{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FZD6HX5FQPBP42UOUXFGFFT7CB","short_pith_number":"pith:FZD6HX5F","canonical_record":{"source":{"id":"2412.06782","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-09T18:59:18Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f2699117bd53f50397184772f85bd8cc0a178dfcaf3375546607ec4a2702467d","abstract_canon_sha256":"0d76e3b06489ccae0437da71e5a94509a58d3cc14bd2e449a7b1ecc30d4161c1"},"schema_version":"1.0"},"canonical_sha256":"2e47e3dfa583c2fe6a8ea5ca62967f10586539e7a0830853ef05a3b51a3b8439","source":{"kind":"arxiv","id":"2412.06782","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06782","created_at":"2026-07-05T11:51:19Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06782v3","created_at":"2026-07-05T11:51:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06782","created_at":"2026-07-05T11:51:19Z"},{"alias_kind":"pith_short_12","alias_value":"FZD6HX5FQPBP","created_at":"2026-07-05T11:51:19Z"},{"alias_kind":"pith_short_16","alias_value":"FZD6HX5FQPBP42UO","created_at":"2026-07-05T11:51:19Z"},{"alias_kind":"pith_short_8","alias_value":"FZD6HX5F","created_at":"2026-07-05T11:51:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FZD6HX5FQPBP42UOUXFGFFT7CB","target":"record","payload":{"canonical_record":{"source":{"id":"2412.06782","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-09T18:59:18Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f2699117bd53f50397184772f85bd8cc0a178dfcaf3375546607ec4a2702467d","abstract_canon_sha256":"0d76e3b06489ccae0437da71e5a94509a58d3cc14bd2e449a7b1ecc30d4161c1"},"schema_version":"1.0"},"canonical_sha256":"2e47e3dfa583c2fe6a8ea5ca62967f10586539e7a0830853ef05a3b51a3b8439","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:19.796688Z","signature_b64":"6uVh7/OYmcbqjkXTHmO1PwahdVhxIOS2WfnDGeKiEf47u0MhIVUdunM/+uzZR6R+6Sxpu/QbOgmQY3jQydjBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e47e3dfa583c2fe6a8ea5ca62967f10586539e7a0830853ef05a3b51a3b8439","last_reissued_at":"2026-07-05T11:51:19.796054Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:19.796054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.06782","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:51:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CoVGVbpiuNH/6LD8zUmVe25+zdV3X+0xR/skxR6lSWMietQGpmajQlWV6I8xlhYL5/TA0LLG7tSspUpTc+e9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:16:07.453546Z"},"content_sha256":"fbea5adbef713ae34656876e67f4d7d4e59e3ec49e2648895189856b1d80fdba","schema_version":"1.0","event_id":"sha256:fbea5adbef713ae34656876e67f4d7d4e59e3ec49e2648895189856b1d80fdba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FZD6HX5FQPBP42UOUXFGFFT7CB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Donglin Wang, Mingyang Sun, Pengxiang Ding, Shangke Lyu, Siteng Huang, Wei Zhao, Zhaoxin Fan, Zhefei Gong","submitted_at":"2024-12-09T18:59:18Z","abstract_excerpt":"In robotic visuomotor policy learning, diffusion-based models have achieved significant success in improving the accuracy of action trajectory generation compared to traditional autoregressive models. However, they suffer from inefficiency due to multiple denoising steps and limited flexibility from complex constraints. In this paper, we introduce Coarse-to-Fine AutoRegressive Policy (CARP), a novel paradigm for visuomotor policy learning that redefines the autoregressive action generation process as a coarse-to-fine, next-scale approach. CARP decouples action generation into two stages: first"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06782","kind":"arxiv","version":3},"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/2412.06782/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":"2026-07-05T11:51:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sM/1dXL9TGsUEUIYkMSW/QhxPn7wg/7DITkfsLGfO27ho6VWC57ua5lIkRX8RoXPSX4MfZIxooQXHIrrV0tLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:16:07.454102Z"},"content_sha256":"0a5437406bdd6cdf423e4e86c39110278b64ed6b9f5a4f50acf81453d47e0b07","schema_version":"1.0","event_id":"sha256:0a5437406bdd6cdf423e4e86c39110278b64ed6b9f5a4f50acf81453d47e0b07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FZD6HX5FQPBP42UOUXFGFFT7CB/bundle.json","state_url":"https://pith.science/pith/FZD6HX5FQPBP42UOUXFGFFT7CB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FZD6HX5FQPBP42UOUXFGFFT7CB/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":"2026-08-07T22:16:07Z","links":{"resolver":"https://pith.science/pith/FZD6HX5FQPBP42UOUXFGFFT7CB","bundle":"https://pith.science/pith/FZD6HX5FQPBP42UOUXFGFFT7CB/bundle.json","state":"https://pith.science/pith/FZD6HX5FQPBP42UOUXFGFFT7CB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FZD6HX5FQPBP42UOUXFGFFT7CB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FZD6HX5FQPBP42UOUXFGFFT7CB","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":"0d76e3b06489ccae0437da71e5a94509a58d3cc14bd2e449a7b1ecc30d4161c1","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-09T18:59:18Z","title_canon_sha256":"f2699117bd53f50397184772f85bd8cc0a178dfcaf3375546607ec4a2702467d"},"schema_version":"1.0","source":{"id":"2412.06782","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06782","created_at":"2026-07-05T11:51:19Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06782v3","created_at":"2026-07-05T11:51:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06782","created_at":"2026-07-05T11:51:19Z"},{"alias_kind":"pith_short_12","alias_value":"FZD6HX5FQPBP","created_at":"2026-07-05T11:51:19Z"},{"alias_kind":"pith_short_16","alias_value":"FZD6HX5FQPBP42UO","created_at":"2026-07-05T11:51:19Z"},{"alias_kind":"pith_short_8","alias_value":"FZD6HX5F","created_at":"2026-07-05T11:51:19Z"}],"graph_snapshots":[{"event_id":"sha256:0a5437406bdd6cdf423e4e86c39110278b64ed6b9f5a4f50acf81453d47e0b07","target":"graph","created_at":"2026-07-05T11:51:19Z","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/2412.06782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In robotic visuomotor policy learning, diffusion-based models have achieved significant success in improving the accuracy of action trajectory generation compared to traditional autoregressive models. However, they suffer from inefficiency due to multiple denoising steps and limited flexibility from complex constraints. In this paper, we introduce Coarse-to-Fine AutoRegressive Policy (CARP), a novel paradigm for visuomotor policy learning that redefines the autoregressive action generation process as a coarse-to-fine, next-scale approach. CARP decouples action generation into two stages: first","authors_text":"Donglin Wang, Mingyang Sun, Pengxiang Ding, Shangke Lyu, Siteng Huang, Wei Zhao, Zhaoxin Fan, Zhefei Gong","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-09T18:59:18Z","title":"CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06782","kind":"arxiv","version":3},"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:fbea5adbef713ae34656876e67f4d7d4e59e3ec49e2648895189856b1d80fdba","target":"record","created_at":"2026-07-05T11:51:19Z","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":"0d76e3b06489ccae0437da71e5a94509a58d3cc14bd2e449a7b1ecc30d4161c1","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-09T18:59:18Z","title_canon_sha256":"f2699117bd53f50397184772f85bd8cc0a178dfcaf3375546607ec4a2702467d"},"schema_version":"1.0","source":{"id":"2412.06782","kind":"arxiv","version":3}},"canonical_sha256":"2e47e3dfa583c2fe6a8ea5ca62967f10586539e7a0830853ef05a3b51a3b8439","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e47e3dfa583c2fe6a8ea5ca62967f10586539e7a0830853ef05a3b51a3b8439","first_computed_at":"2026-07-05T11:51:19.796054Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:19.796054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6uVh7/OYmcbqjkXTHmO1PwahdVhxIOS2WfnDGeKiEf47u0MhIVUdunM/+uzZR6R+6Sxpu/QbOgmQY3jQydjBDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:19.796688Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06782","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbea5adbef713ae34656876e67f4d7d4e59e3ec49e2648895189856b1d80fdba","sha256:0a5437406bdd6cdf423e4e86c39110278b64ed6b9f5a4f50acf81453d47e0b07"],"state_sha256":"e9518c99b46af32998cc878e2c7233cbac8dd60aca8dd82301ee2ebeab169e99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dWFdFhex2IZMBURNTp/LFPnYlgg24ol3i8cOgpsJ34xtdWUYripksN9ZS/AZIpQsH53FJ++6IuFvkNFzvHswBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:16:07.458928Z","bundle_sha256":"f1e5371cb500f13fd55d390270f73b7cc4d452316efd3a88a7cc7b4d30878e36"}}