{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5NOCEGFGN5A5AW7GU7WMXPJQMB","short_pith_number":"pith:5NOCEGFG","canonical_record":{"source":{"id":"2308.16493","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-31T06:53:55Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"ab1236f74611c3b815bbd7480a7d7489cf24373461774cd7722f50ef8ebc6976","abstract_canon_sha256":"442132935192c28e8059dc8eefec96688873083ae53eda5dfb20b0781384b77f"},"schema_version":"1.0"},"canonical_sha256":"eb5c2218a66f41d05be6a7eccbbd30607e0eddb62dc2dad14a48669d8ea6a37d","source":{"kind":"arxiv","id":"2308.16493","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.16493","created_at":"2026-07-05T06:46:28Z"},{"alias_kind":"arxiv_version","alias_value":"2308.16493v1","created_at":"2026-07-05T06:46:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16493","created_at":"2026-07-05T06:46:28Z"},{"alias_kind":"pith_short_12","alias_value":"5NOCEGFGN5A5","created_at":"2026-07-05T06:46:28Z"},{"alias_kind":"pith_short_16","alias_value":"5NOCEGFGN5A5AW7G","created_at":"2026-07-05T06:46:28Z"},{"alias_kind":"pith_short_8","alias_value":"5NOCEGFG","created_at":"2026-07-05T06:46:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5NOCEGFGN5A5AW7GU7WMXPJQMB","target":"record","payload":{"canonical_record":{"source":{"id":"2308.16493","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-31T06:53:55Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"ab1236f74611c3b815bbd7480a7d7489cf24373461774cd7722f50ef8ebc6976","abstract_canon_sha256":"442132935192c28e8059dc8eefec96688873083ae53eda5dfb20b0781384b77f"},"schema_version":"1.0"},"canonical_sha256":"eb5c2218a66f41d05be6a7eccbbd30607e0eddb62dc2dad14a48669d8ea6a37d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:28.431534Z","signature_b64":"AAO2cyk1FK3L+yUttekD6/3V5257jlnULNIVKruicjfN3z3YPxnYceLCWdjLU1LWb4MJbnB91Ni6rGlz0y0ABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb5c2218a66f41d05be6a7eccbbd30607e0eddb62dc2dad14a48669d8ea6a37d","last_reissued_at":"2026-07-05T06:46:28.431131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:28.431131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.16493","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":"2026-07-05T06:46:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BhkBh6SGhbYMT/SLkl4fZufn/n6wmeDm995HL/O0g/+3tRI2kBfgK55PTo8Vl1+jcwgbdkUgzp3W1WF9Lku4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:25:09.319263Z"},"content_sha256":"613daafc530c9a6c8feb88d6352f9639fc9f1326df398c379ee3872bf4b7dabc","schema_version":"1.0","event_id":"sha256:613daafc530c9a6c8feb88d6352f9639fc9f1326df398c379ee3872bf4b7dabc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5NOCEGFGN5A5AW7GU7WMXPJQMB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Expanding Frozen Vision-Language Models without Retraining: Towards Improved Robot Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Mani Amani, Reza Akhavian, Riley Tavassoli","submitted_at":"2023-08-31T06:53:55Z","abstract_excerpt":"Vision-language models (VLMs) have shown powerful capabilities in visual question answering and reasoning tasks by combining visual representations with the abstract skill set large language models (LLMs) learn during pretraining. Vision, while the most popular modality to augment LLMs with, is only one representation of a scene. In human-robot interaction scenarios, robot perception requires accurate scene understanding by the robot. In this paper, we define and demonstrate a method of aligning the embedding spaces of different modalities (in this case, inertial measurement unit (IMU) data) t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16493","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/2308.16493/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":"2026-07-05T06:46:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x41rnQiA5GtMd3vcZc2ZM1tTAfxu7bz5f90NIgBcD8N9iXvFewaEp6RYYJYJTkvEnB/isN1fixBA7r2ik7FUAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:25:09.319840Z"},"content_sha256":"43c3e0d7ef4f29dee92bcd5f1be57fa71a2ba677646a779a4e2d376fbc41dfd7","schema_version":"1.0","event_id":"sha256:43c3e0d7ef4f29dee92bcd5f1be57fa71a2ba677646a779a4e2d376fbc41dfd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5NOCEGFGN5A5AW7GU7WMXPJQMB/bundle.json","state_url":