{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HUAP2UUMIRQXOO6AJGYT7RFR53","short_pith_number":"pith:HUAP2UUM","canonical_record":{"source":{"id":"2502.15760","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T18:55:14Z","cross_cats_sorted":[],"title_canon_sha256":"c376dc4025f95e9f13942dfeb4c8efd876f49466b097394ef2276603e753417a","abstract_canon_sha256":"2aa2c87f78b594d1bd49530be337c91c756e0faf0520446cf414357c1ee01ff0"},"schema_version":"1.0"},"canonical_sha256":"3d00fd528c4461773bc049b13fc4b1eef610b1924e4ca218d53d430fed97cd6b","source":{"kind":"arxiv","id":"2502.15760","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15760","created_at":"2026-07-05T10:18:16Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15760v1","created_at":"2026-07-05T10:18:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15760","created_at":"2026-07-05T10:18:16Z"},{"alias_kind":"pith_short_12","alias_value":"HUAP2UUMIRQX","created_at":"2026-07-05T10:18:16Z"},{"alias_kind":"pith_short_16","alias_value":"HUAP2UUMIRQXOO6A","created_at":"2026-07-05T10:18:16Z"},{"alias_kind":"pith_short_8","alias_value":"HUAP2UUM","created_at":"2026-07-05T10:18:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HUAP2UUMIRQXOO6AJGYT7RFR53","target":"record","payload":{"canonical_record":{"source":{"id":"2502.15760","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T18:55:14Z","cross_cats_sorted":[],"title_canon_sha256":"c376dc4025f95e9f13942dfeb4c8efd876f49466b097394ef2276603e753417a","abstract_canon_sha256":"2aa2c87f78b594d1bd49530be337c91c756e0faf0520446cf414357c1ee01ff0"},"schema_version":"1.0"},"canonical_sha256":"3d00fd528c4461773bc049b13fc4b1eef610b1924e4ca218d53d430fed97cd6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:16.039754Z","signature_b64":"fxpHdy804bF8EppkOA0DoS/hub84sZyKQIDjFcTUN7/qQhgpUjyx5xjHNP4HJoXKNZJiaqwx1PcoS2XYF7G5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d00fd528c4461773bc049b13fc4b1eef610b1924e4ca218d53d430fed97cd6b","last_reissued_at":"2026-07-05T10:18:16.039371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:16.039371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.15760","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DLekYVO13d+qvOmP7tuJUky53uE4kOtGuRjzu1PsYcz4KCX+PugfLyIZT/KniCxk6CFCPy/kpXEfdsBW2/jSCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:16:28.797153Z"},"content_sha256":"a1113c53d91f02bc2c025bfd7798d91e5e641f3d10f446efdbce8ba638d43b4a","schema_version":"1.0","event_id":"sha256:a1113c53d91f02bc2c025bfd7798d91e5e641f3d10f446efdbce8ba638d43b4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HUAP2UUMIRQXOO6AJGYT7RFR53","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Digi-Q: Learning Q-Value Functions for Training Device-Control Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aviral Kumar, Hao Bai, Li Erran Li, Sergey Levine, Yifei Zhou","submitted_at":"2025-02-13T18:55:14Z","abstract_excerpt":"While a number of existing approaches for building foundation model agents rely on prompting or fine-tuning with human demonstrations, it is not sufficient in dynamic environments (e.g., mobile device control). On-policy reinforcement learning (RL) should address these limitations, but collecting actual rollouts in an environment is often undesirable in truly open-ended agentic problems such as mobile device control or interacting with humans, where each unit of interaction is associated with a cost. In such scenarios, a method for policy learning that can utilize off-policy experience by lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15760","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/2502.15760/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":"2026-07-05T10:18:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v+5gptXQxGX3BYO+9mEzOrlErw/jLYmQPG1D3TDPAFoKWSOLkUQ4CmSOC626jcUfmA8khjTypMLg01RnAKEHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:16:28.797657Z"},"content_sha256":"0ac27ff21029b6bfbe7fbc4719d33f5d45686b36548ad070a636c7258b142be2","schema_version":"1.0","event_id":"sha256:0ac27ff21029b6bfbe7fbc4719d33f5d45686b36548ad070a636c7258b142be2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HUAP2UUMIRQXOO6AJGYT7RFR53/bundle.json","state_url":"https://pith.science/pith/HUAP2UUMIRQXOO6AJGYT7RFR53/