{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FIANCK5YV3K7W2B5QFTUOE5QJI","short_pith_number":"pith:FIANCK5Y","canonical_record":{"source":{"id":"2110.12727","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-25T08:34:00Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"5712962717f43093ad61d62e112ff05197c133a4207cf97f6377ca68facc6dac","abstract_canon_sha256":"47ca9c1bd7c81921f853f40d23da97e53bdf6081bf78764bb3e0df53a2cdeca6"},"schema_version":"1.0"},"canonical_sha256":"2a00d12bb8aed5fb683d81674713b04a2346d95d91031f7a35ed54f1a10d45c8","source":{"kind":"arxiv","id":"2110.12727","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.12727","created_at":"2026-07-05T04:37:28Z"},{"alias_kind":"arxiv_version","alias_value":"2110.12727v3","created_at":"2026-07-05T04:37:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12727","created_at":"2026-07-05T04:37:28Z"},{"alias_kind":"pith_short_12","alias_value":"FIANCK5YV3K7","created_at":"2026-07-05T04:37:28Z"},{"alias_kind":"pith_short_16","alias_value":"FIANCK5YV3K7W2B5","created_at":"2026-07-05T04:37:28Z"},{"alias_kind":"pith_short_8","alias_value":"FIANCK5Y","created_at":"2026-07-05T04:37:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FIANCK5YV3K7W2B5QFTUOE5QJI","target":"record","payload":{"canonical_record":{"source":{"id":"2110.12727","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-25T08:34:00Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"5712962717f43093ad61d62e112ff05197c133a4207cf97f6377ca68facc6dac","abstract_canon_sha256":"47ca9c1bd7c81921f853f40d23da97e53bdf6081bf78764bb3e0df53a2cdeca6"},"schema_version":"1.0"},"canonical_sha256":"2a00d12bb8aed5fb683d81674713b04a2346d95d91031f7a35ed54f1a10d45c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:37:28.840053Z","signature_b64":"HF1O6SUOzLBC4+tx3b4/csIYRc6DwNsnJQrpDcUQvlVI5GB5vF87Oqy1Ox2YYAV96+ZSiAFTw5LwuE9BRfClCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a00d12bb8aed5fb683d81674713b04a2346d95d91031f7a35ed54f1a10d45c8","last_reissued_at":"2026-07-05T04:37:28.839586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:37:28.839586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.12727","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":"2026-07-05T04:37:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tJY83Vha95ku9i7R3CbEK9ooEn2EBdIYVRxzl9XNETpDoIhmJYp4n4lVe0BN60gQfEc9k08bAG6Ux4LsgliCDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:46:17.034904Z"},"content_sha256":"7cef0235e1ade211cbabf33d27fa0133b72e2b2ef3672599b815674bbd39ccd2","schema_version":"1.0","event_id":"sha256:7cef0235e1ade211cbabf33d27fa0133b72e2b2ef3672599b815674bbd39ccd2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FIANCK5YV3K7W2B5QFTUOE5QJI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Stochastic Shortest Path with Linear Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiafan He, Quanquan Gu, Tianhao Wang, Yifei Min","submitted_at":"2021-10-25T08:34:00Z","abstract_excerpt":"We study the stochastic shortest path (SSP) problem in reinforcement learning with linear function approximation, where the transition kernel is represented as a linear mixture of unknown models. We call this class of SSP problems as linear mixture SSPs. We propose a novel algorithm with Hoeffding-type confidence sets for learning the linear mixture SSP, which can attain an $\\tilde{\\mathcal{O}}(d B_{\\star}^{1.5}\\sqrt{K/c_{\\min}})$ regret. Here $K$ is the number of episodes, $d$ is the dimension of the feature mapping in the mixture model, $B_{\\star}$ bounds the expected cumulative cost of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12727","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/2110.12727/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":"2026-07-05T04:37:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bs/uegE0Qhnu3wCrHc7j7M+89uCr9HJ4/jn5Isy2S/NfGmy4FE6eX7fgcKKnqVLSg5cAMCsDHqf9VH0Sa9SlBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:46:17.035287Z"},"content_sha256":"4dc629764d8aee19217110dc1b8e49571ba7b3cc3bec35db01c8cbe3a8247141","schema_version":"1.0","event_id":"sha256:4dc629764d8aee19217110dc1b8e49571ba7b3cc3bec35db01c8cbe3a8247141"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FIANCK5YV3K7W2B5QFTUOE5QJI/bundle.json","state_url":"https://pith.