{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6YPC47WC4ZDPCDEYK7LDLVHLWH","short_pith_number":"pith:6YPC47WC","canonical_record":{"source":{"id":"2608.08839","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-09T17:59:35Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3af0755b4e06f5faebc2ceb4bed95d2dcd76fd38244136f2b7d4207b1a44383e","abstract_canon_sha256":"292c4226967c8b56d26d2dbb24cb7028176c64a1de1c0830d62117b7e3150062"},"schema_version":"1.0"},"canonical_sha256":"f61e2e7ec2e646f10c9857d635d4ebb1fbc7a0cd7dd145a42a1d2c413bf7fd8d","source":{"kind":"arxiv","id":"2608.08839","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08839","created_at":"2026-08-11T01:25:29Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08839v1","created_at":"2026-08-11T01:25:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08839","created_at":"2026-08-11T01:25:29Z"},{"alias_kind":"pith_short_12","alias_value":"6YPC47WC4ZDP","created_at":"2026-08-11T01:25:29Z"},{"alias_kind":"pith_short_16","alias_value":"6YPC47WC4ZDPCDEY","created_at":"2026-08-11T01:25:29Z"},{"alias_kind":"pith_short_8","alias_value":"6YPC47WC","created_at":"2026-08-11T01:25:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6YPC47WC4ZDPCDEYK7LDLVHLWH","target":"record","payload":{"canonical_record":{"source":{"id":"2608.08839","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-09T17:59:35Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3af0755b4e06f5faebc2ceb4bed95d2dcd76fd38244136f2b7d4207b1a44383e","abstract_canon_sha256":"292c4226967c8b56d26d2dbb24cb7028176c64a1de1c0830d62117b7e3150062"},"schema_version":"1.0"},"canonical_sha256":"f61e2e7ec2e646f10c9857d635d4ebb1fbc7a0cd7dd145a42a1d2c413bf7fd8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:25:29.593761Z","signature_b64":"2UHpJt/yNNEKoKqARCG7/utmlaBfyEAVIg2CBlf8WGpa05JrCLl+HFmCBmogz3UEybwXtPeZicTtJzWk6U5YDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f61e2e7ec2e646f10c9857d635d4ebb1fbc7a0cd7dd145a42a1d2c413bf7fd8d","last_reissued_at":"2026-08-11T01:25:29.591079Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:25:29.591079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.08839","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":"2026-08-11T01:25:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BXMKv7e7e4QrCXWZeVsF1JuFeGMBtUqXqUx1ANPUoDwAk+vbToOEG9a44/b5pv0KPKXau8Kv9TL648Lv0907Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:04:13.154244Z"},"content_sha256":"4aa909be39a8788ad99542eb2fb9febbd2ce81c792051d6952c2abfe21bfe7ee","schema_version":"1.0","event_id":"sha256:4aa909be39a8788ad99542eb2fb9febbd2ce81c792051d6952c2abfe21bfe7ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6YPC47WC4ZDPCDEYK7LDLVHLWH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SG-WAM: Text-Grounded and Spatial-aware Semantic Guidance for World-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Haoang Li, Haodong Yan, Jiaguan Zhu, Junfeng Li, Junjie He, Ruixin Li, Shunbo Zhou, Tianran Zhang, Wen Chen, Yangyang Zheng, Yuqiao Du, Zhide Zhong","submitted_at":"2026-08-09T17:59:35Z","abstract_excerpt":"World-Action Models (WAMs) have emerged as a promising paradigm for robotic manipulation. However, most existing WAMs generate future videos and actions by relying mainly on visual cues rather than language instructions, since off-the-shelf text encoders embed instructions independently of visual observations. As a result, the videos predicted by these WAMs are often semantically misaligned with their corresponding language instructions, which degrades the accuracy of the predicted actions. To overcome this limitation, we propose SG-WAM, a semantic guidance method for world-action models that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08839","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/2608.08839/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":"2026-08-11T01:25:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VJrcSGkQerIJApGoVrIRSTq9yMQRr5qTtpEsUqVT+2ZgmyMlrgvFp0qqUR9wBH9w7qRPUl93PPLP7vHO0S42Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:04:13.154986Z"},"content_sha256":"a19b621903b1ff65e53f6c570329f22544f22271d0b71a91ee08df68ae8b1cfd","schema_version":"1.0","event_id":"sha256:a19b621903b1ff65e53f6c570329f22544f22271d0b71a91ee08df68ae8b1cfd"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:6YPC47WC4ZDPCDEYK7LDLVHLWH","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.15607/RSS.2025.XXI.010) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Kevin Black, Noah Brown, James Darpinian, Karan Dhabalia, Danny Driess, Adnan Esmail, Michael Robert Equi, et al. π0.5: a vision-language-action model with open-world generalization. In9th Annual Conference on Robot Learning, 2025a. Kevin