{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PP2VIP7AY6EHVHIOVQR2STQYLG","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":"e6d2cbbb2d0ce1d8b47973c09eb1a7695868b792eeff40067d62387f606ac0ef","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T15:51:39Z","title_canon_sha256":"e43fbf5c7df358b34785b0dee35f5a6b787022449d592849908f2eb2b3b5c5f3"},"schema_version":"1.0","source":{"id":"2606.24994","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24994","created_at":"2026-06-25T00:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24994v1","created_at":"2026-06-25T00:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24994","created_at":"2026-06-25T00:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"PP2VIP7AY6EH","created_at":"2026-06-25T00:17:47Z"},{"alias_kind":"pith_short_16","alias_value":"PP2VIP7AY6EHVHIO","created_at":"2026-06-25T00:17:47Z"},{"alias_kind":"pith_short_8","alias_value":"PP2VIP7A","created_at":"2026-06-25T00:17:47Z"}],"graph_snapshots":[{"event_id":"sha256:6403364716d956e0c4d206c1c750e61069794d833d18cbb7a8bd8080ca8b3253","target":"graph","created_at":"2026-06-25T00:17:47Z","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/2606.24994/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) for language-model reasoning can fail at both extremes of task difficulty: easy prompts often produce all-correct, low-diversity rollout groups with little gradient signal, while hard prompts can produce all-incorrect groups with no positive reward. We introduce ExTra (Exploratory Trajectory Optimization), a GRPO-compatible framework that extracts exploration signals from the model's own rollouts. ExTra combines two mechanisms: (i) a novelty reward that adds embedding-based diversity bonuses after GRPO normalization, rewarding diverse corre","authors_text":"Bryan Kian Hsiang Low, Daniel Dahlmeier, Junxiang Jia, See-kiong Ng, Wenyang Hu, Zhen Shu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T15:51:39Z","title":"ExTra: Exploratory Trajectory Optimization for Language Model Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24994","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:c5282e4ee539801937fcfba600083628037024ac456b088da213a87d373c5a4e","target":"record","created_at":"2026-06-25T00:17:47Z","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":"e6d2cbbb2d0ce1d8b47973c09eb1a7695868b792eeff40067d62387f606ac0ef","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T15:51:39Z","title_canon_sha256":"e43fbf5c7df358b34785b0dee35f5a6b787022449d592849908f2eb2b3b5c5f3"},"schema_version":"1.0","source":{"id":"2606.24994","kind":"arxiv","version":1}},"canonical_sha256":"7bf5543fe0c7887a9d0eac23a94e1859a22eb063dc88991a8b2aeeb62303efd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bf5543fe0c7887a9d0eac23a94e1859a22eb063dc88991a8b2aeeb62303efd0","first_computed_at":"2026-06-25T00:17:47.769039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T00:17:47.769039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Azsa44KPaKIgrsIKiskjFYQqPeHZYftcQ/JWBr6Kfy6WzbKArfGpKlXfy83u9gjwVpD7l1/M1miNpUHDoD1tBg==","signature_status":"signed_v1","signed_at":"2026-06-25T00:17:47.769441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24994","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5282e4ee539801937fcfba600083628037024ac456b088da213a87d373c5a4e","sha256:6403364716d956e0c4d206c1c750e61069794d833d18cbb7a8bd8080ca8b3253"],"state_sha256":"f65578a85c9141e0c933cf91708f63411a9f85e0b571f628cc4ef155f614d545"}