{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CO3YFY7NJHQDPCVRC6ZEQPQVJ4","short_pith_number":"pith:CO3YFY7N","canonical_record":{"source":{"id":"2501.18880","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T04:30:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bc892686095129445b0bfd90bd953f79f38758aef6f8b62461bcd88e443998a7","abstract_canon_sha256":"86d8d528255f2c36581497643f5a1921bc1da045d37f5f8d42da8992c906da8a"},"schema_version":"1.0"},"canonical_sha256":"13b782e3ed49e0378ab117b2483e154f3e295468a62f8da5baaeed5a976d64a1","source":{"kind":"arxiv","id":"2501.18880","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18880","created_at":"2026-07-05T10:07:52Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18880v1","created_at":"2026-07-05T10:07:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18880","created_at":"2026-07-05T10:07:52Z"},{"alias_kind":"pith_short_12","alias_value":"CO3YFY7NJHQD","created_at":"2026-07-05T10:07:52Z"},{"alias_kind":"pith_short_16","alias_value":"CO3YFY7NJHQDPCVR","created_at":"2026-07-05T10:07:52Z"},{"alias_kind":"pith_short_8","alias_value":"CO3YFY7N","created_at":"2026-07-05T10:07:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CO3YFY7NJHQDPCVRC6ZEQPQVJ4","target":"record","payload":{"canonical_record":{"source":{"id":"2501.18880","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T04:30:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bc892686095129445b0bfd90bd953f79f38758aef6f8b62461bcd88e443998a7","abstract_canon_sha256":"86d8d528255f2c36581497643f5a1921bc1da045d37f5f8d42da8992c906da8a"},"schema_version":"1.0"},"canonical_sha256":"13b782e3ed49e0378ab117b2483e154f3e295468a62f8da5baaeed5a976d64a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:52.981243Z","signature_b64":"eQth4r1xvMAgvs4pJipvqEvVSB7Bpdgk7xCFuh1kVKCH9XOnfbdAXQ5rsVieLXTe8ZxHch4AAJumYSzl4cNvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13b782e3ed49e0378ab117b2483e154f3e295468a62f8da5baaeed5a976d64a1","last_reissued_at":"2026-07-05T10:07:52.980762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:52.980762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.18880","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":"2026-07-05T10:07:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9pp146M5xOIjBWtdmgppE6ya+/zu5nAWo8JV/PwLb6uDPu3RjEmha5pbiQOPzOCrZsncUZJJavrK2KXm9fyiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:09:47.592861Z"},"content_sha256":"08d64c482f4293ffce19db2a603eb4120a5a2621e5870318646cfec5996441d8","schema_version":"1.0","event_id":"sha256:08d64c482f4293ffce19db2a603eb4120a5a2621e5870318646cfec5996441d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CO3YFY7NJHQDPCVRC6ZEQPQVJ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chinmay Hegde, Joshua R. Waite, Md. Zahid Hasan, Qisai Liu, Soumik Sarkar, Zhanhong Jiang","submitted_at":"2025-01-31T04:30:42Z","abstract_excerpt":"Vision-language model (VLM) fine-tuning for application-specific visual grounding based on natural language instructions has become one of the most popular approaches for learning-enabled autonomous systems. However, such fine-tuning relies heavily on high-quality datasets to achieve successful performance in various downstream tasks. Additionally, VLMs often encounter limitations due to insufficient and imbalanced fine-tuning data. To address these issues, we propose a new generalizable framework to improve VLM fine-tuning by integrating it with a reinforcement learning (RL) agent. Our method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18880","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/2501.18880/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":"2026-07-05T10:07:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8t8wAP5yEqRYARpnrCBnmMJzThiKkVD+tfaeVOhlMcSQr5xfBP/YRCFK3h3o1IBzf20VYnvTEWzCWJh4xFgKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:09:47.593158Z"},"content_sha256":"45ade3cbb740849199c07a0f7eacaf3f3a9ec2d1784f90f00acb30219ea1c257","schema_version":"1.0","event_id":"sha256:45ade3cbb740849199c07a0f7eacaf3f3a9ec2d1784f90f00acb30219ea1c257"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CO3YFY7NJHQDPCVRC6ZEQPQVJ4/bundle.json","state_url":"https://pith.science/pith/CO3YFY7NJHQDPCVRC6ZEQPQVJ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CO3YFY7NJHQDPCVRC6ZEQPQVJ4/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":"2026-08-17T14:09:47Z","links":{"resolver":"https://pith.science/pith/CO3YFY7NJHQDPCVRC6ZEQPQVJ4","bundle":"https://pith.science/pith/CO3YFY7NJHQDPCVRC6ZEQPQVJ4/bundle.json","state":"https://pith.science/pith/CO3YFY7NJHQDPCVRC6ZEQPQVJ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CO3YFY7NJHQDPCVRC6ZEQPQVJ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CO3YFY7NJHQDPCVRC6ZEQPQVJ4","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":"86d8d528255f2c36581497643f5a1921bc1da045d37f5f8d42da8992c906da8a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T04:30:42Z","title_canon_sha256":"bc892686095129445b0bfd90bd953f79f38758aef6f8b62461bcd88e443998a7"},"schema_version":"1.0","source":{"id":"2501.18880","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18880","created_at":"2026-07-05T10:07:52Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18880v1","created_at":"2026-07-05T10:07:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18880","created_at":"2026-07-05T10:07:52Z"},{"alias_kind":"pith_short_12","alias_value":"CO3YFY7NJHQD","created_at":"2026-07-05T10:07:52Z"},{"alias_kind":"pith_short_16","alias_value":"CO3YFY7NJHQDPCVR","created_at":"2026-07-05T10:07:52Z"},{"alias_kind":"pith_short_8","alias_value":"CO3YFY7N","created_at":"2026-07-05T10:07:52Z"}],"graph_snapshots":[{"event_id":"sha256:45ade3cbb740849199c07a0f7eacaf3f3a9ec2d1784f90f00acb30219ea1c257","target":"graph","created_at":"2026-07-05T10:07:52Z","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/2501.18880/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language model (VLM) fine-tuning for application-specific visual grounding based on natural language instructions has become one of the most popular approaches for learning-enabled autonomous systems. However, such fine-tuning relies heavily on high-quality datasets to achieve successful performance in various downstream tasks. Additionally, VLMs often encounter limitations due to insufficient and imbalanced fine-tuning data. To address these issues, we propose a new generalizable framework to improve VLM fine-tuning by integrating it with a reinforcement learning (RL) agent. Our method","authors_text":"Chinmay Hegde, Joshua R. Waite, Md. Zahid Hasan, Qisai Liu, Soumik Sarkar, Zhanhong Jiang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T04:30:42Z","title":"RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18880","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":"sha256:08d64c482f4293ffce19db2a603eb4120a5a2621e5870318646cfec5996441d8","target":"record","created_at":"2026-07-05T10:07:52Z","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":"86d8d528255f2c36581497643f5a1921bc1da045d37f5f8d42da8992c906da8a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T04:30:42Z","title_canon_sha256":"bc892686095129445b0bfd90bd953f79f38758aef6f8b62461bcd88e443998a7"},"schema_version":"1.0","source":{"id":"2501.18880","kind":"arxiv","version":1}},"canonical_sha256":"13b782e3ed49e0378ab117b2483e154f3e295468a62f8da5baaeed5a976d64a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13b782e3ed49e0378ab117b2483e154f3e295468a62f8da5baaeed5a976d64a1","first_computed_at":"2026-07-05T10:07:52.980762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:52.980762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eQth4r1xvMAgvs4pJipvqEvVSB7Bpdgk7xCFuh1kVKCH9XOnfbdAXQ5rsVieLXTe8ZxHch4AAJumYSzl4cNvDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:52.981243Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18880","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08d64c482f4293ffce19db2a603eb4120a5a2621e5870318646cfec5996441d8","sha256:45ade3cbb740849199c07a0f7eacaf3f3a9ec2d1784f90f00acb30219ea1c257"],"state_sha256":"f3182eccb28d3dce6a22fd11fc43c242992d934fb9da84639a93f25f603d86d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CT1KrMQm5bIdD7XsXaSsAn/MsGbj37Fk/PP3htssC/9x7I6dTUMpmxDYCVlOyZQdWRg7assqv3KrQdZ4eRs8CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T14:09:47.596619Z","bundle_sha256":"7fe2515399d0edcd5d27df794499f3d5fc053cc00452747f7c405b19420f57f1"}}