{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PZIESAFJ3HGBNHWTCX4GCOHYDS","short_pith_number":"pith:PZIESAFJ","canonical_record":{"source":{"id":"2606.10184","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T21:21:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"40135c302b2fc60798aac563170a67453e452b96f530fe4234e194b2b81499e3","abstract_canon_sha256":"d3e5063cb0207fec472abaace1a0d63cb44f1cf8620bf5f26d3f3405ae006f6f"},"schema_version":"1.0"},"canonical_sha256":"7e504900a9d9cc169ed315f86138f81c90329fd671a5b4a6066bd5376a7b044a","source":{"kind":"arxiv","id":"2606.10184","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10184","created_at":"2026-06-10T01:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10184v1","created_at":"2026-06-10T01:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10184","created_at":"2026-06-10T01:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"PZIESAFJ3HGB","created_at":"2026-06-10T01:08:58Z"},{"alias_kind":"pith_short_16","alias_value":"PZIESAFJ3HGBNHWT","created_at":"2026-06-10T01:08:58Z"},{"alias_kind":"pith_short_8","alias_value":"PZIESAFJ","created_at":"2026-06-10T01:08:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PZIESAFJ3HGBNHWTCX4GCOHYDS","target":"record","payload":{"canonical_record":{"source":{"id":"2606.10184","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T21:21:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"40135c302b2fc60798aac563170a67453e452b96f530fe4234e194b2b81499e3","abstract_canon_sha256":"d3e5063cb0207fec472abaace1a0d63cb44f1cf8620bf5f26d3f3405ae006f6f"},"schema_version":"1.0"},"canonical_sha256":"7e504900a9d9cc169ed315f86138f81c90329fd671a5b4a6066bd5376a7b044a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:08:58.526002Z","signature_b64":"54yONFI4MJgweWqqQPYeIHPf4ObOpwcMDN2WVXlyj6eMavBAvUNiE6LRZoEWpOeC3Bu3nl7vo7VS7EOZG573Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e504900a9d9cc169ed315f86138f81c90329fd671a5b4a6066bd5376a7b044a","last_reissued_at":"2026-06-10T01:08:58.525104Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:08:58.525104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.10184","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":"2026-06-10T01:08:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"efygQu/dI1BifXICyw89/6gXtjS+3bOsVD+CgbAu5JeqZkgUTAqFTxi/qE0UjcwarRvjtIeOqCW2ke2vVZvCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T16:01:53.599649Z"},"content_sha256":"b0d78952e8539a21d7d467b07f5cb2f1ca6e6344f6ccfb3d80a73f99d3573e37","schema_version":"1.0","event_id":"sha256:b0d78952e8539a21d7d467b07f5cb2f1ca6e6344f6ccfb3d80a73f99d3573e37"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PZIESAFJ3HGBNHWTCX4GCOHYDS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dropout-GRPO: Variational Stochasticity for Continuous Latent Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Wooil Jung","submitted_at":"2026-06-08T21:21:42Z","abstract_excerpt":"Group Relative Policy Optimization (GRPO) relies on the diversity of $K$ rollouts within each group; otherwise, the group-mean advantage $A^{(k)} = r^{(k)} - \\mu_r$ collapses to zero. This presents a structural challenge for latent-reasoning models like Coconut, which feed continuous hidden states recurrently in place of discrete chain-of-thought tokens. Because the latent phase is inherently deterministic given the parameters and prompt, multiple rollouts produce identical trajectories, stalling GRPO's progress. Consequently, applying group-relative reinforcement learning to continuous latent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10184","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/2606.10184/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":"2026-06-10T01:08:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xttxe/4pLuy1rzWTZs7PJGSzj4nZdkR1aIk29fV52vurUomfJDQSQtv9nxMInV8O97sjyxF2FENnrLFFqrdXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T16:01:53.600021Z"},"content_sha256":"dfc7dac9a6f72697af6f249aa3391c31a7ea399b796c26af1f68ca4fd6867b1d","schema_version":"1.0","event_id":"sha256:dfc7dac9a6f72697af6f249aa3391c31a7ea399b796c26af1f68ca4fd6867b1d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PZIESAFJ3HGBNHWTCX4GCOHYDS/bundle.json","state_url":"https