{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VS3FT6ZZ2KRY7TWNPVLLWUVKXP","short_pith_number":"pith:VS3FT6ZZ","schema_version":"1.0","canonical_sha256":"acb659fb39d2a38fcecd7d56bb52aabbd5954034aff8d68f28aefd97cfaf27d8","source":{"kind":"arxiv","id":"2605.14323","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Latent Routing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Dynamic Latent Routing recovers globally optimal policies by composing learned sub-policies to improve low-data language model fine-tuning.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Amir Abdullah, Fangyuan Yu, Xin Su","submitted_at":"2026-05-14T03:35:46Z","abstract_excerpt":"We investigate the temporal concatenation of sub-policies in Markov Decision Processes (MDP) with time-varying reward functions. We introduce General Dijkstra Search (GDS), and prove that globally optimal goal-reaching policies can be recovered through temporal composition of intermediate optimal sub-policies. Motivated by the \"search, select, update\" principle underlying GDS, we propose Dynamic Latent Routing (DLR), a language-model post-training method that jointly learns discrete latent codes, routing policies, and model parameters through dynamic search in a single training stage. In low-d"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.14323","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T03:35:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"053ff61afba5cb9c959c212834e1d656d977b42a269996ce53447947c04bb37a","abstract_canon_sha256":"07849c9d1a4bf545b3e2a82e4b983491ba8c311b3d8a1b2b18df2693d350a8f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:09.808923Z","signature_b64":"Cvrvy8m5gKlxyvfdiQAUq/4Awz0PTQAY7tuGNZb094kQ2KaYjQhB3gG/UB6lOcAKC8HWceaTwgxelU7JohDoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acb659fb39d2a38fcecd7d56bb52aabbd5954034aff8d68f28aefd97cfaf27d8","last_reissued_at":"2026-05-17T23:39:09.808381Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:09.808381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Latent Routing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Dynamic Latent Routing recovers globally optimal policies by composing learned sub-policies to improve low-data language model fine-tuning.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Amir Abdullah, Fangyuan Yu, Xin Su","submitted_at":"2026-05-14T03:35:46Z","abstract_excerpt":"We investigate the temporal concatenation of sub-policies in Markov Decision Processes (MDP) with time-varying reward functions. We introduce General Dijkstra Search (GDS), and prove that globally optimal goal-reaching policies can be recovered through temporal composition of intermediate optimal sub-policies. Motivated by the \"search, select, update\" principle underlying GDS, we propose Dynamic Latent Routing (DLR), a language-model post-training method that jointly learns discrete latent codes, routing policies, and model parameters through dynamic search in a single training stage. In low-d"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"In low-data fine-tuning settings, DLR matches or outperforms supervised fine-tuning across four datasets and six models, achieving a mean gain of +6.6 percentage points, while prior discrete-latent baselines consistently underperform SFT.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the optimality guarantees and search principle from General Dijkstra Search in MDPs transfer effectively to the non-stationary, high-dimensional setting of language model post-training without introducing hidden biases or optimization instabilities.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Dynamic Latent Routing jointly learns discrete latent codes, routing policies, and model parameters via dynamic search to match or exceed supervised fine-tuning by 6.6 points on average in low-data settings across four datasets and six models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Dynamic Latent Routing recovers globally optimal policies by composing learned sub-policies to improve low-data language model fine-tuning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f8e4659fe691fbe54d74086337cf1ec7da3a4a2afd57db837e1e2232949e86d2"},"source":{"id":"2605.14323","kind":"arxiv","version":1},"verdict":{"id":"16c71107-db8a-4430-acef-4ad0a8557dd1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:45:27.516595Z","strongest_claim":"In low-data fine-tuning settings, DLR matches or outperforms supervised fine-tuning across four datasets and six models, achieving a mean gain of +6.6 percentage points, while prior discrete-latent baselines consistently underperform SFT.","one_line_summary":"Dynamic Latent Routing jointly learns discrete latent codes, routing policies, and model parameters via dynamic search to match or exceed supervised fine-tuning by 6.6 points on average in low-data settings across four datasets and six models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the optimality guarantees and search principle from General Dijkstra Search in MDPs transfer effectively to the non-stationary, high-dimensional setting of language model post-training without introducing hidden biases or optimization instabilities.","pith_extraction_headline":"Dynamic Latent Routing recovers globally optimal policies by composing learned sub-policies to improve low-data language model fine-tuning."},"references":{"count":70,"sample":[{"doi":"","year":2017,"title":"Hindsight experience replay","work_id":"b4ff437e-eec1-45ab-9ee2-e70f0e4c45a4","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Introducing Claude Opus 4.7","work_id":"93e7fbe6-fe60-46cb-9cca-d936e25cd4c7","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"The option-critic architecture","work_id":"eca5b255-3362-4279-8e47-baa1fa132831","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Successor features for transfer in reinforcement learning","work_id":"0c3776bc-e342-4c21-adda-1ff1b22ce73c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Probing classifiers: Promises, shortcomings, and advances.Computational Linguistics, 48(1):207–219, 2022","work_id":"14d0b945-57f3-41b0-b491-72316d4c06b5","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":70,"snapshot_sha256":"de5cc2c99271703570f8a5c460fae39d8ff7b0ade229e6cc096927452a5384a8","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f1863e9f4efa9195501d90122a4c64020c051095898c9a1e196df5aca7dda042"},"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":"2605.14323","created_at":"2026-05-17T23:39:09.808475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14323v1","created_at":"2026-05-17T23:39:09.808475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14323","created_at":"2026-05-17T23:39:09.808475+00:00"},{"alias_kind":"pith_short_12","alias_value":"VS3FT6ZZ2KRY","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"VS3FT6ZZ2KRY7TWN","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"VS3FT6ZZ","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VS3FT6ZZ2KRY7TWNPVLLWUVKXP","json":"https://pith.science/pith/VS3FT6ZZ2KRY7TWNPVLLWUVKXP.json","graph_json":"https://pith.science/api/pith-number/VS3FT6ZZ2KRY7TWNPVLLWUVKXP/graph.json","events_json":"https://pith.science/api/pith-number/VS3FT6ZZ2KRY7TWNPVLLWUVKXP/events.json","paper":"https://pith.science/paper/VS3FT6ZZ"},"agent_actions":{"view_html":"https://pith.science/pith/VS3FT6ZZ2KRY7TWNPVLLWUVKXP","download_json":"https://pith.science/pith/VS3FT6ZZ2KRY7TWNPVLLWUVKXP.json","view_paper":"https://pith.science/paper/VS3FT6ZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14323&json=true","fetch_graph":"https://pith.science/api/pith-number/VS3FT6ZZ2KRY7TWNPVLLWUVKXP/graph.json","fetch_events":"https://pith.science/api/pith-number/VS3FT6ZZ2KRY7TWNPVLLWUVKXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VS3FT6ZZ2KRY7TWNPVLLWUVKXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VS3FT6ZZ2KRY7TWNPVLLWUVKXP/action/storage_attestation","attest_author":"https://pith.science/pith/VS3FT6ZZ2KRY7TWNPVLLWUVKXP/action/author_attestation","sign_citation":"https://pith.science/pith/VS3FT6ZZ2KRY7TWNPVLLWUVKXP/action/citation_signature","submit_replication":"https://pith.science/pith/VS3FT6ZZ2KRY7TWNPVLLWUVKXP/action/replication_record"}},"created_at":"2026-05-17T23:39:09.808475+00:00","updated_at":"2026-05-17T23:39:09.808475+00:00"}