{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3JTHBD5MWDQX63MQQB6GUO4YWG","short_pith_number":"pith:3JTHBD5M","canonical_record":{"source":{"id":"2511.19399","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-24T18:35:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"acdc7b9f2d45d37d915aa709727a76f50f9087709f7d9234bfc673a2199656f3","abstract_canon_sha256":"384da7e97856ad823a25490fef04c67517a3a39561b0b426e0dc20eda726fc33"},"schema_version":"1.0"},"canonical_sha256":"da66708facb0e17f6d90807c6a3b98b1acb468abc08f99bb8ee5a521cf4281db","source":{"kind":"arxiv","id":"2511.19399","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.19399","created_at":"2026-05-20T00:00:28Z"},{"alias_kind":"arxiv_version","alias_value":"2511.19399v3","created_at":"2026-05-20T00:00:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.19399","created_at":"2026-05-20T00:00:28Z"},{"alias_kind":"pith_short_12","alias_value":"3JTHBD5MWDQX","created_at":"2026-05-20T00:00:28Z"},{"alias_kind":"pith_short_16","alias_value":"3JTHBD5MWDQX63MQ","created_at":"2026-05-20T00:00:28Z"},{"alias_kind":"pith_short_8","alias_value":"3JTHBD5M","created_at":"2026-05-20T00:00:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3JTHBD5MWDQX63MQQB6GUO4YWG","target":"record","payload":{"canonical_record":{"source":{"id":"2511.19399","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-24T18:35:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"acdc7b9f2d45d37d915aa709727a76f50f9087709f7d9234bfc673a2199656f3","abstract_canon_sha256":"384da7e97856ad823a25490fef04c67517a3a39561b0b426e0dc20eda726fc33"},"schema_version":"1.0"},"canonical_sha256":"da66708facb0e17f6d90807c6a3b98b1acb468abc08f99bb8ee5a521cf4281db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:28.703113Z","signature_b64":"rgueS+mEENnMLv5kQkpUXanXEQRPrN50hKzZrbUm6nAik+RT3kPVSayVrDL1Iz9Qs9Ha8Qb4M4ariLegTuTUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da66708facb0e17f6d90807c6a3b98b1acb468abc08f99bb8ee5a521cf4281db","last_reissued_at":"2026-05-20T00:00:28.702475Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:28.702475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.19399","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":"2026-05-20T00:00:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I6bD28q1nuMYVPq0CH23kePDQVtohlNEBRHq5vgyPdSYUtGRrE90YDTUilsPe19olZ8+qmO4YqDBqQsTjhKhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T19:42:12.626209Z"},"content_sha256":"3808811f81866492081d811685e8c731a9a0b5512bd91dcec9463b43af9978c9","schema_version":"1.0","event_id":"sha256:3808811f81866492081d811685e8c731a9a0b5512bd91dcec9463b43af9978c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3JTHBD5MWDQX63MQQB6GUO4YWG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Akari Asai, David Sontag, Faeze Brahman, Hamish Ivison, Hannaneh Hajishirzi, Jingming Zhuo, Luca Soldaini, Luke Zettlemoyer, Molly Park, Pang Wei Koh, Pradeep Dasigi, Rulin Shao, Samuel G. Finlayson, Sewon Min, Shannon Zejiang Shen, Tongshuang Wu, Tyler Murray, Varsha Kishore, Wen-tau Yih, Xinran Zhao, Yoon Kim","submitted_at":"2025-11-24T18:35:54Z","abstract_excerpt":"Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form QA tasks via reinforcement learning with verifiable rewards, which does not extend to realistic long-form tasks. We address this with Reinforcement Learning with Evolving Rubrics (RLER), where rubrics are constructed and maintained to co-evolve with the policy model during training. This allows the rubrics to incorporate newly explored information from search and contrasting model responses, enabling better fact chec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.19399","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/2511.19399/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":"2026-05-20T00:00:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1aFbEV04M30W77aroekERL+2Rnr9Sgh2l9I/mvq6iKH5IcYc/EQZEfsZuLLWi1oS7kebFHXSWxFlAF1EbgorAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T19:42:12.626614Z"},"content_sha256":"b8f51ab1c60e3ff3cf453ea8009a40542f4cd2e4dc9b2ca9da71b9141b8f8e22","schema_version":"1.0","event_id":"sha256:b8f51ab1c60e3ff3cf453ea8009a40542f4cd2e4dc9b2ca9da71b9141b8f8e22"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3JTHBD5MWDQX63MQQB6GUO4YWG/bundle.json","state_url":"https://pith.science