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HUAP2UUMIRQXOO6AJGYT7RFR53/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":"2026-08-04T10:16:28Z","links":{"resolver":"https://pith.science/pith/HUAP2UUMIRQXOO6AJGYT7RFR53","bundle":"https://pith.science/pith/HUAP2UUMIRQXOO6AJGYT7RFR53/bundle.json","state":"https://pith.science/pith/HUAP2UUMIRQXOO6AJGYT7RFR53/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HUAP2UUMIRQXOO6AJGYT7RFR53/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HUAP2UUMIRQXOO6AJGYT7RFR53","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":"2aa2c87f78b594d1bd49530be337c91c756e0faf0520446cf414357c1ee01ff0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T18:55:14Z","title_canon_sha256":"c376dc4025f95e9f13942dfeb4c8efd876f49466b097394ef2276603e753417a"},"schema_version":"1.0","source":{"id":"2502.15760","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15760","created_at":"2026-07-05T10:18:16Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15760v1","created_at":"2026-07-05T10:18:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15760","created_at":"2026-07-05T10:18:16Z"},{"alias_kind":"pith_short_12","alias_value":"HUAP2UUMIRQX","created_at":"2026-07-05T10:18:16Z"},{"alias_kind":"pith_short_16","alias_value":"HUAP2UUMIRQXOO6A","created_at":"2026-07-05T10:18:16Z"},{"alias_kind":"pith_short_8","alias_value":"HUAP2UUM","created_at":"2026-07-05T10:18:16Z"}],"graph_snapshots":[{"event_id":"sha256:0ac27ff21029b6bfbe7fbc4719d33f5d45686b36548ad070a636c7258b142be2","target":"graph","created_at":"2026-07-05T10:18:16Z","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/2502.15760/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While a number of existing approaches for building foundation model agents rely on prompting or fine-tuning with human demonstrations, it is not sufficient in dynamic environments (e.g., mobile device control). On-policy reinforcement learning (RL) should address these limitations, but collecting actual rollouts in an environment is often undesirable in truly open-ended agentic problems such as mobile device control or interacting with humans, where each unit of interaction is associated with a cost. In such scenarios, a method for policy learning that can utilize off-policy experience by lear","authors_text":"Aviral Kumar, Hao Bai, Li Erran Li, Sergey Levine, Yifei Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T18:55:14Z","title":"Digi-Q: Learning Q-Value Functions for Training Device-Control Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15760","kind":"arxiv","version":1},"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:a1113c53d91f02bc2c025bfd7798d91e5e641f3d10f446efdbce8ba638d43b4a","target":"record","created_at":"2026-07-05T10:18:16Z","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":"2aa2c87f78b594d1bd49530be337c91c756e0faf0520446cf414357c1ee01ff0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T18:55:14Z","title_canon_sha256":"c376dc4025f95e9f13942dfeb4c8efd876f49466b097394ef2276603e753417a"},"schema_version":"1.0","source":{"id":"2502.15760","kind":"arxiv","version":1}},"canonical_sha256":"3d00fd528c4461773bc049b13fc4b1eef610b1924e4ca218d53d430fed97cd6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d00fd528c4461773bc049b13fc4b1eef610b1924e4ca218d53d430fed97cd6b","first_computed_at":"2026-07-05T10:18:16.039371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:16.039371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fxpHdy804bF8EppkOA0DoS/hub84sZyKQIDjFcTUN7/qQhgpUjyx5xjHNP4HJoXKNZJiaqwx1PcoS2XYF7G5Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:16.039754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.15760","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1113c53d91f02bc2c025bfd7798d91e5e641f3d10f446efdbce8ba638d43b4a","sha256:0ac27ff21029b6bfbe7fbc4719d33f5d45686b36548ad070a636c7258b142be2"],"state_sha256":"b577f17faa4ebe7d5c85491f3b1834026a171e96a41086d0c7ddc654a2ee66d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"onhX0jffUBnLzaA4EG6vobcrFLLYMjx0mlRexVvM+hH9+pAHhHK0hjyAs4rvZZSwEiXHbW3lw4TkHM0qtFh0AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:16:28.802073Z","bundle_sha256":"247d131a34863aa6a9f0e0af5c16656a131b17f9a1765c6bc2d58eece118d015"}}