{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:E264CY2MSQF4FZ7Q5HM4BUTW27","short_pith_number":"pith:E264CY2M","canonical_record":{"source":{"id":"2604.20328","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-22T08:22:23Z","cross_cats_sorted":[],"title_canon_sha256":"babc85231be9f3153e21fc0b7cd79da2bed899ffcbe63d3c8306193a988ca7ff","abstract_canon_sha256":"052aeb79afc3f64f03ca841590c441f74a38bde32704bb9880dd7ea95b2e35b4"},"schema_version":"1.0"},"canonical_sha256":"26bdc1634c940bc2e7f0e9d9c0d276d7e521aced7b4b7990269fc89d627a8187","source":{"kind":"arxiv","id":"2604.20328","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.20328","created_at":"2026-06-29T01:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2604.20328v2","created_at":"2026-06-29T01:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.20328","created_at":"2026-06-29T01:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"E264CY2MSQF4","created_at":"2026-06-29T01:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"E264CY2MSQF4FZ7Q","created_at":"2026-06-29T01:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"E264CY2M","created_at":"2026-06-29T01:14:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:E264CY2MSQF4FZ7Q5HM4BUTW27","target":"record","payload":{"canonical_record":{"source":{"id":"2604.20328","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-22T08:22:23Z","cross_cats_sorted":[],"title_canon_sha256":"babc85231be9f3153e21fc0b7cd79da2bed899ffcbe63d3c8306193a988ca7ff","abstract_canon_sha256":"052aeb79afc3f64f03ca841590c441f74a38bde32704bb9880dd7ea95b2e35b4"},"schema_version":"1.0"},"canonical_sha256":"26bdc1634c940bc2e7f0e9d9c0d276d7e521aced7b4b7990269fc89d627a8187","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:31.379659Z","signature_b64":"uMl+viJeAwzOg/0Tt2lbD5SQOHl6zlNJUYcQc7YIEghJxySCkU6S/KyF7+huF1REq+dQF4lm54+Kjcth5Et1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26bdc1634c940bc2e7f0e9d9c0d276d7e521aced7b4b7990269fc89d627a8187","last_reissued_at":"2026-06-29T01:14:31.379176Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:31.379176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.20328","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-29T01:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FWJ7U2i0yuldsbjTNmKpex5PIRVJtKQ2lQqFAWB7NZRHA6+0fZ9DN16wdlAVQo6pGM1QC4N3dLVY3CIj+WBWBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T17:25:58.961005Z"},"content_sha256":"427c46be5c3c98202e64f7ad9661eed47c3712e0b5b92fe638de25def7724c48","schema_version":"1.0","event_id":"sha256:427c46be5c3c98202e64f7ad9661eed47c3712e0b5b92fe638de25def7724c48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:E264CY2MSQF4FZ7Q5HM4BUTW27","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Hybrid latent reasoning interleaves discrete text generation with continuous visual states and optimizes the combination through decoupled policy learning.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zhang, Jinwen Luo, Shi-Zhe Chen, Tao Cheng, Yixin Qin, Zheng Wei","submitted_at":"2026-04-22T08:22:23Z","abstract_excerpt":"Chain-of-Thought (CoT) reasoning significantly elevates the complex problem-solving capabilities of multimodal large language models (MLLMs). However, adapting CoT to vision typically discretizes signals to fit LLM inputs, causing early semantic collapse and discarding fine-grained details. While external tools can mitigate this, they introduce a rigid bottleneck, confining reasoning to predefined operations. Although recent latent reasoning paradigms internalize visual states to overcome these limitations, optimizing the resulting hybrid discrete-continuous action space remains challenging. I"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"HyLaR outperforms standard MLLMs and state-of-the-art latent reasoning approaches across fine-grained perception and general multimodal understanding benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The hybrid discrete-continuous action space can be effectively optimized via DePO with independent trust-region constraints and exact closed-form vMF KL regularizer without introducing instabilities or requiring extensive tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"HyLaR with DePO enables effective RL in hybrid discrete-continuous spaces for multimodal models, outperforming prior MLLMs on perception and understanding benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Hybrid latent reasoning interleaves discrete text generation with continuous visual states and optimizes the combination through decoupled policy learning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7937486afadb009a9b8b6a15e42628e18f8badd3b1015be6769c4df06f16bacf"},"source":{"id":"2604.20328","kind":"arxiv","version":2},"verdict":{"id":"feef6044-d18c-4823-b458-e36c7fff8f9a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T01:14:42.494900Z","strongest_claim":"HyLaR outperforms standard MLLMs and state-of-the-art latent reasoning approaches across fine-grained perception and general multimodal understanding benchmarks.","one_line_summary":"HyLaR with DePO enables effective RL in hybrid discrete-continuous spaces for multimodal models, outperforming prior MLLMs on perception and understanding benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The hybrid discrete-continuous action space can be effectively optimized via DePO with independent trust-region constraints and exact closed-form vMF KL regularizer without introducing instabilities or requiring extensive tuning.","pith_extraction_headline":"Hybrid latent reasoning interleaves discrete text generation with continuous visual states and optimizes the combination through decoupled policy learning."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.20328/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T14:43:16.450368Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T02:01:52.429681Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ef30cdec3e955be5ea350d70b217a387a2e5dc6afad95f658985cdb89f63033c"},"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":"feef6044-d18c-4823-b458-e36c7fff8f9a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-29T01:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IQnTvohqHrYtr2p65UTD82Mh0VeN25/0Jcpb1zkRCmISUhCRM2w51McgWyYy8QyAVNVNnEe6VLkoGv4wTqYODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T17:25:58.961508Z"},"content_sha256":"782a97c07143e59d003cb15a117f8595bbeba5c0fdf7f5e468cf3d87ed366c34","schema_version":"1.0","event_id":"sha256:782a97c07143e59d003cb15a117f8595bbeba5c0fdf7f5e468cf3d87ed366c34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E264CY2MSQF4FZ7Q5HM4BUTW27/bundle.json","state_url":"https://pith.science/pith/E264CY2MSQF4FZ7Q5HM4BUTW27/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E264CY2MSQF4FZ7Q5HM4BUTW27/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":"2026-08-01T17:25:58Z","links":{"resolver":"https://pith.science/pith/E264CY2MSQF4FZ7Q5HM4BUTW27","bundle":"https://pith.science/pith/E264CY2MSQF4FZ7Q5HM4BUTW27/bundle.json","state":"https://pith.science/pith/E264CY2MSQF4FZ7Q5HM4BUTW27/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E264CY2MSQF4FZ7Q5HM4BUTW27/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:E264CY2MSQF4FZ7Q5HM4BUTW27","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":"052aeb79afc3f64f03ca841590c441f74a38bde32704bb9880dd7ea95b2e35b4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-22T08:22:23Z","title_canon_sha256":"babc85231be9f3153e21fc0b7cd79da2bed899ffcbe63d3c8306193a988ca7ff"},"schema_version":"1.0","source":{"id":"2604.20328","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.20328","created_at":"2026-06-29T01:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2604.20328v2","created_at":"2026-06-29T01:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.20328","created_at":"2026-06-29T01:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"E264CY2MSQF4","created_at":"2026-06-29T01:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"E264CY2MSQF4FZ7Q","created_at":"2026-06-29T01:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"E264CY2M","created_at":"2026-06-29T01:14:31Z"}],"graph_snapshots":[{"event_id":"sha256:782a97c07143e59d003cb15a117f8595bbeba5c0fdf7f5e468cf3d87ed366c34","target":"graph","created_at":"2026-06-29T01:14:31Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"HyLaR outperforms standard MLLMs and state-of-the-art latent reasoning approaches across fine-grained perception and general multimodal understanding benchmarks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The hybrid discrete-continuous action space can be effectively optimized via DePO with independent trust-region constraints and exact closed-form vMF KL regularizer without introducing instabilities or requiring extensive tuning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"HyLaR with DePO enables effective RL in hybrid discrete-continuous spaces for multimodal models, outperforming prior MLLMs on perception and understanding benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Hybrid latent reasoning interleaves discrete text generation with continuous visual states and optimizes the combination through decoupled policy learning."