{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JGCFBTRBM3VKOBOZZUUDJXOAFD","short_pith_number":"pith:JGCFBTRB","canonical_record":{"source":{"id":"2409.17727","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-26T10:56:35Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c95248d109701e4c7ceee7d5f2fe706e3b214e313868a70f464d6ebc09d8dfc3","abstract_canon_sha256":"4c8079fe9e7fd1b606b3fab82d1e8ac6192347e4bab7a2fd86f319b418d01c36"},"schema_version":"1.0"},"canonical_sha256":"498450ce2166eaa705d9cd2834ddc028dd9b338243b360f68c0819ee51383702","source":{"kind":"arxiv","id":"2409.17727","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17727","created_at":"2026-07-05T09:12:14Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17727v1","created_at":"2026-07-05T09:12:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17727","created_at":"2026-07-05T09:12:14Z"},{"alias_kind":"pith_short_12","alias_value":"JGCFBTRBM3VK","created_at":"2026-07-05T09:12:14Z"},{"alias_kind":"pith_short_16","alias_value":"JGCFBTRBM3VKOBOZ","created_at":"2026-07-05T09:12:14Z"},{"alias_kind":"pith_short_8","alias_value":"JGCFBTRB","created_at":"2026-07-05T09:12:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JGCFBTRBM3VKOBOZZUUDJXOAFD","target":"record","payload":{"canonical_record":{"source":{"id":"2409.17727","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-26T10:56:35Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c95248d109701e4c7ceee7d5f2fe706e3b214e313868a70f464d6ebc09d8dfc3","abstract_canon_sha256":"4c8079fe9e7fd1b606b3fab82d1e8ac6192347e4bab7a2fd86f319b418d01c36"},"schema_version":"1.0"},"canonical_sha256":"498450ce2166eaa705d9cd2834ddc028dd9b338243b360f68c0819ee51383702","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:14.813956Z","signature_b64":"HA9EkeVK8rPhbDrcNc7gnrKLE9qIRk9FISQL9qD7s0LKyYlKsB7KiAagvMy8Q4c1YFPUoIEqAAkm5CZfHoNQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"498450ce2166eaa705d9cd2834ddc028dd9b338243b360f68c0819ee51383702","last_reissued_at":"2026-07-05T09:12:14.813472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:14.813472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.17727","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":"2026-07-05T09:12:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eiD/FBCUzHlKEriNbaYOk9PniMnKnZwAjEP/Sc2htUh1BjF0yoazqVJR6rN+iMSsfNM42i1fTyTWRnDTbMxJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:03:24.143366Z"},"content_sha256":"77eda24a9bd231013472ff1cd2b44e67540c7fab17b94dac325b4a904c0b37d8","schema_version":"1.0","event_id":"sha256:77eda24a9bd231013472ff1cd2b44e67540c7fab17b94dac325b4a904c0b37d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JGCFBTRBM3VKOBOZZUUDJXOAFD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robotic-CLIP: Fine-tuning CLIP on Action Data for Robotic Applications","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Anh Nguyen, Baoru Huang, Minh Nhat Vu, Ngan Le, Nghia Nguyen, Thieu Vo, Tung D. Ta","submitted_at":"2024-09-26T10:56:35Z","abstract_excerpt":"Vision language models have played a key role in extracting meaningful features for various robotic applications. Among these, Contrastive Language-Image Pretraining (CLIP) is widely used in robotic tasks that require both vision and natural language understanding. However, CLIP was trained solely on static images paired with text prompts and has not yet been fully adapted for robotic tasks involving dynamic actions. In this paper, we introduce Robotic-CLIP to enhance robotic perception capabilities. We first gather and label large-scale action data, and then build our Robotic-CLIP by fine-tun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17727","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/2409.17727/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":"2026-07-05T09:12:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kmlMZWOwKgCyIU/7IainwAMPirXSO8+fSxpFThK4FaBFMXpecFNJIv539DdJcYtnfUTbK0z2ITOm7TVnDm6yBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:03:24.143857Z"},"content_sha256":"8c88d4313f2379c8fd184e7c0f7ab249f2d0f346e11d87689355aa9ab5e79edb","schema_version":"1.0","event_id":"sha256:8c88d4313f2379c8fd184e7c0f7ab249f2d0f346e11d87689355aa9ab5e79edb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JGCFBTRBM3VKOBOZZUUDJXOAFD/bundle.json","state_url":"https