://pith.science/pith/PZIESAFJ3HGBNHWTCX4GCOHYDS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PZIESAFJ3HGBNHWTCX4GCOHYDS/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":"2026-06-29T16:01:53Z","links":{"resolver":"https://pith.science/pith/PZIESAFJ3HGBNHWTCX4GCOHYDS","bundle":"https://pith.science/pith/PZIESAFJ3HGBNHWTCX4GCOHYDS/bundle.json","state":"https://pith.science/pith/PZIESAFJ3HGBNHWTCX4GCOHYDS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PZIESAFJ3HGBNHWTCX4GCOHYDS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PZIESAFJ3HGBNHWTCX4GCOHYDS","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":"d3e5063cb0207fec472abaace1a0d63cb44f1cf8620bf5f26d3f3405ae006f6f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T21:21:42Z","title_canon_sha256":"40135c302b2fc60798aac563170a67453e452b96f530fe4234e194b2b81499e3"},"schema_version":"1.0","source":{"id":"2606.10184","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10184","created_at":"2026-06-10T01:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10184v1","created_at":"2026-06-10T01:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10184","created_at":"2026-06-10T01:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"PZIESAFJ3HGB","created_at":"2026-06-10T01:08:58Z"},{"alias_kind":"pith_short_16","alias_value":"PZIESAFJ3HGBNHWT","created_at":"2026-06-10T01:08:58Z"},{"alias_kind":"pith_short_8","alias_value":"PZIESAFJ","created_at":"2026-06-10T01:08:58Z"}],"graph_snapshots":[{"event_id":"sha256:dfc7dac9a6f72697af6f249aa3391c31a7ea399b796c26af1f68ca4fd6867b1d","target":"graph","created_at":"2026-06-10T01:08:58Z","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/2606.10184/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group Relative Policy Optimization (GRPO) relies on the diversity of $K$ rollouts within each group; otherwise, the group-mean advantage $A^{(k)} = r^{(k)} - \\mu_r$ collapses to zero. This presents a structural challenge for latent-reasoning models like Coconut, which feed continuous hidden states recurrently in place of discrete chain-of-thought tokens. Because the latent phase is inherently deterministic given the parameters and prompt, multiple rollouts produce identical trajectories, stalling GRPO's progress. Consequently, applying group-relative reinforcement learning to continuous latent","authors_text":"Wooil Jung","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T21:21:42Z","title":"Dropout-GRPO: Variational Stochasticity for Continuous Latent Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10184","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:b0d78952e8539a21d7d467b07f5cb2f1ca6e6344f6ccfb3d80a73f99d3573e37","target":"record","created_at":"2026-06-10T01:08:58Z","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":"d3e5063cb0207fec472abaace1a0d63cb44f1cf8620bf5f26d3f3405ae006f6f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T21:21:42Z","title_canon_sha256":"40135c302b2fc60798aac563170a67453e452b96f530fe4234e194b2b81499e3"},"schema_version":"1.0","source":{"id":"2606.10184","kind":"arxiv","version":1}},"canonical_sha256":"7e504900a9d9cc169ed315f86138f81c90329fd671a5b4a6066bd5376a7b044a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e504900a9d9cc169ed315f86138f81c90329fd671a5b4a6066bd5376a7b044a","first_computed_at":"2026-06-10T01:08:58.525104Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:08:58.525104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"54yONFI4MJgweWqqQPYeIHPf4ObOpwcMDN2WVXlyj6eMavBAvUNiE6LRZoEWpOeC3Bu3nl7vo7VS7EOZG573Dg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:08:58.526002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10184","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0d78952e8539a21d7d467b07f5cb2f1ca6e6344f6ccfb3d80a73f99d3573e37","sha256:dfc7dac9a6f72697af6f249aa3391c31a7ea399b796c26af1f68ca4fd6867b1d"],"state_sha256":"ac5f2ee8b0979ca1636da31ad33182f0efaa7e043a11f8ff0495c07a325d7d35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X2ujVtYF0hbvirMznjKFykw0Bd0t8lUQra44YbfkWbhbB4yEHox2U5h6c/rfzoA1vsuPRJA+0g1oBehCwdgjDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T16:01:53.601955Z","bundle_sha256":"cac5797defb4d5b3445de6b972c95422cd6c3d8a80810e8f2bf81b5e6710aa46"}}