{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NCCZAI3Q5ZRPA5KVPJ4PREWCWY","short_pith_number":"pith:NCCZAI3Q","canonical_record":{"source":{"id":"2406.11815","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-17T17:55:29Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"8913ee406cbe0eda60b0f180bf5d2f440ef039745128b400bbe14019005e649e","abstract_canon_sha256":"52f6dfd82684d92535a492e6e7a6916c065b58f4b9cb62ac441d2e9b928f8c07"},"schema_version":"1.0"},"canonical_sha256":"6885902370ee62f075557a78f892c2b61dac8dbc3ff7915e6cbbd63049e476ce","source":{"kind":"arxiv","id":"2406.11815","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11815","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11815v1","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11815","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_12","alias_value":"NCCZAI3Q5ZRP","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_16","alias_value":"NCCZAI3Q5ZRPA5KV","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_8","alias_value":"NCCZAI3Q","created_at":"2026-07-05T08:32:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NCCZAI3Q5ZRPA5KVPJ4PREWCWY","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11815","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-17T17:55:29Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"8913ee406cbe0eda60b0f180bf5d2f440ef039745128b400bbe14019005e649e","abstract_canon_sha256":"52f6dfd82684d92535a492e6e7a6916c065b58f4b9cb62ac441d2e9b928f8c07"},"schema_version":"1.0"},"canonical_sha256":"6885902370ee62f075557a78f892c2b61dac8dbc3ff7915e6cbbd63049e476ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:58.183608Z","signature_b64":"ok/4IWEK5oHvE6JeABcyyXwgRa88L38EK9wkv6lidIJdZndhwIJd6ru2Zev2CqhX0eJu3FaeHmcVcfvLodwmDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6885902370ee62f075557a78f892c2b61dac8dbc3ff7915e6cbbd63049e476ce","last_reissued_at":"2026-07-05T08:32:58.183180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:58.183180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11815","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":"2026-07-05T08:32:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"61Mb1d4uXSqvuncoSzKBE2NUiqxkwSd0rGe4V7XCkVUbhD13/a4fawdy37+qqyID3yAE1Lt2SlNaO+noQ9gkAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:27:31.516933Z"},"content_sha256":"4c27203a942514cbed461c09ab8a5df99d0202dc966d85c1171e32ea858025b3","schema_version":"1.0","event_id":"sha256:4c27203a942514cbed461c09ab8a5df99d0202dc966d85c1171e32ea858025b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NCCZAI3Q5ZRPA5KVPJ4PREWCWY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Baifeng Shi, Dantong Niu, Giscard Biamby, Jerome Quenum, Roei Herzig, Trevor Darrell, Yutong Bai, Yuvan Sharma","submitted_at":"2024-06-17T17:55:29Z","abstract_excerpt":"In recent years, instruction-tuned Large Multimodal Models (LMMs) have been successful at several tasks, including image captioning and visual question answering; yet leveraging these models remains an open question for robotics. Prior LMMs for robotics applications have been extensively trained on language and action data, but their ability to generalize in different settings has often been less than desired. To address this, we introduce LLARVA, a model trained with a novel instruction tuning method that leverages structured prompts to unify a range of robotic learning tasks, scenarios, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11815","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/2406.11815/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":"2026-07-05T08:32:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wdwCj9vGxT0/yFu7XxDnQV2HGY4oSYhhVXV4kml9ZnOzp87LuPAsYNBLiu+lQ85ejHIfIdusd54Vk70TPBKvBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:27:31.517492Z"},"content_sha256":"460d92ff7b2c9695f2f3ba324f94b91918e92f6355c5e0cbfe0e7d48b14f9535","schema_version":"1.0","event_id":"sha256:460d92ff7b2c9695f2f3ba324f94b91918e92f6355c5e0cbfe0e7d48b14f9535"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NCCZAI3Q5ZRPA5KVPJ4PREWCWY/bundle.json","state_url":"https://pith.science/pith/NCCZAI3Q5ZRPA5KVPJ4PREWCWY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NCCZAI3Q5ZRPA5KVPJ4PREWCWY/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":"2026-08-06T11:27:31Z","links":{"resolver":"https://pith.science/pith/NCCZAI3Q5ZRPA5KVPJ4PREWCWY","bundle":"https://pith.science/pith/NCCZAI3Q5ZRPA5KVPJ4PREWCWY/bundle.json","state":"https://pith.science/pith/NCCZAI3Q5ZRPA5KVPJ4PREWCWY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NCCZAI3Q5ZRPA5KVPJ4PREWCWY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NCCZAI3Q5ZRPA5KVPJ4PREWCWY","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":"52f6dfd82684d92535a492e6e7a6916c065b58f4b9cb62ac441d2e9b928f8c07","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-17T17:55:29Z","title_canon_sha256":"8913ee406cbe0eda60b0f180bf5d2f440ef039745128b400bbe14019005e649e"},"schema_version":"1.0","source":{"id":"2406.11815","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11815","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11815v1","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11815","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_12","alias_value":"NCCZAI3Q5ZRP","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_16","alias_value":"NCCZAI3Q5ZRPA5KV","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_8","alias_value":"NCCZAI3Q","created_at":"2026-07-05T08:32:58Z"}],"graph_snapshots":[{"event_id":"sha256:460d92ff7b2c9695f2f3ba324f94b91918e92f6355c5e0cbfe0e7d48b14f9535","target":"graph","created_at":"2026-07-05T08:32:58Z","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/2406.11815/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, instruction-tuned Large Multimodal Models (LMMs) have been successful at several tasks, including image captioning and visual question answering; yet leveraging these models remains an open question for robotics. Prior LMMs for robotics applications have been extensively trained on language and action data, but their ability to generalize in different settings has often been less than desired. To address this, we introduce LLARVA, a model trained with a novel instruction tuning method that leverages structured prompts to unify a range of robotic learning tasks, scenarios, and ","authors_text":"Baifeng Shi, Dantong Niu, Giscard Biamby, Jerome Quenum, Roei Herzig, Trevor Darrell, Yutong Bai, Yuvan Sharma","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-17T17:55:29Z","title":"LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11815","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":"sha256:4c27203a942514cbed461c09ab8a5df99d0202dc966d85c1171e32ea858025b3","target":"record","created_at":"2026-07-05T08:32:58Z","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":"52f6dfd82684d92535a492e6e7a6916c065b58f4b9cb62ac441d2e9b928f8c07","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-17T17:55:29Z","title_canon_sha256":"8913ee406cbe0eda60b0f180bf5d2f440ef039745128b400bbe14019005e649e"},"schema_version":"1.0","source":{"id":"2406.11815","kind":"arxiv","version":1}},"canonical_sha256":"6885902370ee62f075557a78f892c2b61dac8dbc3ff7915e6cbbd63049e476ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6885902370ee62f075557a78f892c2b61dac8dbc3ff7915e6cbbd63049e476ce","first_computed_at":"2026-07-05T08:32:58.183180Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:58.183180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ok/4IWEK5oHvE6JeABcyyXwgRa88L38EK9wkv6lidIJdZndhwIJd6ru2Zev2CqhX0eJu3FaeHmcVcfvLodwmDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:58.183608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11815","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c27203a942514cbed461c09ab8a5df99d0202dc966d85c1171e32ea858025b3","sha256:460d92ff7b2c9695f2f3ba324f94b91918e92f6355c5e0cbfe0e7d48b14f9535"],"state_sha256":"1cd800ec9357fe219b68577ab74ad6660d36c5be9d63f3f170000169d8ff5df0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kn0Zbmi6tZySh/kKcAWR4jltdyR1H1MQ48aqiLqZI2Ia6O/Kv+HnoLcd6Tj84l1KN1/A++ftRM9s3HSEv3bDDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T11:27:31.521547Z","bundle_sha256":"9f35f39cc2b2365550b962a22d0caf35819d6210bea404ba31c4325c6fe283b2"}}