{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2Q7GPC27AYWXVKYKW35LOQCDQX","short_pith_number":"pith:2Q7GPC27","canonical_record":{"source":{"id":"2605.31228","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T12:31:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dbca9631691a8aaa2149af829a7019cdbcb9ee23193a9d14af3c70571a71ba66","abstract_canon_sha256":"7edcd298a37679da3035684a822b91735bc45a83c852725d9a0937d250a4450d"},"schema_version":"1.0"},"canonical_sha256":"d43e678b5f062d7aab0ab6fab7404385fe248f65b783aefb69d02cfdf5617436","source":{"kind":"arxiv","id":"2605.31228","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31228","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31228v1","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31228","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"2Q7GPC27AYWX","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"2Q7GPC27AYWXVKYK","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"2Q7GPC27","created_at":"2026-06-01T01:04:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2Q7GPC27AYWXVKYKW35LOQCDQX","target":"record","payload":{"canonical_record":{"source":{"id":"2605.31228","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T12:31:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dbca9631691a8aaa2149af829a7019cdbcb9ee23193a9d14af3c70571a71ba66","abstract_canon_sha256":"7edcd298a37679da3035684a822b91735bc45a83c852725d9a0937d250a4450d"},"schema_version":"1.0"},"canonical_sha256":"d43e678b5f062d7aab0ab6fab7404385fe248f65b783aefb69d02cfdf5617436","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:04:05.116599Z","signature_b64":"F3x9iRzw5BoInOgjqxMHs7tOrwuZUaZw+AcrPqYj6zNOLK7eebZJR2GHtAXowD8jswk96OghPG82AtgSGgvzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d43e678b5f062d7aab0ab6fab7404385fe248f65b783aefb69d02cfdf5617436","last_reissued_at":"2026-06-01T01:04:05.115819Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:04:05.115819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.31228","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":"2026-06-01T01:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"blQW3XDw/3jv6B1Vyy2VmBjAQNR9ZdSYwEe7Ohr5+jJsEgF9KWOs62TgZvn8Ge3UZhCCI2P24bzY3bvz3wQICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T16:18:37.965839Z"},"content_sha256":"c3362cfab0d8bd6606869f78558e00533683d545b1120f02a041c150ed47155d","schema_version":"1.0","event_id":"sha256:c3362cfab0d8bd6606869f78558e00533683d545b1120f02a041c150ed47155d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2Q7GPC27AYWXVKYKW35LOQCDQX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EchoRL: Reinforcement Learning via Rollout Echoing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aniri, Jinhe Bi, Michael F\\\"arber, Minglai Yang, Sikuan Yan, Volker Tresp, Wenke Huang, Xingcheng Zhou, Xun Xiao, Yujun Wang, Yunpu Ma, Zixuan Cao","submitted_at":"2026-05-29T12:31:55Z","abstract_excerpt":"Reinforcement Learning with Verifiable Rewards is an effective route for post-training to strengthen the reasoning capability of large language models. However, as training proceeds, the learning signal can collapse thus makes the training gain become marginal and ineffective. Specifically, a growing fraction of prompts' rollouts become advantage-degenerated: all the self-generated rollouts show verified-success, making the standard deviation over their rewards be zero; accordingly each rollout's advantage becomes degenerated (zero) as well. Given such rollouts' advantages, the policy-gradient"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31228","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/2605.31228/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":"2026-06-01T01:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EoFdoNZS2weKnTnlGV9lJ87WOK9LNHGdFxNajVFlN0BI0f6t9WJ3kduykOxrieO0rdeZh5jK+YTogSGiSO00Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T16:18:37.966508Z"},"content_sha256":"dedfd0de17d20413ef905da86ce3c2b51dfbe8f32f9abf2aae2c11a488280d23","schema_version":"1.0","event_id":"sha256:dedfd0de17d20413ef905da86ce3c2b51dfbe8f32f9abf2aae2c11a488280d23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2Q7GPC27AYWXVKYKW35LOQCDQX/bundle.json","state_url