{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3NWI74FITLUPA22WMUKNUSGTB7","short_pith_number":"pith:3NWI74FI","canonical_record":{"source":{"id":"2412.11974","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-16T16:58:28Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"6143b5ead61fe78890415fc0677caf004ee93e83690457117e6c649c174c8f27","abstract_canon_sha256":"72dfc6925eac7c4c9b083eb71637cd6659a69720268deb3181a494656e35905b"},"schema_version":"1.0"},"canonical_sha256":"db6c8ff0a89ae8f06b566514da48d30fe22a7c6ce27dc11e86cffd9d505fa7d2","source":{"kind":"arxiv","id":"2412.11974","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11974","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11974v2","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11974","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"3NWI74FITLUP","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"pith_short_16","alias_value":"3NWI74FITLUPA22W","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"pith_short_8","alias_value":"3NWI74FI","created_at":"2026-07-05T09:50:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3NWI74FITLUPA22WMUKNUSGTB7","target":"record","payload":{"canonical_record":{"source":{"id":"2412.11974","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-16T16:58:28Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"6143b5ead61fe78890415fc0677caf004ee93e83690457117e6c649c174c8f27","abstract_canon_sha256":"72dfc6925eac7c4c9b083eb71637cd6659a69720268deb3181a494656e35905b"},"schema_version":"1.0"},"canonical_sha256":"db6c8ff0a89ae8f06b566514da48d30fe22a7c6ce27dc11e86cffd9d505fa7d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:09.566071Z","signature_b64":"5OKLaQ/tdksxGeLUuKWPB2bLtav2W7A4bSCFaGh8Jt5+d1e/ITP6FW2UxYIlgDhNul39i5z2B1SKqvMvdaYKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db6c8ff0a89ae8f06b566514da48d30fe22a7c6ce27dc11e86cffd9d505fa7d2","last_reissued_at":"2026-07-05T09:50:09.565564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:09.565564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.11974","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":"2026-07-05T09:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K1wvKVtDMLGCJ4OPaqD6sFiAOOPJAqvhAyjHCxh2joTXT/RgvCLQ4TkAwfJ4c16KCDt7tI6TRcNRFB500a9+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T18:54:57.298619Z"},"content_sha256":"c182a0ae9ca149249300537317a493c61c23547a45888c1ac7fcb84ec09ea1fc","schema_version":"1.0","event_id":"sha256:c182a0ae9ca149249300537317a493c61c23547a45888c1ac7fcb84ec09ea1fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3NWI74FITLUPA22WMUKNUSGTB7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.RO","authors_text":"Deepanway Ghosal, Pengfei Hong, Qi Sun, Soujanya Poria, Tej Deep Pala, U-Xuan Tan, Vernon Toh","submitted_at":"2024-12-16T16:58:28Z","abstract_excerpt":"Traditional reinforcement learning-based robotic control methods are often task-specific and fail to generalize across diverse environments or unseen objects and instructions. Visual Language Models (VLMs) demonstrate strong scene understanding and planning capabilities but lack the ability to generate actionable policies tailored to specific robotic embodiments. To address this, Visual-Language-Action (VLA) models have emerged, yet they face challenges in long-horizon spatial reasoning and grounded task planning. In this work, we propose the Embodied Multimodal Action Model with Grounded Chai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11974","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/2412.11974/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":"2026-07-05T09:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f0SOeY6uM6V5OTLZZWY7+rW+iWRScZ1/vC0qrTHTPG/fkYx+HwwXVpNPo/Rt7USSLlk0qhwYC64YcuBE1HPtDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T18:54:57.299127Z"},"content_sha256":"98aad516c010d06f4024141fdce9fe6e0a1fe403822e76e156ffe93e6f1bd49b","schema_version":"1.0","event_id":"sha256:98aad516c010d06f4024141fdce9fe6e0a1fe403822e76e156ffe93e6f1bd49b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3NWI74FITLUPA22WMUKNUSGTB7/bundle.json","state_url":"https://pith.science/pith