{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:D6U4KJ5EG5IBE2T22KGWBL2Q3Q","short_pith_number":"pith:D6U4KJ5E","canonical_record":{"source":{"id":"2406.15677","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-21T22:49:23Z","cross_cats_sorted":[],"title_canon_sha256":"dabb4f622167c91d79081a5f783c7855f14631fa5867536cc7b5828fac99feec","abstract_canon_sha256":"bedb983101a6b37af0e06e9a1c97666f7988d4f61341440d1aa175edd4dcc087"},"schema_version":"1.0"},"canonical_sha256":"1fa9c527a43750126a7ad28d60af50dc1c879a8f0fd74ce87a528f09f51b4278","source":{"kind":"arxiv","id":"2406.15677","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15677","created_at":"2026-07-05T11:27:19Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15677v2","created_at":"2026-07-05T11:27:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15677","created_at":"2026-07-05T11:27:19Z"},{"alias_kind":"pith_short_12","alias_value":"D6U4KJ5EG5IB","created_at":"2026-07-05T11:27:19Z"},{"alias_kind":"pith_short_16","alias_value":"D6U4KJ5EG5IBE2T2","created_at":"2026-07-05T11:27:19Z"},{"alias_kind":"pith_short_8","alias_value":"D6U4KJ5E","created_at":"2026-07-05T11:27:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:D6U4KJ5EG5IBE2T22KGWBL2Q3Q","target":"record","payload":{"canonical_record":{"source":{"id":"2406.15677","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-21T22:49:23Z","cross_cats_sorted":[],"title_canon_sha256":"dabb4f622167c91d79081a5f783c7855f14631fa5867536cc7b5828fac99feec","abstract_canon_sha256":"bedb983101a6b37af0e06e9a1c97666f7988d4f61341440d1aa175edd4dcc087"},"schema_version":"1.0"},"canonical_sha256":"1fa9c527a43750126a7ad28d60af50dc1c879a8f0fd74ce87a528f09f51b4278","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:19.066927Z","signature_b64":"kAND0XsVVN2eKJiByu1s7t/YeEr77eRqAhKtBPaPOED/B8oBd1SgKWVW45MeOmtGu8OozPSEs6zDZnHmEqsGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fa9c527a43750126a7ad28d60af50dc1c879a8f0fd74ce87a528f09f51b4278","last_reissued_at":"2026-07-05T11:27:19.066453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:19.066453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.15677","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:27:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dpq5juu/vVHrcWIw3zzBY66hs/kPZ4Mqzfa/AxzS+wP1VUGhArHVOJbCdfs85H+dZK57psyyb6noQ3R1QNg2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:55:18.648416Z"},"content_sha256":"ae1c4502cef7770afb687f1663f91f38f6311dead19f77f05969c671edc20ab4","schema_version":"1.0","event_id":"sha256:ae1c4502cef7770afb687f1663f91f38f6311dead19f77f05969c671edc20ab4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:D6U4KJ5EG5IBE2T22KGWBL2Q3Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Efficient and Robust Language-conditioned Manipulation using Textual-Visual Relevancy and Equivariant Language Mapping","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chenghao Wang, Dian Wang, Haojie Huang, Jason Xinyu Liu, Linfeng Zhao, Mingxi Jia, Robert Platt, Robin Walters, Stefanie Tellex, Zhewen Zhang","submitted_at":"2024-06-21T22:49:23Z","abstract_excerpt":"Controlling robots through natural language is pivotal for enhancing human-robot collaboration and synthesizing complex robot behaviors. Recent works that are trained on large robot datasets show impressive generalization abilities. However, such pretrained methods are (1) often fragile to unseen scenarios, and (2) expensive to adapt to new tasks. This paper introduces Grounded Equivariant Manipulation (GEM), a robust yet efficient approach that leverages pretrained vision-language models with equivariant language mapping for language-conditioned manipulation tasks. Our experiments demonstrate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15677","kind":"arxiv","version":2},"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/2406.15677/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":"2026-07-05T11:27:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m6bkT2/jikijf1FxFxumFnL7ANYnIgywbufP6A36BNxKJ8m9qilYdnu1tFdyne21YMCphDgJJb4Mf3+n0XVbDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:55:18.648788Z"},"content_sha256":"54d6d8e92aca4e920d2956e3deeb5cfea78fbb4a98770bafbd9f101e7780ac97","schema_version":"1.0","event_id":"sha256:54d6d8e92aca4e920d2956e3deeb5cfea78fbb4a98770bafbd9f101e7780ac97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D6U4KJ5EG5IBE2T22KGWBL2Q3Q/bundle.json","state_url":"https://pith.science