":"https://pith.science/pith/2Q7GPC27AYWXVKYKW35LOQCDQX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2Q7GPC27AYWXVKYKW35LOQCDQX/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":"2026-06-07T16:18:37Z","links":{"resolver":"https://pith.science/pith/2Q7GPC27AYWXVKYKW35LOQCDQX","bundle":"https://pith.science/pith/2Q7GPC27AYWXVKYKW35LOQCDQX/bundle.json","state":"https://pith.science/pith/2Q7GPC27AYWXVKYKW35LOQCDQX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2Q7GPC27AYWXVKYKW35LOQCDQX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2Q7GPC27AYWXVKYKW35LOQCDQX","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":"7edcd298a37679da3035684a822b91735bc45a83c852725d9a0937d250a4450d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T12:31:55Z","title_canon_sha256":"dbca9631691a8aaa2149af829a7019cdbcb9ee23193a9d14af3c70571a71ba66"},"schema_version":"1.0","source":{"id":"2605.31228","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31228","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31228v1","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31228","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"2Q7GPC27AYWX","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"2Q7GPC27AYWXVKYK","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"2Q7GPC27","created_at":"2026-06-01T01:04:05Z"}],"graph_snapshots":[{"event_id":"sha256:dedfd0de17d20413ef905da86ce3c2b51dfbe8f32f9abf2aae2c11a488280d23","target":"graph","created_at":"2026-06-01T01:04:05Z","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/2605.31228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Verifiable Rewards is an effective route for post-training to strengthen the reasoning capability of large language models. However, as training proceeds, the learning signal can collapse thus makes the training gain become marginal and ineffective. Specifically, a growing fraction of prompts' rollouts become advantage-degenerated: all the self-generated rollouts show verified-success, making the standard deviation over their rewards be zero; accordingly each rollout's advantage becomes degenerated (zero) as well. Given such rollouts' advantages, the policy-gradient","authors_text":"Aniri, Jinhe Bi, Michael F\\\"arber, Minglai Yang, Sikuan Yan, Volker Tresp, Wenke Huang, Xingcheng Zhou, Xun Xiao, Yujun Wang, Yunpu Ma, Zixuan Cao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T12:31:55Z","title":"EchoRL: Reinforcement Learning via Rollout Echoing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31228","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:c3362cfab0d8bd6606869f78558e00533683d545b1120f02a041c150ed47155d","target":"record","created_at":"2026-06-01T01:04:05Z","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":"7edcd298a37679da3035684a822b91735bc45a83c852725d9a0937d250a4450d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T12:31:55Z","title_canon_sha256":"dbca9631691a8aaa2149af829a7019cdbcb9ee23193a9d14af3c70571a71ba66"},"schema_version":"1.0","source":{"id":"2605.31228","kind":"arxiv","version":1}},"canonical_sha256":"d43e678b5f062d7aab0ab6fab7404385fe248f65b783aefb69d02cfdf5617436","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d43e678b5f062d7aab0ab6fab7404385fe248f65b783aefb69d02cfdf5617436","first_computed_at":"2026-06-01T01:04:05.115819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:04:05.115819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F3x9iRzw5BoInOgjqxMHs7tOrwuZUaZw+AcrPqYj6zNOLK7eebZJR2GHtAXowD8jswk96OghPG82AtgSGgvzDA==","signature_status":"signed_v1","signed_at":"2026-06-01T01:04:05.116599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31228","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3362cfab0d8bd6606869f78558e00533683d545b1120f02a041c150ed47155d","sha256:dedfd0de17d20413ef905da86ce3c2b51dfbe8f32f9abf2aae2c11a488280d23"],"state_sha256":"5d6b15dfeec130ff699da38689e6dffb6ef07f4ce4d9faa5cc46e3e119d8f05e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zAHxmuspA4qELxdRSXJ3Cr+EF0TawQhJENhwYf3sJsPTaAvFTzlEpD/HUh93eF9cRXHmjcOQyDWMNMPEkudQCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T16:18:37.970524Z","bundle_sha256":"adebf3039a738de456b7af7856b1ac82578f71ab55f1e13972bde9cfad355474"}}