B","arxiv_id":"2608.08839","detector":"doi_compliance","evidence":{"ref_index":3,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.15607/rss.2025.xxi.01","reconstructed_doi":"10.15607/RSS.2025.XXI.010"},"severity":"advisory","ref_index":3,"audited_at":"2026-08-14T04:49:26.106243Z","event_type":"pith.integrity.v1","detected_doi":"10.15607/RSS.2025.XXI.010","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"3975db3e551ba1e5ea41359877bf343635e5defda9b7259988419e0a28328503","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":19541,"payload_sha256":"185be72f6d9ec8c33757c9daa97c164a573b9b47223b9206f7a778bb3cd77f76","signature_b64":"/Mq8PasAPRR80WQ82GeIKn1ldIEGoWutqY6CRngoTr/B8d4GTbL2nEVpWazKIuVvvZ2uy0s2UhJ4ctNeFui8AQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-14T04:53:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SYEV1ovmxtrAHyT6J3dU5kulG7eTFbU6r1j616KE15Q53/5lMBskniNtg9KmpimR6JVFcsDemNs5hJ49ZD04Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:04:13.158118Z"},"content_sha256":"7a7cd92025f5f87b7b39cb60ed21c6bbc2663d276525c6b8cb90dcb72a39180f","schema_version":"1.0","event_id":"sha256:7a7cd92025f5f87b7b39cb60ed21c6bbc2663d276525c6b8cb90dcb72a39180f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH/bundle.json","state_url":"https://pith.science/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH/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":"2026-08-17T04:04:13Z","links":{"resolver":"https://pith.science/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH","bundle":"https://pith.science/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH/bundle.json","state":"https://pith.science/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6YPC47WC4ZDPCDEYK7LDLVHLWH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6YPC47WC4ZDPCDEYK7LDLVHLWH","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"292c4226967c8b56d26d2dbb24cb7028176c64a1de1c0830d62117b7e3150062","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-09T17:59:35Z","title_canon_sha256":"3af0755b4e06f5faebc2ceb4bed95d2dcd76fd38244136f2b7d4207b1a44383e"},"schema_version":"1.0","source":{"id":"2608.08839","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08839","created_at":"2026-08-11T01:25:29Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08839v1","created_at":"2026-08-11T01:25:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08839","created_at":"2026-08-11T01:25:29Z"},{"alias_kind":"pith_short_12","alias_value":"6YPC47WC4ZDP","created_at":"2026-08-11T01:25:29Z"},{"alias_kind":"pith_short_16","alias_value":"6YPC47WC4ZDPCDEY","created_at":"2026-08-11T01:25:29Z"},{"alias_kind":"pith_short_8","alias_value":"6YPC47WC","created_at":"2026-08-11T01:25:29Z"}],"graph_snapshots":[{"event_id":"sha256:a19b621903b1ff65e53f6c570329f22544f22271d0b71a91ee08df68ae8b1cfd","target":"graph","created_at":"2026-08-11T01:25:29Z","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/2608.08839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"World-Action Models (WAMs) have emerged as a promising paradigm for robotic manipulation. However, most existing WAMs generate future videos and actions by relying mainly on visual cues rather than language instructions, since off-the-shelf text encoders embed instructions independently of visual observations. As a result, the videos predicted by these WAMs are often semantically misaligned with their corresponding language instructions, which degrades the accuracy of the predicted actions. To overcome this limitation, we propose SG-WAM, a semantic guidance method for world-action models that ","authors_text":"Haoang Li, Haodong Yan, Jiaguan Zhu, Junfeng Li, Junjie He, Ruixin Li, Shunbo Zhou, Tianran Zhang, Wen Chen, Yangyang Zheng, Yuqiao Du, Zhide Zhong","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-09T17:59:35Z","title":"SG-WAM: Text-Grounded and Spatial-aware Semantic Guidance for World-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08839","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":"sha256:4aa909be39a8788ad99542eb2fb9febbd2ce81c792051d6952c2abfe21bfe7ee","target":"record","created_at":"2026-08-11T01:25:29Z","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":"292c4226967c8b56d26d2dbb24cb7028176c64a1de1c0830d62117b7e3150062","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-09T17:59:35Z","title_canon_sha256":"3af0755b4e06f5faebc2ceb4bed95d2dcd76fd38244136f2b7d4207b1a44383e"},"schema_version":"1.0","source":{"id":"2608.08839","kind":"arxiv","version":1}},"canonical_sha256":"f61e2e7ec2e646f10c9857d635d4ebb1fbc7a0cd7dd145a42a1d2c413bf7fd8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f61e2e7ec2e646f10c9857d635d4ebb1fbc7a0cd7dd145a42a1d2c413bf7fd8d","first_computed_at":"2026-08-11T01:25:29.591079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:25:29.591079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2UHpJt/yNNEKoKqARCG7/utmlaBfyEAVIg2CBlf8WGpa05JrCLl+HFmCBmogz3UEybwXtPeZicTtJzWk6U5YDw==","signature_status":"signed_v1","signed_at":"2026-08-11T01:25:29.593761Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08839","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4aa909be39a8788ad99542eb2fb9febbd2ce81c792051d6952c2abfe21bfe7ee","sha256:a19b621903b1ff65e53f6c570329f22544f22271d0b71a91ee08df68ae8b1cfd","sha256:7a7cd92025f5f87b7b39cb60ed21c6bbc2663d276525c6b8cb90dcb72a39180f"],"state_sha256":"d9c13c85ff08cee00106703e374158d647de37cb647d05f290869ac7cebd5f15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B9NQpW9Oip4wTS8AVLbbblLHoVgVCw7gQy7XzFHODe2ANJ2nWCgrDSvOKUZxe2mZTtSWA4rzNlWTQhbYKRgCBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T04:04:13.159886Z","bundle_sha256":"98bc7bea1e3f2a18223bfa3e5a8e3fd40fdf71e024068ff65933bf2a3e128334"}}