{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:32CQSAMGOXNBGNBHN6MZ76WBAI","short_pith_number":"pith:32CQSAMG","schema_version":"1.0","canonical_sha256":"de8509018675da1334276f999ffac1022c1d22af4b9b847ac338f86bb9c9d4a9","source":{"kind":"arxiv","id":"2504.00461","version":1},"attestation_state":"computed","paper":{"title":"Efficient Near-Optimal Algorithm for Online Shortest Paths in Directed Acyclic Graphs with Bandit Feedback Against Adaptive Adversaries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Arnab Maiti, Gabriele Farina, Kevin Jamieson, Lillian J. Ratliff, Zhiyuan Fan","submitted_at":"2025-04-01T06:35:42Z","abstract_excerpt":"In this paper, we study the online shortest path problem in directed acyclic graphs (DAGs) under bandit feedback against an adaptive adversary. Given a DAG $G = (V, E)$ with a source node $v_{\\mathsf{s}}$ and a sink node $v_{\\mathsf{t}}$, let $X \\subseteq \\{0,1\\}^{|E|}$ denote the set of all paths from $v_{\\mathsf{s}}$ to $v_{\\mathsf{t}}$. At each round $t$, we select a path $\\mathbf{x}_t \\in X$ and receive bandit feedback on our loss $\\langle \\mathbf{x}_t, \\mathbf{y}_t \\rangle \\in [-1,1]$, where $\\mathbf{y}_t$ is an adversarially chosen loss vector. Our goal is to minimize regret with respect"},"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":"2504.00461","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-01T06:35:42Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"b8915a8233b01b6c48d8e76a9b64185d2d1fcba52a3cc0347f58e3cb48509a0d","abstract_canon_sha256":"42e063e263ba84e96709cd50cf98c430210612dcece6ff045c94ad64422830e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:47.268241Z","signature_b64":"kSSLTqQp3LPJQjCftmUe0nMlfR79lVpzlDrKqnmUholOaPUS+QvP1EiHEhFiSkLuDAhkHZ7kv3iTY9TXfkd8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de8509018675da1334276f999ffac1022c1d22af4b9b847ac338f86bb9c9d4a9","last_reissued_at":"2026-07-05T10:43:47.267697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:47.267697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Near-Optimal Algorithm for Online Shortest Paths in Directed Acyclic Graphs with Bandit Feedback Against Adaptive Adversaries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Arnab Maiti, Gabriele Farina, Kevin Jamieson, Lillian J. Ratliff, Zhiyuan Fan","submitted_at":"2025-04-01T06:35:42Z","abstract_excerpt":"In this paper, we study the online shortest path problem in directed acyclic graphs (DAGs) under bandit feedback against an adaptive adversary. Given a DAG $G = (V, E)$ with a source node $v_{\\mathsf{s}}$ and a sink node $v_{\\mathsf{t}}$, let $X \\subseteq \\{0,1\\}^{|E|}$ denote the set of all paths from $v_{\\mathsf{s}}$ to $v_{\\mathsf{t}}$. At each round $t$, we select a path $\\mathbf{x}_t \\in X$ and receive bandit feedback on our loss $\\langle \\mathbf{x}_t, \\mathbf{y}_t \\rangle \\in [-1,1]$, where $\\mathbf{y}_t$ is an adversarially chosen loss vector. Our goal is to minimize regret with respect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00461","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/2504.00461/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":"2504.00461","created_at":"2026-07-05T10:43:47.267760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.00461v1","created_at":"2026-07-05T10:43:47.267760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00461","created_at":"2026-07-05T10:43:47.267760+00:00"},{"alias_kind":"pith_short_12","alias_value":"32CQSAMGOXNB","created_at":"2026-07-05T10:43:47.267760+00:00"},{"alias_kind":"pith_short_16","alias_value":"32CQSAMGOXNBGNBH","created_at":"2026-07-05T10:43:47.267760+00:00"},{"alias_kind":"pith_short_8","alias_value":"32CQSAMG","created_at":"2026-07-05T10:43:47.267760+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15663","citing_title":"On the Power of Adaptivity for $\\varepsilon$-Best Arm Identification in Linear Bandits","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05266","citing_title":"Differential Privacy in the Extensive-Form Bandit Problem","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/32CQSAMGOXNBGNBHN6MZ76WBAI","json":"https://pith.science/pith/32CQSAMGOXNBGNBHN6MZ76WBAI.json","graph_json":"https://pith.science/api/pith-number/32CQSAMGOXNBGNBHN6MZ76WBAI/graph.json","events_json":"https://pith.science/api/pith-number/32CQSAMGOXNBGNBHN6MZ76WBAI/events.json","paper":"https://pith.science/paper/32CQSAMG"},"agent_actions":{"view_html":"https://pith.science/pith/32CQSAMGOXNBGNBHN6MZ76WBAI","download_json":"https://pith.science/pith/32CQSAMGOXNBGNBHN6MZ76WBAI.json","view_paper":"https://pith.science/paper/32CQSAMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.00461&json=true","fetch_graph":"https://pith.science/api/pith-number/32CQSAMGOXNBGNBHN6MZ76WBAI/graph.json","fetch_events":"https://pith.science/api/pith-number/32CQSAMGOXNBGNBHN6MZ76WBAI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32CQSAMGOXNBGNBHN6MZ76WBAI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32CQSAMGOXNBGNBHN6MZ76WBAI/action/storage_attestation","attest_author":"https://pith.science/pith/32CQSAMGOXNBGNBHN6MZ76WBAI/action/author_attestation","sign_citation":"https://pith.science/pith/32CQSAMGOXNBGNBHN6MZ76WBAI/action/citation_signature","submit_replication":"https://pith.science/pith/32CQSAMGOXNBGNBHN6MZ76WBAI/action/replication_record"}},"created_at":"2026-07-05T10:43:47.267760+00:00","updated_at":"2026-07-05T10:43:47.267760+00:00"}