{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B6SUJ6GU77PEYBYAM6X2M7VNEY","short_pith_number":"pith:B6SUJ6GU","schema_version":"1.0","canonical_sha256":"0fa544f8d4ffde4c070067afa67ead26379dec1648395b1fe2ca58502959fc16","source":{"kind":"arxiv","id":"2507.16473","version":2},"attestation_state":"computed","paper":{"title":"Learning Temporal Abstractions via Variational Homomorphisms in Option-Induced Abstract MDPs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chang Li, Chao Xue, Haoran Lv, Qiong Cao, Xiaodong He, Yaren Zhang","submitted_at":"2025-07-22T11:22:58Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable reasoning ability through explicit Chain-of-Thought (CoT) prompting, but generating these step-by-step textual explanations is computationally expensive and slow. To overcome this, we aim to develop a framework for efficient, implicit reasoning, where the model \"thinks\" in a latent space without generating explicit text for every step. We propose that these latent thoughts can be modeled as temporally-extended abstract actions, or options, within a hierarchical reinforcement learning framework. To effectively learn a diverse library of options"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.16473","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-22T11:22:58Z","cross_cats_sorted":[],"title_canon_sha256":"10c017f7b57f4db48d7913c8d76d56c3a0bde67e5d9df4916fb7a7a1f26e31e8","abstract_canon_sha256":"50687b479b2b118d74d320ee69de6d1cb3fa7893f8750cab72a02644ef4f8b59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:33.627336Z","signature_b64":"bCoGauVTVT2fwEyVzG27gPF/nP2n1+AZqGWxtNc55sBq9Zvv1+fMpB21P5EBtdl01kYeZSgbCQWNHcjk4DaIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fa544f8d4ffde4c070067afa67ead26379dec1648395b1fe2ca58502959fc16","last_reissued_at":"2026-07-05T11:42:33.626779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:33.626779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Temporal Abstractions via Variational Homomorphisms in Option-Induced Abstract MDPs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chang Li, Chao Xue, Haoran Lv, Qiong Cao, Xiaodong He, Yaren Zhang","submitted_at":"2025-07-22T11:22:58Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable reasoning ability through explicit Chain-of-Thought (CoT) prompting, but generating these step-by-step textual explanations is computationally expensive and slow. To overcome this, we aim to develop a framework for efficient, implicit reasoning, where the model \"thinks\" in a latent space without generating explicit text for every step. We propose that these latent thoughts can be modeled as temporally-extended abstract actions, or options, within a hierarchical reinforcement learning framework. To effectively learn a diverse library of options"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16473","kind":"arxiv","version":2},"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/2507.16473/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.16473","created_at":"2026-07-05T11:42:33.626833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16473v2","created_at":"2026-07-05T11:42:33.626833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16473","created_at":"2026-07-05T11:42:33.626833+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6SUJ6GU77PE","created_at":"2026-07-05T11:42:33.626833+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6SUJ6GU77PEYBYA","created_at":"2026-07-05T11:42:33.626833+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6SUJ6GU","created_at":"2026-07-05T11:42:33.626833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B6SUJ6GU77PEYBYAM6X2M7VNEY","json":"https://pith.science/pith/B6SUJ6GU77PEYBYAM6X2M7VNEY.json","graph_json":"https://pith.science/api/pith-number/B6SUJ6GU77PEYBYAM6X2M7VNEY/graph.json","events_json":"https://pith.science/api/pith-number/B6SUJ6GU77PEYBYAM6X2M7VNEY/events.json","paper":"https://pith.science/paper/B6SUJ6GU"},"agent_actions":{"view_html":"https://pith.science/pith/B6SUJ6GU77PEYBYAM6X2M7VNEY","download_json":"https://pith.science/pith/B6SUJ6GU77PEYBYAM6X2M7VNEY.json","view_paper":"https://pith.science/paper/B6SUJ6GU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16473&json=true","fetch_graph":"https://pith.science/api/pith-number/B6SUJ6GU77PEYBYAM6X2M7VNEY/graph.json","fetch_events":"https://pith.science/api/pith-number/B6SUJ6GU77PEYBYAM6X2M7VNEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6SUJ6GU77PEYBYAM6X2M7VNEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6SUJ6GU77PEYBYAM6X2M7VNEY/action/storage_attestation","attest_author":"https://pith.science/pith/B6SUJ6GU77PEYBYAM6X2M7VNEY/action/author_attestation","sign_citation":"https://pith.science/pith/B6SUJ6GU77PEYBYAM6X2M7VNEY/action/citation_signature","submit_replication":"https://pith.science/pith/B6SUJ6GU77PEYBYAM6X2M7VNEY/action/replication_record"}},"created_at":"2026-07-05T11:42:33.626833+00:00","updated_at":"2026-07-05T11:42:33.626833+00:00"}