science/pith/FIANCK5YV3K7W2B5QFTUOE5QJI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FIANCK5YV3K7W2B5QFTUOE5QJI/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":"2026-07-06T08:46:17Z","links":{"resolver":"https://pith.science/pith/FIANCK5YV3K7W2B5QFTUOE5QJI","bundle":"https://pith.science/pith/FIANCK5YV3K7W2B5QFTUOE5QJI/bundle.json","state":"https://pith.science/pith/FIANCK5YV3K7W2B5QFTUOE5QJI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FIANCK5YV3K7W2B5QFTUOE5QJI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FIANCK5YV3K7W2B5QFTUOE5QJI","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":"47ca9c1bd7c81921f853f40d23da97e53bdf6081bf78764bb3e0df53a2cdeca6","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-25T08:34:00Z","title_canon_sha256":"5712962717f43093ad61d62e112ff05197c133a4207cf97f6377ca68facc6dac"},"schema_version":"1.0","source":{"id":"2110.12727","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.12727","created_at":"2026-07-05T04:37:28Z"},{"alias_kind":"arxiv_version","alias_value":"2110.12727v3","created_at":"2026-07-05T04:37:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12727","created_at":"2026-07-05T04:37:28Z"},{"alias_kind":"pith_short_12","alias_value":"FIANCK5YV3K7","created_at":"2026-07-05T04:37:28Z"},{"alias_kind":"pith_short_16","alias_value":"FIANCK5YV3K7W2B5","created_at":"2026-07-05T04:37:28Z"},{"alias_kind":"pith_short_8","alias_value":"FIANCK5Y","created_at":"2026-07-05T04:37:28Z"}],"graph_snapshots":[{"event_id":"sha256:4dc629764d8aee19217110dc1b8e49571ba7b3cc3bec35db01c8cbe3a8247141","target":"graph","created_at":"2026-07-05T04:37:28Z","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/2110.12727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the stochastic shortest path (SSP) problem in reinforcement learning with linear function approximation, where the transition kernel is represented as a linear mixture of unknown models. We call this class of SSP problems as linear mixture SSPs. We propose a novel algorithm with Hoeffding-type confidence sets for learning the linear mixture SSP, which can attain an $\\tilde{\\mathcal{O}}(d B_{\\star}^{1.5}\\sqrt{K/c_{\\min}})$ regret. Here $K$ is the number of episodes, $d$ is the dimension of the feature mapping in the mixture model, $B_{\\star}$ bounds the expected cumulative cost of the ","authors_text":"Jiafan He, Quanquan Gu, Tianhao Wang, Yifei Min","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-25T08:34:00Z","title":"Learning Stochastic Shortest Path with Linear Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12727","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":"sha256:7cef0235e1ade211cbabf33d27fa0133b72e2b2ef3672599b815674bbd39ccd2","target":"record","created_at":"2026-07-05T04:37:28Z","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":"47ca9c1bd7c81921f853f40d23da97e53bdf6081bf78764bb3e0df53a2cdeca6","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-25T08:34:00Z","title_canon_sha256":"5712962717f43093ad61d62e112ff05197c133a4207cf97f6377ca68facc6dac"},"schema_version":"1.0","source":{"id":"2110.12727","kind":"arxiv","version":3}},"canonical_sha256":"2a00d12bb8aed5fb683d81674713b04a2346d95d91031f7a35ed54f1a10d45c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a00d12bb8aed5fb683d81674713b04a2346d95d91031f7a35ed54f1a10d45c8","first_computed_at":"2026-07-05T04:37:28.839586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:37:28.839586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HF1O6SUOzLBC4+tx3b4/csIYRc6DwNsnJQrpDcUQvlVI5GB5vF87Oqy1Ox2YYAV96+ZSiAFTw5LwuE9BRfClCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:37:28.840053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.12727","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cef0235e1ade211cbabf33d27fa0133b72e2b2ef3672599b815674bbd39ccd2","sha256:4dc629764d8aee19217110dc1b8e49571ba7b3cc3bec35db01c8cbe3a8247141"],"state_sha256":"33d949e080287c1c48b922be108dd2afb0106e8214aa0cb29b0e7238fc3241fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5zIH8Xkvqv85OP3uLfzk2hTIa4gU3GPAuLk6FQN4tr2q2xFez+a3FPXa970ovBdrEdMw5P7kB7Lz6PYmhgMCCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:46:17.037656Z","bundle_sha256":"d44874c3834163a72805702402e885a69b33c15790164cf9fab830f5aca7dab5"}}