/pith/3JTHBD5MWDQX63MQQB6GUO4YWG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3JTHBD5MWDQX63MQQB6GUO4YWG/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":"2026-06-01T19:42:12Z","links":{"resolver":"https://pith.science/pith/3JTHBD5MWDQX63MQQB6GUO4YWG","bundle":"https://pith.science/pith/3JTHBD5MWDQX63MQQB6GUO4YWG/bundle.json","state":"https://pith.science/pith/3JTHBD5MWDQX63MQQB6GUO4YWG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3JTHBD5MWDQX63MQQB6GUO4YWG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3JTHBD5MWDQX63MQQB6GUO4YWG","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":"384da7e97856ad823a25490fef04c67517a3a39561b0b426e0dc20eda726fc33","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-24T18:35:54Z","title_canon_sha256":"acdc7b9f2d45d37d915aa709727a76f50f9087709f7d9234bfc673a2199656f3"},"schema_version":"1.0","source":{"id":"2511.19399","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.19399","created_at":"2026-05-20T00:00:28Z"},{"alias_kind":"arxiv_version","alias_value":"2511.19399v3","created_at":"2026-05-20T00:00:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.19399","created_at":"2026-05-20T00:00:28Z"},{"alias_kind":"pith_short_12","alias_value":"3JTHBD5MWDQX","created_at":"2026-05-20T00:00:28Z"},{"alias_kind":"pith_short_16","alias_value":"3JTHBD5MWDQX63MQ","created_at":"2026-05-20T00:00:28Z"},{"alias_kind":"pith_short_8","alias_value":"3JTHBD5M","created_at":"2026-05-20T00:00:28Z"}],"graph_snapshots":[{"event_id":"sha256:b8f51ab1c60e3ff3cf453ea8009a40542f4cd2e4dc9b2ca9da71b9141b8f8e22","target":"graph","created_at":"2026-05-20T00:00:28Z","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/2511.19399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form QA tasks via reinforcement learning with verifiable rewards, which does not extend to realistic long-form tasks. We address this with Reinforcement Learning with Evolving Rubrics (RLER), where rubrics are constructed and maintained to co-evolve with the policy model during training. This allows the rubrics to incorporate newly explored information from search and contrasting model responses, enabling better fact chec","authors_text":"Akari Asai, David Sontag, Faeze Brahman, Hamish Ivison, Hannaneh Hajishirzi, Jingming Zhuo, Luca Soldaini, Luke Zettlemoyer, Molly Park, Pang Wei Koh, Pradeep Dasigi, Rulin Shao, Samuel G. Finlayson, Sewon Min, Shannon Zejiang Shen, Tongshuang Wu, Tyler Murray, Varsha Kishore, Wen-tau Yih, Xinran Zhao, Yoon Kim","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-24T18:35:54Z","title":"DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.19399","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":"sha256:3808811f81866492081d811685e8c731a9a0b5512bd91dcec9463b43af9978c9","target":"record","created_at":"2026-05-20T00:00:28Z","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":"384da7e97856ad823a25490fef04c67517a3a39561b0b426e0dc20eda726fc33","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-24T18:35:54Z","title_canon_sha256":"acdc7b9f2d45d37d915aa709727a76f50f9087709f7d9234bfc673a2199656f3"},"schema_version":"1.0","source":{"id":"2511.19399","kind":"arxiv","version":3}},"canonical_sha256":"da66708facb0e17f6d90807c6a3b98b1acb468abc08f99bb8ee5a521cf4281db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da66708facb0e17f6d90807c6a3b98b1acb468abc08f99bb8ee5a521cf4281db","first_computed_at":"2026-05-20T00:00:28.702475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:28.702475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rgueS+mEENnMLv5kQkpUXanXEQRPrN50hKzZrbUm6nAik+RT3kPVSayVrDL1Iz9Qs9Ha8Qb4M4ariLegTuTUBA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:28.703113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.19399","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3808811f81866492081d811685e8c731a9a0b5512bd91dcec9463b43af9978c9","sha256:b8f51ab1c60e3ff3cf453ea8009a40542f4cd2e4dc9b2ca9da71b9141b8f8e22"],"state_sha256":"89f1cff5b3fcfb7ab896687bbb6733fb7a92b7ec409da4d65b2d40081641e56d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E7l5p1Fgqam8/GjvXk4fIob59kg4lj1GDHKzzkLTeTWg8nW162SLFCETUftGNG9WmAlMSYoUI84Fd1E4v5ycDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T19:42:12.628711Z","bundle_sha256":"3fd25fc5f8f76f82e5496c09218e8c40777628b1e1e8b5bbc03ea2d081152a53"}}