/pith/D6U4KJ5EG5IBE2T22KGWBL2Q3Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D6U4KJ5EG5IBE2T22KGWBL2Q3Q/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":"2026-07-07T14:55:18Z","links":{"resolver":"https://pith.science/pith/D6U4KJ5EG5IBE2T22KGWBL2Q3Q","bundle":"https://pith.science/pith/D6U4KJ5EG5IBE2T22KGWBL2Q3Q/bundle.json","state":"https://pith.science/pith/D6U4KJ5EG5IBE2T22KGWBL2Q3Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D6U4KJ5EG5IBE2T22KGWBL2Q3Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D6U4KJ5EG5IBE2T22KGWBL2Q3Q","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":"bedb983101a6b37af0e06e9a1c97666f7988d4f61341440d1aa175edd4dcc087","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-21T22:49:23Z","title_canon_sha256":"dabb4f622167c91d79081a5f783c7855f14631fa5867536cc7b5828fac99feec"},"schema_version":"1.0","source":{"id":"2406.15677","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15677","created_at":"2026-07-05T11:27:19Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15677v2","created_at":"2026-07-05T11:27:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15677","created_at":"2026-07-05T11:27:19Z"},{"alias_kind":"pith_short_12","alias_value":"D6U4KJ5EG5IB","created_at":"2026-07-05T11:27:19Z"},{"alias_kind":"pith_short_16","alias_value":"D6U4KJ5EG5IBE2T2","created_at":"2026-07-05T11:27:19Z"},{"alias_kind":"pith_short_8","alias_value":"D6U4KJ5E","created_at":"2026-07-05T11:27:19Z"}],"graph_snapshots":[{"event_id":"sha256:54d6d8e92aca4e920d2956e3deeb5cfea78fbb4a98770bafbd9f101e7780ac97","target":"graph","created_at":"2026-07-05T11:27:19Z","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/2406.15677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Controlling robots through natural language is pivotal for enhancing human-robot collaboration and synthesizing complex robot behaviors. Recent works that are trained on large robot datasets show impressive generalization abilities. However, such pretrained methods are (1) often fragile to unseen scenarios, and (2) expensive to adapt to new tasks. This paper introduces Grounded Equivariant Manipulation (GEM), a robust yet efficient approach that leverages pretrained vision-language models with equivariant language mapping for language-conditioned manipulation tasks. Our experiments demonstrate","authors_text":"Chenghao Wang, Dian Wang, Haojie Huang, Jason Xinyu Liu, Linfeng Zhao, Mingxi Jia, Robert Platt, Robin Walters, Stefanie Tellex, Zhewen Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-21T22:49:23Z","title":"Learning Efficient and Robust Language-conditioned Manipulation using Textual-Visual Relevancy and Equivariant Language Mapping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15677","kind":"arxiv","version":2},"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:ae1c4502cef7770afb687f1663f91f38f6311dead19f77f05969c671edc20ab4","target":"record","created_at":"2026-07-05T11:27:19Z","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":"bedb983101a6b37af0e06e9a1c97666f7988d4f61341440d1aa175edd4dcc087","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-21T22:49:23Z","title_canon_sha256":"dabb4f622167c91d79081a5f783c7855f14631fa5867536cc7b5828fac99feec"},"schema_version":"1.0","source":{"id":"2406.15677","kind":"arxiv","version":2}},"canonical_sha256":"1fa9c527a43750126a7ad28d60af50dc1c879a8f0fd74ce87a528f09f51b4278","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fa9c527a43750126a7ad28d60af50dc1c879a8f0fd74ce87a528f09f51b4278","first_computed_at":"2026-07-05T11:27:19.066453Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:19.066453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kAND0XsVVN2eKJiByu1s7t/YeEr77eRqAhKtBPaPOED/B8oBd1SgKWVW45MeOmtGu8OozPSEs6zDZnHmEqsGCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:19.066927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15677","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae1c4502cef7770afb687f1663f91f38f6311dead19f77f05969c671edc20ab4","sha256:54d6d8e92aca4e920d2956e3deeb5cfea78fbb4a98770bafbd9f101e7780ac97"],"state_sha256":"ad898cc0d9b1de670a52bfb913ab4b8186f11c136a0121e0067b35e7ebc14835"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mZbqOSqVktAJpo5d42pkK0XbUj8oJwNiDV4+IibmTD9WM1iYDbBOT0+zU6B4wJskD2awyfDBHimgrRsqXYXoDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:55:18.650879Z","bundle_sha256":"1ef3632a1b4527a3089a3d931508e19ac9ffd8e8b41a63a4a427e91eeb3a07b5"}}