}],"snapshot_sha256":"7937486afadb009a9b8b6a15e42628e18f8badd3b1015be6769c4df06f16bacf"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-21T14:43:16.450368Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-20T02:01:52.429681Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.20328/integrity.json","findings":[],"snapshot_sha256":"ef30cdec3e955be5ea350d70b217a387a2e5dc6afad95f658985cdb89f63033c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chain-of-Thought (CoT) reasoning significantly elevates the complex problem-solving capabilities of multimodal large language models (MLLMs). However, adapting CoT to vision typically discretizes signals to fit LLM inputs, causing early semantic collapse and discarding fine-grained details. While external tools can mitigate this, they introduce a rigid bottleneck, confining reasoning to predefined operations. Although recent latent reasoning paradigms internalize visual states to overcome these limitations, optimizing the resulting hybrid discrete-continuous action space remains challenging. I","authors_text":"Hao Zhang, Jinwen Luo, Shi-Zhe Chen, Tao Cheng, Yixin Qin, Zheng Wei","cross_cats":[],"headline":"Hybrid latent reasoning interleaves discrete text generation with continuous visual states and optimizes the combination through decoupled policy learning.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-22T08:22:23Z","title":"HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.20328","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T01:14:42.494900Z","id":"feef6044-d18c-4823-b458-e36c7fff8f9a","model_set":{"reader":"grok-4.3"},"one_line_summary":"HyLaR with DePO enables effective RL in hybrid discrete-continuous spaces for multimodal models, outperforming prior MLLMs on perception and understanding benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Hybrid latent reasoning interleaves discrete text generation with continuous visual states and optimizes the combination through decoupled policy learning.","strongest_claim":"HyLaR outperforms standard MLLMs and state-of-the-art latent reasoning approaches across fine-grained perception and general multimodal understanding benchmarks.","weakest_assumption":"The hybrid discrete-continuous action space can be effectively optimized via DePO with independent trust-region constraints and exact closed-form vMF KL regularizer without introducing instabilities or requiring extensive tuning."}},"verdict_id":"feef6044-d18c-4823-b458-e36c7fff8f9a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:427c46be5c3c98202e64f7ad9661eed47c3712e0b5b92fe638de25def7724c48","target":"record","created_at":"2026-06-29T01:14:31Z","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":"052aeb79afc3f64f03ca841590c441f74a38bde32704bb9880dd7ea95b2e35b4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-22T08:22:23Z","title_canon_sha256":"babc85231be9f3153e21fc0b7cd79da2bed899ffcbe63d3c8306193a988ca7ff"},"schema_version":"1.0","source":{"id":"2604.20328","kind":"arxiv","version":2}},"canonical_sha256":"26bdc1634c940bc2e7f0e9d9c0d276d7e521aced7b4b7990269fc89d627a8187","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26bdc1634c940bc2e7f0e9d9c0d276d7e521aced7b4b7990269fc89d627a8187","first_computed_at":"2026-06-29T01:14:31.379176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:14:31.379176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uMl+viJeAwzOg/0Tt2lbD5SQOHl6zlNJUYcQc7YIEghJxySCkU6S/KyF7+huF1REq+dQF4lm54+Kjcth5Et1Ag==","signature_status":"signed_v1","signed_at":"2026-06-29T01:14:31.379659Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.20328","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:427c46be5c3c98202e64f7ad9661eed47c3712e0b5b92fe638de25def7724c48","sha256:782a97c07143e59d003cb15a117f8595bbeba5c0fdf7f5e468cf3d87ed366c34"],"state_sha256":"87a10834249b99d08e66a9c1634f97866b5b65148fd5922e32de14e78852c720"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4JA+UGTJoQXcNFaf9iyvwx/gFOacRkjekGNLW1cpkTenKSMscbSbRGu7MOSd8/nhdf4IMxVeLaxHP1d+Gn3fAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T17:25:58.984891Z","bundle_sha256":"82c13dd57fa0053d4c39e877ba48acd193f95a05dda8ed7ea8eff4d327c4e15a"}}