{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ONP2L35FBVR3ASES3IHQOY6FAG","short_pith_number":"pith:ONP2L35F","canonical_record":{"source":{"id":"2507.20622","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-28T08:36:01Z","cross_cats_sorted":[],"title_canon_sha256":"1edeabaf2ac598cc431d1ce1a280d57d549edc4f9a1969e1664033dea5e38f39","abstract_canon_sha256":"a717fd121203259cc6574253722f10c4fbe0ad0505eec2c38ebf15c0019aa5cd"},"schema_version":"1.0"},"canonical_sha256":"735fa5efa50d63b04892da0f0763c5018d6d5fef8c76a503f4138acea3cbd49d","source":{"kind":"arxiv","id":"2507.20622","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20622","created_at":"2026-07-05T11:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20622v1","created_at":"2026-07-05T11:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20622","created_at":"2026-07-05T11:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"ONP2L35FBVR3","created_at":"2026-07-05T11:44:22Z"},{"alias_kind":"pith_short_16","alias_value":"ONP2L35FBVR3ASES","created_at":"2026-07-05T11:44:22Z"},{"alias_kind":"pith_short_8","alias_value":"ONP2L35F","created_at":"2026-07-05T11:44:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ONP2L35FBVR3ASES3IHQOY6FAG","target":"record","payload":{"canonical_record":{"source":{"id":"2507.20622","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-28T08:36:01Z","cross_cats_sorted":[],"title_canon_sha256":"1edeabaf2ac598cc431d1ce1a280d57d549edc4f9a1969e1664033dea5e38f39","abstract_canon_sha256":"a717fd121203259cc6574253722f10c4fbe0ad0505eec2c38ebf15c0019aa5cd"},"schema_version":"1.0"},"canonical_sha256":"735fa5efa50d63b04892da0f0763c5018d6d5fef8c76a503f4138acea3cbd49d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:22.689405Z","signature_b64":"HzSEQbhzI7PechztEQX6OU93mpqBBBPWNYbaeRt0MrhhLqfIH/BdyWOhgNlvS0GX9DPh9SNhXrwoOROqHpP3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"735fa5efa50d63b04892da0f0763c5018d6d5fef8c76a503f4138acea3cbd49d","last_reissued_at":"2026-07-05T11:44:22.688960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:22.688960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.20622","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":"2026-07-05T11:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pkkrmehKxZ3xe2CH819QCwVgpGm5LwST9lbl5bV4pkE46YebR5I4Q45BNcQPVxHICo1TRAE6U//KRWHj3MKSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:59:38.256465Z"},"content_sha256":"f901aad1e10821cb069b1195cb6045aa763c7ffa40b39b730f7915fd361deeb3","schema_version":"1.0","event_id":"sha256:f901aad1e10821cb069b1195cb6045aa763c7ffa40b39b730f7915fd361deeb3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ONP2L35FBVR3ASES3IHQOY6FAG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FMimic: Foundation Models are Fine-grained Action Learners from Human Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guangyan Chen, Haoyang Lu, Meiling Wang, Mengxiao Hu, Mengyin Fu, Te Cui, Tianxing Zhou, Yao Mu, Yi Yang, Yufeng Yue, Zicai Peng","submitted_at":"2025-07-28T08:36:01Z","abstract_excerpt":"Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in foundation models, particularly Vision Language Models (VLMs), have demonstrated remarkable capabilities in visual and linguistic reasoning for VIL tasks. Despite this progress, existing approaches primarily utilize these models for learning high-level plans from human demonstrations, relying on pre-defined motion primitives for executing physical interactions, which remains a major bottleneck for robotic systems. In this work, we present FMimic, a no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20622","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/2507.20622/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":"2026-07-05T11:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1mw+MXKOgBMvTWfvJY2c+FGu+XiozMP+SaH8j6xcZa+ar5zV1r66hIvfFgvAOICKDMis/VJQzHa3uKZimN2WDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:59:38.256839Z"},"content_sha256":"ceb3e6bf4d1a6bc8d35f16e1afe714631be2156587432a3c7f3b18ec57854a4f","schema_version":"1.0","event_id":"sha256:ceb3e6bf4d1a6bc8d35f16e1afe714631be2156587432a3c7f3b18ec57854a4f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ONP2L35FBVR3ASES3IHQOY6FAG/bundle.json","