/3NWI74FITLUPA22WMUKNUSGTB7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3NWI74FITLUPA22WMUKNUSGTB7/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":"2026-07-12T18:54:57Z","links":{"resolver":"https://pith.science/pith/3NWI74FITLUPA22WMUKNUSGTB7","bundle":"https://pith.science/pith/3NWI74FITLUPA22WMUKNUSGTB7/bundle.json","state":"https://pith.science/pith/3NWI74FITLUPA22WMUKNUSGTB7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3NWI74FITLUPA22WMUKNUSGTB7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3NWI74FITLUPA22WMUKNUSGTB7","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":"72dfc6925eac7c4c9b083eb71637cd6659a69720268deb3181a494656e35905b","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-16T16:58:28Z","title_canon_sha256":"6143b5ead61fe78890415fc0677caf004ee93e83690457117e6c649c174c8f27"},"schema_version":"1.0","source":{"id":"2412.11974","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11974","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11974v2","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11974","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"3NWI74FITLUP","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"pith_short_16","alias_value":"3NWI74FITLUPA22W","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"pith_short_8","alias_value":"3NWI74FI","created_at":"2026-07-05T09:50:09Z"}],"graph_snapshots":[{"event_id":"sha256:98aad516c010d06f4024141fdce9fe6e0a1fe403822e76e156ffe93e6f1bd49b","target":"graph","created_at":"2026-07-05T09:50:09Z","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/2412.11974/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional reinforcement learning-based robotic control methods are often task-specific and fail to generalize across diverse environments or unseen objects and instructions. Visual Language Models (VLMs) demonstrate strong scene understanding and planning capabilities but lack the ability to generate actionable policies tailored to specific robotic embodiments. To address this, Visual-Language-Action (VLA) models have emerged, yet they face challenges in long-horizon spatial reasoning and grounded task planning. In this work, we propose the Embodied Multimodal Action Model with Grounded Chai","authors_text":"Deepanway Ghosal, Pengfei Hong, Qi Sun, Soujanya Poria, Tej Deep Pala, U-Xuan Tan, Vernon Toh","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-16T16:58:28Z","title":"Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11974","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:c182a0ae9ca149249300537317a493c61c23547a45888c1ac7fcb84ec09ea1fc","target":"record","created_at":"2026-07-05T09:50:09Z","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":"72dfc6925eac7c4c9b083eb71637cd6659a69720268deb3181a494656e35905b","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-16T16:58:28Z","title_canon_sha256":"6143b5ead61fe78890415fc0677caf004ee93e83690457117e6c649c174c8f27"},"schema_version":"1.0","source":{"id":"2412.11974","kind":"arxiv","version":2}},"canonical_sha256":"db6c8ff0a89ae8f06b566514da48d30fe22a7c6ce27dc11e86cffd9d505fa7d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db6c8ff0a89ae8f06b566514da48d30fe22a7c6ce27dc11e86cffd9d505fa7d2","first_computed_at":"2026-07-05T09:50:09.565564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:09.565564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5OKLaQ/tdksxGeLUuKWPB2bLtav2W7A4bSCFaGh8Jt5+d1e/ITP6FW2UxYIlgDhNul39i5z2B1SKqvMvdaYKDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:09.566071Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11974","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c182a0ae9ca149249300537317a493c61c23547a45888c1ac7fcb84ec09ea1fc","sha256:98aad516c010d06f4024141fdce9fe6e0a1fe403822e76e156ffe93e6f1bd49b"],"state_sha256":"1b647e5124fcc2c5e753c5dc44321fc1c1ed62ecede98207779c591adc557121"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oapSUgTo51b/VhMdBSa+sRwKX7riB6w2p6dwAWJ0mwMF8FoCkXxT8OXM1RS6m//iBh4s/Ik+PREyFd9Fhz2HAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T18:54:57.301925Z","bundle_sha256":"dbdc134db2b143d16c6b9828331721a8fa26be547a55a494cdde52f37b98b75b"}}