{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IZCESOS4QJYZRWGBYXLBSRV2WO","short_pith_number":"pith:IZCESOS4","canonical_record":{"source":{"id":"2605.24203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-22T20:43:47Z","cross_cats_sorted":[],"title_canon_sha256":"94531fbe6bb9fe31e9c8788fe5104adb6e95998450db13347ebcea79f6d468af","abstract_canon_sha256":"9fc2a9e37a1ca9bb94cb1d9a581f9cd0077b289b1ad7a3524e6e158285eeeded"},"schema_version":"1.0"},"canonical_sha256":"4644493a5c827198d8c1c5d61946bab3bdfbb852a109c6e2847904c4f0948262","source":{"kind":"arxiv","id":"2605.24203","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24203","created_at":"2026-05-26T01:02:52Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24203v1","created_at":"2026-05-26T01:02:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24203","created_at":"2026-05-26T01:02:52Z"},{"alias_kind":"pith_short_12","alias_value":"IZCESOS4QJYZ","created_at":"2026-05-26T01:02:52Z"},{"alias_kind":"pith_short_16","alias_value":"IZCESOS4QJYZRWGB","created_at":"2026-05-26T01:02:52Z"},{"alias_kind":"pith_short_8","alias_value":"IZCESOS4","created_at":"2026-05-26T01:02:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IZCESOS4QJYZRWGBYXLBSRV2WO","target":"record","payload":{"canonical_record":{"source":{"id":"2605.24203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-22T20:43:47Z","cross_cats_sorted":[],"title_canon_sha256":"94531fbe6bb9fe31e9c8788fe5104adb6e95998450db13347ebcea79f6d468af","abstract_canon_sha256":"9fc2a9e37a1ca9bb94cb1d9a581f9cd0077b289b1ad7a3524e6e158285eeeded"},"schema_version":"1.0"},"canonical_sha256":"4644493a5c827198d8c1c5d61946bab3bdfbb852a109c6e2847904c4f0948262","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:52.291121Z","signature_b64":"NWQOyOnkw31OzRyecYHwa/No4Q1p1UCDxxgIKkHKjLJyNnWZVQ700MdoLRGuubY5amVwIVWg3WET6KQqagiyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4644493a5c827198d8c1c5d61946bab3bdfbb852a109c6e2847904c4f0948262","last_reissued_at":"2026-05-26T01:02:52.290374Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:52.290374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.24203","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":"2026-05-26T01:02:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2qIsFm25QDyNjQdP3BnWt2wNOQ1v47KIUEhNFewE4rNZy0JcMO30sVdYdeXpsPFsXSu5zHTu34W4WEvFkD5XDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:23:41.755614Z"},"content_sha256":"d0ec06dd1054841f1ac8a19925756eccf34b47de7f8e8b6ecef21c2c5440fe88","schema_version":"1.0","event_id":"sha256:d0ec06dd1054841f1ac8a19925756eccf34b47de7f8e8b6ecef21c2c5440fe88"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IZCESOS4QJYZRWGBYXLBSRV2WO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bo Zhao, Mohamed Elhoseiny, Runze Wang, Tao Lin, Tianwen Qian, Xiangyang Xue, Yanwei Fu, Yu-Gang Jiang, Yu Li, Yuqian Fu","submitted_at":"2026-05-22T20:43:47Z","abstract_excerpt":"Vision-language-action (VLA) models have shown strong potential for generalist robot manipulation, yet they remain limited by insufficient spatial reasoning, particularly in determining where to interact in complex visual scenes. While recent efforts introduce various forms of visual planning to address this issue, existing approaches either rely on global geometric cues, symbolic intermediate representations, or externally generated visual signals, which are often weakly coupled with downstream action prediction. In this work, we revisit visual planning in VLA systems and argue that effective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24203","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/2605.24203/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":"2026-05-26T01:02:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5CTMx2BJgxS1AWJPvYjnz4lYVrkOimXLc2bmQYFAkdL7uXHufIW/AGS/VnuL99TqUlOjFusI1p+140bb0uP6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:23:41.755991Z"},"content_sha256":"dbcdc384b55c86db4fb31bf23540d8a4852355a01936fafc99e4dfeae69f8a5c","schema_version":"1.0","event_id":"sha256:dbcdc384b55c86db4fb31bf23540d8a4852355a01936fafc99e4dfeae69f8a5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IZCESOS4QJYZRWGBYXLBSRV2WO/bundle.json","state_url":"https://pith.science/pith/IZCESOS4QJYZRWGBYXLBSRV2WO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IZCESOS4QJYZRWGBYXLBSRV2WO/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":"2026-06-02T23:23:41Z","links":{"resolver":"https://pith.science/pith/IZCESOS4QJYZRWGBYXLBSRV2WO","bundle":"https://pith.science/pith/IZCESOS4QJYZRWGBYXLBSRV2WO/bundle.json","state":"https://pith.science/pith/IZCESOS4QJYZRWGBYXLBSRV2WO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IZCESOS4QJYZRWGBYXLBSRV2WO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IZCESOS4QJYZRWGBYXLBSRV2WO","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":"9fc2a9e37a1ca9bb94cb1d9a581f9cd0077b289b1ad7a3524e6e158285eeeded","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-22T20:43:47Z","title_canon_sha256":"94531fbe6bb9fe31e9c8788fe5104adb6e95998450db13347ebcea79f6d468af"},"schema_version":"1.0","source":{"id":"2605.24203","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24203","created_at":"2026-05-26T01:02:52Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24203v1","created_at":"2026-05-26T01:02:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24203","created_at":"2026-05-26T01:02:52Z"},{"alias_kind":"pith_short_12","alias_value":"IZCESOS4QJYZ","created_at":"2026-05-26T01:02:52Z"},{"alias_kind":"pith_short_16","alias_value":"IZCESOS4QJYZRWGB","created_at":"2026-05-26T01:02:52Z"},{"alias_kind":"pith_short_8","alias_value":"IZCESOS4","created_at":"2026-05-26T01:02:52Z"}],"graph_snapshots":[{"event_id":"sha256:dbcdc384b55c86db4fb31bf23540d8a4852355a01936fafc99e4dfeae69f8a5c","target":"graph","created_at":"2026-05-26T01:02:52Z","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/2605.24203/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language-action (VLA) models have shown strong potential for generalist robot manipulation, yet they remain limited by insufficient spatial reasoning, particularly in determining where to interact in complex visual scenes. While recent efforts introduce various forms of visual planning to address this issue, existing approaches either rely on global geometric cues, symbolic intermediate representations, or externally generated visual signals, which are often weakly coupled with downstream action prediction. In this work, we revisit visual planning in VLA systems and argue that effective","authors_text":"Bo Zhao, Mohamed Elhoseiny, Runze Wang, Tao Lin, Tianwen Qian, Xiangyang Xue, Yanwei Fu, Yu-Gang Jiang, Yu Li, Yuqian Fu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-22T20:43:47Z","title":"Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24203","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:d0ec06dd1054841f1ac8a19925756eccf34b47de7f8e8b6ecef21c2c5440fe88","target":"record","created_at":"2026-05-26T01:02:52Z","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":"9fc2a9e37a1ca9bb94cb1d9a581f9cd0077b289b1ad7a3524e6e158285eeeded","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-22T20:43:47Z","title_canon_sha256":"94531fbe6bb9fe31e9c8788fe5104adb6e95998450db13347ebcea79f6d468af"},"schema_version":"1.0","source":{"id":"2605.24203","kind":"arxiv","version":1}},"canonical_sha256":"4644493a5c827198d8c1c5d61946bab3bdfbb852a109c6e2847904c4f0948262","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4644493a5c827198d8c1c5d61946bab3bdfbb852a109c6e2847904c4f0948262","first_computed_at":"2026-05-26T01:02:52.290374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:02:52.290374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NWQOyOnkw31OzRyecYHwa/No4Q1p1UCDxxgIKkHKjLJyNnWZVQ700MdoLRGuubY5amVwIVWg3WET6KQqagiyDA==","signature_status":"signed_v1","signed_at":"2026-05-26T01:02:52.291121Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24203","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0ec06dd1054841f1ac8a19925756eccf34b47de7f8e8b6ecef21c2c5440fe88","sha256:dbcdc384b55c86db4fb31bf23540d8a4852355a01936fafc99e4dfeae69f8a5c"],"state_sha256":"900dd5b469f04e487dc490f7d9b83d62c42f1cac3a4b5a469b633fbea94c2acf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CAtKnRhBHR4xJTCkIH7GepVTBVb51ioHBlPtNcpXifWgjOCPeuHmPrELhPVicE5RPRtbTvwVP82NuZHcYnLJBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T23:23:41.758016Z","bundle_sha256":"f1d8c47e991238b328540d750b4a083c223ea71860dfc475205fabc2c75a3c5e"}}