{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4RMMTDPLP2HUXUKBA223CB4AMZ","short_pith_number":"pith:4RMMTDPL","canonical_record":{"source":{"id":"2505.23678","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:20:26Z","cross_cats_sorted":[],"title_canon_sha256":"2325a750a619f2bf4918b0015036d01ea081a11617f88218dd52a918c36ecfb5","abstract_canon_sha256":"42e722d90a276cd68567a1bbef03a739c5d5cc0c04158056d5b4d03e9758c90a"},"schema_version":"1.0"},"canonical_sha256":"e458c98deb7e8f4bd14106b5b10780667ed8f2e9f5b9668fa1f0368fec62d164","source":{"kind":"arxiv","id":"2505.23678","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23678","created_at":"2026-05-20T00:01:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23678v3","created_at":"2026-05-20T00:01:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23678","created_at":"2026-05-20T00:01:34Z"},{"alias_kind":"pith_short_12","alias_value":"4RMMTDPLP2HU","created_at":"2026-05-20T00:01:34Z"},{"alias_kind":"pith_short_16","alias_value":"4RMMTDPLP2HUXUKB","created_at":"2026-05-20T00:01:34Z"},{"alias_kind":"pith_short_8","alias_value":"4RMMTDPL","created_at":"2026-05-20T00:01:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4RMMTDPLP2HUXUKBA223CB4AMZ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23678","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:20:26Z","cross_cats_sorted":[],"title_canon_sha256":"2325a750a619f2bf4918b0015036d01ea081a11617f88218dd52a918c36ecfb5","abstract_canon_sha256":"42e722d90a276cd68567a1bbef03a739c5d5cc0c04158056d5b4d03e9758c90a"},"schema_version":"1.0"},"canonical_sha256":"e458c98deb7e8f4bd14106b5b10780667ed8f2e9f5b9668fa1f0368fec62d164","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:34.061935Z","signature_b64":"BrU4PjXRPN8vgyJNwWkVkq7cTc63phwjcFd99EmMslGqs4xXLnUsnCxPqYGgivwz9Pjh40QpU76RLwixUs6/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e458c98deb7e8f4bd14106b5b10780667ed8f2e9f5b9668fa1f0368fec62d164","last_reissued_at":"2026-05-20T00:01:34.061098Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:34.061098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23678","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ABzQuC3xs4PTmJ4dasCV9VZq4sRbNDMUDG40F7hkybCix35egrvIUfvKmoOEGpsgx3xgzSAF+ORhIGWukualCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T06:55:52.701186Z"},"content_sha256":"97862ee9557358386e2ce63105bf0f8f5edab728769852209dd9765df1cea4df","schema_version":"1.0","event_id":"sha256:97862ee9557358386e2ce63105bf0f8f5edab728769852209dd9765df1cea4df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4RMMTDPLP2HUXUKBA223CB4AMZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grounded Reinforcement Learning for Visual Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aviral Kumar, Ayush Jain, Gabriel Sarch, Katerina Fragkiadaki, Michael J. Tarr, Naitik Khandelwal, Snigdha Saha","submitted_at":"2025-05-29T17:20:26Z","abstract_excerpt":"While reinforcement learning (RL) over chains of thought has significantly advanced language models in tasks such as mathematics and coding, visual reasoning introduces added complexity by requiring models to direct visual attention, interpret perceptual inputs, and ground abstract reasoning in spatial evidence. We introduce ViGoRL (Visually Grounded Reinforcement Learning), a vision-language model trained with RL to explicitly anchor each reasoning step to specific visual coordinates. Inspired by human visual decision-making, ViGoRL learns to produce spatially grounded reasoning traces, guidi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23678","kind":"arxiv","version":3},"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/2505.23678/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":"2026-05-20T00:01:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DpLWx8AggIZlM/1pz1Y78dfbJb7NmtXiSQ8uhtn1O6rup/zQoUZGuv8ZEU4Rc6OgX6O2Lvm+qH+lwzJTBkW4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T06:55:52.701580Z"},"content_sha256":"7e6947bff5ca618045add2a61be93026119c0de848f6822fcdea53ae9e3ffeff","schema_version":"1.0","event_id":"sha256:7e6947bff5ca618045add2a61be93026119c0de848f6822fcdea53ae9e3ffeff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4RMMTDPLP2HUXUKBA223CB4AMZ/bundle.json","state_url":"https://pith.science/pith/4RMMTDPLP2HUXUKBA223CB4AMZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4RMMTDPLP2HUXUKBA223CB4AMZ/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":"2026-05-20T06:55:52Z","links":{"resolver":"https://pith.science/pith/4RMMTDPLP2HUXUKBA223CB4AMZ","bundle":"https://pith.science/pith/4RMMTDPLP2HUXUKBA223CB4AMZ/bundle.json","state":"https://pith.science/pith/4RMMTDPLP2HUXUKBA223CB4AMZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4RMMTDPLP2HUXUKBA223CB4AMZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4RMMTDPLP2HUXUKBA223CB4AMZ","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":"42e722d90a276cd68567a1bbef03a739c5d5cc0c04158056d5b4d03e9758c90a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:20:26Z","title_canon_sha256":"2325a750a619f2bf4918b0015036d01ea081a11617f88218dd52a918c36ecfb5"},"schema_version":"1.0","source":{"id":"2505.23678","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23678","created_at":"2026-05-20T00:01:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23678v3","created_at":"2026-05-20T00:01:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23678","created_at":"2026-05-20T00:01:34Z"},{"alias_kind":"pith_short_12","alias_value":"4RMMTDPLP2HU","created_at":"2026-05-20T00:01:34Z"},{"alias_kind":"pith_short_16","alias_value":"4RMMTDPLP2HUXUKB","created_at":"2026-05-20T00:01:34Z"},{"alias_kind":"pith_short_8","alias_value":"4RMMTDPL","created_at":"2026-05-20T00:01:34Z"}],"graph_snapshots":[{"event_id":"sha256:7e6947bff5ca618045add2a61be93026119c0de848f6822fcdea53ae9e3ffeff","target":"graph","created_at":"2026-05-20T00:01:34Z","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/2505.23678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While reinforcement learning (RL) over chains of thought has significantly advanced language models in tasks such as mathematics and coding, visual reasoning introduces added complexity by requiring models to direct visual attention, interpret perceptual inputs, and ground abstract reasoning in spatial evidence. We introduce ViGoRL (Visually Grounded Reinforcement Learning), a vision-language model trained with RL to explicitly anchor each reasoning step to specific visual coordinates. Inspired by human visual decision-making, ViGoRL learns to produce spatially grounded reasoning traces, guidi","authors_text":"Aviral Kumar, Ayush Jain, Gabriel Sarch, Katerina Fragkiadaki, Michael J. Tarr, Naitik Khandelwal, Snigdha Saha","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:20:26Z","title":"Grounded Reinforcement Learning for Visual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23678","kind":"arxiv","version":3},"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":"sha256:97862ee9557358386e2ce63105bf0f8f5edab728769852209dd9765df1cea4df","target":"record","created_at":"2026-05-20T00:01:34Z","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":"42e722d90a276cd68567a1bbef03a739c5d5cc0c04158056d5b4d03e9758c90a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:20:26Z","title_canon_sha256":"2325a750a619f2bf4918b0015036d01ea081a11617f88218dd52a918c36ecfb5"},"schema_version":"1.0","source":{"id":"2505.23678","kind":"arxiv","version":3}},"canonical_sha256":"e458c98deb7e8f4bd14106b5b10780667ed8f2e9f5b9668fa1f0368fec62d164","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e458c98deb7e8f4bd14106b5b10780667ed8f2e9f5b9668fa1f0368fec62d164","first_computed_at":"2026-05-20T00:01:34.061098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:34.061098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BrU4PjXRPN8vgyJNwWkVkq7cTc63phwjcFd99EmMslGqs4xXLnUsnCxPqYGgivwz9Pjh40QpU76RLwixUs6/AQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:34.061935Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23678","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97862ee9557358386e2ce63105bf0f8f5edab728769852209dd9765df1cea4df","sha256:7e6947bff5ca618045add2a61be93026119c0de848f6822fcdea53ae9e3ffeff"],"state_sha256":"62a20e15906163187cc1bd4a2e4bd26ee88901dff4c47159242fee781809f5bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"loGsuThjiXRH6kQa9IZvgt/pdWa9caYgQAtlpz0qmyb13WqEl2an8D/QhKDBzPGCV/T1OTLokyFHqpOBb5c1DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T06:55:52.703652Z","bundle_sha256":"beb26fc1d1312ccf49f8d43c58a6289df758ca6beb8fd8293aebd0e91ab82757"}}