlot generates an explicit visual scene marker from language to let goal-conditioned VLA policies handle precise zero-shot slot placement."}],"snapshot_sha256":"7b2b38b702b6d476e029a33606fc3f8af3ad940e87e0cc0eafb0a05e71722c6c"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.10432/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) policies have emerged as a versatile paradigm for generalist robotic manipulation. However, precise object placement under compositional language remains challenging for end-to-end VLA policies. Slot-level placement requires reliable slot grounding and centimeter-level geometric precision. To this end, we propose AnySlot, a framework that reduces compositional complexity by introducing an explicit spatial visual goal between language grounding and control. AnySlot converts language into a visual goal by rendering a spatial marker at the intended slot, then executes","authors_text":"Ci-Jyun Liang, Jorge Mendez-Mendz, Qinbo Zhang, Qi Su, Rongtao Xu, Sifan Zhou, Zhaofeng Hu","cross_cats":[],"headline":"AnySlot generates an explicit visual scene marker from language to let goal-conditioned VLA policies handle precise zero-shot slot placement.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-04-12T03:09:44Z","title":"AnySlot: Goal-Conditioned Vision-Language-Action Policies for Zero-Shot Slot-Level Placement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.10432","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-10T16:38:01.997535Z","id":"dfca2dba-48cd-4dbf-8ad6-9cd9d84a40f0","model_set":{"reader":"grok-4.3"},"one_line_summary":"AnySlot decouples language grounding from low-level control by inserting an explicit visual goal image, yielding better zero-shot performance on precise slot placement tasks than flat VLA policies.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"AnySlot generates an explicit visual scene marker from language to let goal-conditioned VLA policies handle precise zero-shot slot placement.","strongest_claim":"AnySlot significantly outperforms flat VLA baselines and previous modular grounding methods in zero-shot slot-level placement.","weakest_assumption":"That generating a reliable scene marker from language instructions is always possible and that the goal-conditioned policy can consistently achieve the required sub-centimeter spatial accuracy without additional fine-tuning or domain-specific data."}},"verdict_id":"dfca2dba-48cd-4dbf-8ad6-9cd9d84a40f0"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:62fa45bd9b30e21b5bb2580e1565e264df939b0b287fde1e2faee754314ba452","target":"record","created_at":"2026-06-01T01:02:39Z","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":"2ebe52d0beed5ebb0273e1540e0c18d7b60aae9ddae4d1da81fbb5096ae7aa80","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-04-12T03:09:44Z","title_canon_sha256":"f9df4a0442c5866e1f58b9ecce9ea10256ed2be905ecb74482c27e26ef8f850e"},"schema_version":"1.0","source":{"id":"2604.10432","kind":"arxiv","version":3}},"canonical_sha256":"6df75b6b735d310fac6d5bc093428cc17b12fdbe0aad900ef329b70ee1704c1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6df75b6b735d310fac6d5bc093428cc17b12fdbe0aad900ef329b70ee1704c1e","first_computed_at":"2026-06-01T01:02:39.392374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:39.392374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f0T34sioLBMMXxnNxrDO3hFkRtuNiIL0TUeyklYt3UrfkUMkknXvu41WLRhNCDFfFEjQEGxT+6I0Zb6+0zC4Ag==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:39.393447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.10432","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62fa45bd9b30e21b5bb2580e1565e264df939b0b287fde1e2faee754314ba452","sha256:b5ca29225fe53b5364b6b3eaf2555a62d377ad7c1ee4fbc27e9d9f51d9dfde28"],"state_sha256":"dc08be625d61a165a6bfea0052edb9b32d56f652dcf6efedddf4d462e7607954"}