state_url":"https://pith.science/pith/ONP2L35FBVR3ASES3IHQOY6FAG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ONP2L35FBVR3ASES3IHQOY6FAG/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":"2026-07-06T16:59:38Z","links":{"resolver":"https://pith.science/pith/ONP2L35FBVR3ASES3IHQOY6FAG","bundle":"https://pith.science/pith/ONP2L35FBVR3ASES3IHQOY6FAG/bundle.json","state":"https://pith.science/pith/ONP2L35FBVR3ASES3IHQOY6FAG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ONP2L35FBVR3ASES3IHQOY6FAG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ONP2L35FBVR3ASES3IHQOY6FAG","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":"a717fd121203259cc6574253722f10c4fbe0ad0505eec2c38ebf15c0019aa5cd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-28T08:36:01Z","title_canon_sha256":"1edeabaf2ac598cc431d1ce1a280d57d549edc4f9a1969e1664033dea5e38f39"},"schema_version":"1.0","source":{"id":"2507.20622","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20622","created_at":"2026-07-05T11:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20622v1","created_at":"2026-07-05T11:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20622","created_at":"2026-07-05T11:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"ONP2L35FBVR3","created_at":"2026-07-05T11:44:22Z"},{"alias_kind":"pith_short_16","alias_value":"ONP2L35FBVR3ASES","created_at":"2026-07-05T11:44:22Z"},{"alias_kind":"pith_short_8","alias_value":"ONP2L35F","created_at":"2026-07-05T11:44:22Z"}],"graph_snapshots":[{"event_id":"sha256:ceb3e6bf4d1a6bc8d35f16e1afe714631be2156587432a3c7f3b18ec57854a4f","target":"graph","created_at":"2026-07-05T11:44:22Z","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/2507.20622/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in foundation models, particularly Vision Language Models (VLMs), have demonstrated remarkable capabilities in visual and linguistic reasoning for VIL tasks. Despite this progress, existing approaches primarily utilize these models for learning high-level plans from human demonstrations, relying on pre-defined motion primitives for executing physical interactions, which remains a major bottleneck for robotic systems. In this work, we present FMimic, a no","authors_text":"Guangyan Chen, Haoyang Lu, Meiling Wang, Mengxiao Hu, Mengyin Fu, Te Cui, Tianxing Zhou, Yao Mu, Yi Yang, Yufeng Yue, Zicai Peng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-28T08:36:01Z","title":"FMimic: Foundation Models are Fine-grained Action Learners from Human Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20622","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:f901aad1e10821cb069b1195cb6045aa763c7ffa40b39b730f7915fd361deeb3","target":"record","created_at":"2026-07-05T11:44:22Z","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":"a717fd121203259cc6574253722f10c4fbe0ad0505eec2c38ebf15c0019aa5cd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-28T08:36:01Z","title_canon_sha256":"1edeabaf2ac598cc431d1ce1a280d57d549edc4f9a1969e1664033dea5e38f39"},"schema_version":"1.0","source":{"id":"2507.20622","kind":"arxiv","version":1}},"canonical_sha256":"735fa5efa50d63b04892da0f0763c5018d6d5fef8c76a503f4138acea3cbd49d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"735fa5efa50d63b04892da0f0763c5018d6d5fef8c76a503f4138acea3cbd49d","first_computed_at":"2026-07-05T11:44:22.688960Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:22.688960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HzSEQbhzI7PechztEQX6OU93mpqBBBPWNYbaeRt0MrhhLqfIH/BdyWOhgNlvS0GX9DPh9SNhXrwoOROqHpP3DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:22.689405Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.20622","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f901aad1e10821cb069b1195cb6045aa763c7ffa40b39b730f7915fd361deeb3","sha256:ceb3e6bf4d1a6bc8d35f16e1afe714631be2156587432a3c7f3b18ec57854a4f"],"state_sha256":"3364259e2f5f301dcc50eb738e4e2b49a6e830289566adb789d118b817aabd25"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KG9UjXF4p4VVRGnemgSGbuXJkuejVrBBhDa5d38K4+0SlE1SLc06IqIok88JV7ynYVlty1u1k4FwsTtt5ax1CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:59:38.258876Z","bundle_sha256":"fd5a411824cb2ab465f5e27499695aaaa3ce2c6827a6462c3e31c5efa82667e6"}}