"https://pith.science/pith/5NOCEGFGN5A5AW7GU7WMXPJQMB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5NOCEGFGN5A5AW7GU7WMXPJQMB/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":"2026-08-08T06:25:09Z","links":{"resolver":"https://pith.science/pith/5NOCEGFGN5A5AW7GU7WMXPJQMB","bundle":"https://pith.science/pith/5NOCEGFGN5A5AW7GU7WMXPJQMB/bundle.json","state":"https://pith.science/pith/5NOCEGFGN5A5AW7GU7WMXPJQMB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5NOCEGFGN5A5AW7GU7WMXPJQMB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5NOCEGFGN5A5AW7GU7WMXPJQMB","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":"442132935192c28e8059dc8eefec96688873083ae53eda5dfb20b0781384b77f","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-31T06:53:55Z","title_canon_sha256":"ab1236f74611c3b815bbd7480a7d7489cf24373461774cd7722f50ef8ebc6976"},"schema_version":"1.0","source":{"id":"2308.16493","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.16493","created_at":"2026-07-05T06:46:28Z"},{"alias_kind":"arxiv_version","alias_value":"2308.16493v1","created_at":"2026-07-05T06:46:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16493","created_at":"2026-07-05T06:46:28Z"},{"alias_kind":"pith_short_12","alias_value":"5NOCEGFGN5A5","created_at":"2026-07-05T06:46:28Z"},{"alias_kind":"pith_short_16","alias_value":"5NOCEGFGN5A5AW7G","created_at":"2026-07-05T06:46:28Z"},{"alias_kind":"pith_short_8","alias_value":"5NOCEGFG","created_at":"2026-07-05T06:46:28Z"}],"graph_snapshots":[{"event_id":"sha256:43c3e0d7ef4f29dee92bcd5f1be57fa71a2ba677646a779a4e2d376fbc41dfd7","target":"graph","created_at":"2026-07-05T06:46:28Z","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/2308.16493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have shown powerful capabilities in visual question answering and reasoning tasks by combining visual representations with the abstract skill set large language models (LLMs) learn during pretraining. Vision, while the most popular modality to augment LLMs with, is only one representation of a scene. In human-robot interaction scenarios, robot perception requires accurate scene understanding by the robot. In this paper, we define and demonstrate a method of aligning the embedding spaces of different modalities (in this case, inertial measurement unit (IMU) data) t","authors_text":"Mani Amani, Reza Akhavian, Riley Tavassoli","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-31T06:53:55Z","title":"Expanding Frozen Vision-Language Models without Retraining: Towards Improved Robot Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16493","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":"sha256:613daafc530c9a6c8feb88d6352f9639fc9f1326df398c379ee3872bf4b7dabc","target":"record","created_at":"2026-07-05T06:46:28Z","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":"442132935192c28e8059dc8eefec96688873083ae53eda5dfb20b0781384b77f","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-31T06:53:55Z","title_canon_sha256":"ab1236f74611c3b815bbd7480a7d7489cf24373461774cd7722f50ef8ebc6976"},"schema_version":"1.0","source":{"id":"2308.16493","kind":"arxiv","version":1}},"canonical_sha256":"eb5c2218a66f41d05be6a7eccbbd30607e0eddb62dc2dad14a48669d8ea6a37d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb5c2218a66f41d05be6a7eccbbd30607e0eddb62dc2dad14a48669d8ea6a37d","first_computed_at":"2026-07-05T06:46:28.431131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:28.431131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AAO2cyk1FK3L+yUttekD6/3V5257jlnULNIVKruicjfN3z3YPxnYceLCWdjLU1LWb4MJbnB91Ni6rGlz0y0ABA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:28.431534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.16493","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:613daafc530c9a6c8feb88d6352f9639fc9f1326df398c379ee3872bf4b7dabc","sha256:43c3e0d7ef4f29dee92bcd5f1be57fa71a2ba677646a779a4e2d376fbc41dfd7"],"state_sha256":"ceeae10880620ce3ddd9c4fdb5c047779017f280ac239fb2e13dcb5c5fa3bfce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"efAuVYTeWPSlr7fOfIht/xFzVVQnIudSZ2rYGQY2I/3yoXQIJ620RMYkdh7KGHdfJDmcRdsLlweIVR1iq2FXAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:25:09.324392Z","bundle_sha256":"98f6265d12bb0a3a2ed692eeba169801893c1c2103d797c0e6f2f64815ff6085"}}