://pith.science/pith/JGCFBTRBM3VKOBOZZUUDJXOAFD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JGCFBTRBM3VKOBOZZUUDJXOAFD/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":"2026-08-08T15:03:24Z","links":{"resolver":"https://pith.science/pith/JGCFBTRBM3VKOBOZZUUDJXOAFD","bundle":"https://pith.science/pith/JGCFBTRBM3VKOBOZZUUDJXOAFD/bundle.json","state":"https://pith.science/pith/JGCFBTRBM3VKOBOZZUUDJXOAFD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JGCFBTRBM3VKOBOZZUUDJXOAFD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JGCFBTRBM3VKOBOZZUUDJXOAFD","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":"4c8079fe9e7fd1b606b3fab82d1e8ac6192347e4bab7a2fd86f319b418d01c36","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-26T10:56:35Z","title_canon_sha256":"c95248d109701e4c7ceee7d5f2fe706e3b214e313868a70f464d6ebc09d8dfc3"},"schema_version":"1.0","source":{"id":"2409.17727","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17727","created_at":"2026-07-05T09:12:14Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17727v1","created_at":"2026-07-05T09:12:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17727","created_at":"2026-07-05T09:12:14Z"},{"alias_kind":"pith_short_12","alias_value":"JGCFBTRBM3VK","created_at":"2026-07-05T09:12:14Z"},{"alias_kind":"pith_short_16","alias_value":"JGCFBTRBM3VKOBOZ","created_at":"2026-07-05T09:12:14Z"},{"alias_kind":"pith_short_8","alias_value":"JGCFBTRB","created_at":"2026-07-05T09:12:14Z"}],"graph_snapshots":[{"event_id":"sha256:8c88d4313f2379c8fd184e7c0f7ab249f2d0f346e11d87689355aa9ab5e79edb","target":"graph","created_at":"2026-07-05T09:12:14Z","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/2409.17727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision language models have played a key role in extracting meaningful features for various robotic applications. Among these, Contrastive Language-Image Pretraining (CLIP) is widely used in robotic tasks that require both vision and natural language understanding. However, CLIP was trained solely on static images paired with text prompts and has not yet been fully adapted for robotic tasks involving dynamic actions. In this paper, we introduce Robotic-CLIP to enhance robotic perception capabilities. We first gather and label large-scale action data, and then build our Robotic-CLIP by fine-tun","authors_text":"Anh Nguyen, Baoru Huang, Minh Nhat Vu, Ngan Le, Nghia Nguyen, Thieu Vo, Tung D. Ta","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-26T10:56:35Z","title":"Robotic-CLIP: Fine-tuning CLIP on Action Data for Robotic Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17727","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":"sha256:77eda24a9bd231013472ff1cd2b44e67540c7fab17b94dac325b4a904c0b37d8","target":"record","created_at":"2026-07-05T09:12:14Z","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":"4c8079fe9e7fd1b606b3fab82d1e8ac6192347e4bab7a2fd86f319b418d01c36","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-26T10:56:35Z","title_canon_sha256":"c95248d109701e4c7ceee7d5f2fe706e3b214e313868a70f464d6ebc09d8dfc3"},"schema_version":"1.0","source":{"id":"2409.17727","kind":"arxiv","version":1}},"canonical_sha256":"498450ce2166eaa705d9cd2834ddc028dd9b338243b360f68c0819ee51383702","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"498450ce2166eaa705d9cd2834ddc028dd9b338243b360f68c0819ee51383702","first_computed_at":"2026-07-05T09:12:14.813472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:14.813472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HA9EkeVK8rPhbDrcNc7gnrKLE9qIRk9FISQL9qD7s0LKyYlKsB7KiAagvMy8Q4c1YFPUoIEqAAkm5CZfHoNQAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:14.813956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.17727","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77eda24a9bd231013472ff1cd2b44e67540c7fab17b94dac325b4a904c0b37d8","sha256:8c88d4313f2379c8fd184e7c0f7ab249f2d0f346e11d87689355aa9ab5e79edb"],"state_sha256":"c4d75ae2c8924b17593568c3ae7ba3d0f1ee889b8b5b51bc3c5ca49feadb249b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r1u5FUyjzdpRqKpxIFBvJepJgs6HR3/ztv8ItEFy9JPBYH9+QSK0QRbwDsJxOQvOYAR1XlLMz3eP/a6ZmGj+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:03:24.148199Z","bundle_sha256":"e9d4714d845a5c7fb4686ece889777d1debe0767dc9ec119ccef20b7dcad0066"}}