{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XS67K5ZENM3CIRB42YHJKN6PQA","short_pith_number":"pith:XS67K5ZE","canonical_record":{"source":{"id":"2606.08501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T07:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"233f8c8448d641f4a7727d67a09e53c3470bb42e913d27ec8ceec0c04aae1d17","abstract_canon_sha256":"bb831f2ec09f51108d373f3bdc119b6bbe14e9e1f79f74720c3981a94ed6fe1e"},"schema_version":"1.0"},"canonical_sha256":"bcbdf577246b3624443cd60e9537cf8025eedbac465b1ccd3a48ab03b5271d9d","source":{"kind":"arxiv","id":"2606.08501","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08501","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08501v1","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08501","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"XS67K5ZENM3C","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"XS67K5ZENM3CIRB4","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"XS67K5ZE","created_at":"2026-06-09T01:05:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XS67K5ZENM3CIRB42YHJKN6PQA","target":"record","payload":{"canonical_record":{"source":{"id":"2606.08501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T07:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"233f8c8448d641f4a7727d67a09e53c3470bb42e913d27ec8ceec0c04aae1d17","abstract_canon_sha256":"bb831f2ec09f51108d373f3bdc119b6bbe14e9e1f79f74720c3981a94ed6fe1e"},"schema_version":"1.0"},"canonical_sha256":"bcbdf577246b3624443cd60e9537cf8025eedbac465b1ccd3a48ab03b5271d9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:38.452419Z","signature_b64":"AZ3i7ziX0gom8vWQy1dkYvnGFv6yuI7RSQVMzatTIPMj9o0mlkNLC4dXWAHZQ+jJzFFYVTpthnMBqHqIE/bKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcbdf577246b3624443cd60e9537cf8025eedbac465b1ccd3a48ab03b5271d9d","last_reissued_at":"2026-06-09T01:05:38.451957Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:38.451957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.08501","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":"2026-06-09T01:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+XTFFSW1w5RkDyDnfZT/DS+Bv1DSXBkFcBwxdFN7TA9PsibCxOCXOh7r6Ld6EaZHqia/njknwZs7AGsE9GL8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T12:55:38.105936Z"},"content_sha256":"96402674df84e97cc55f92668ebb12d9aa65337cb25b7fea0080fb775e83e8bd","schema_version":"1.0","event_id":"sha256:96402674df84e97cc55f92668ebb12d9aa65337cb25b7fea0080fb775e83e8bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XS67K5ZENM3CIRB42YHJKN6PQA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongchen Luo, Jie Xiao, Kai Zhu, Wei Zhai, Xueyang Fu, Yang Cao, Yawen Shao, Yu Liu, Zheng-Jun Zha","submitted_at":"2026-06-07T07:59:55Z","abstract_excerpt":"Reinforcement learning (RL) holds immense promise for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, progress is fundamentally constrained by a dual misalignment between authentic generation trajectory and the gradient update process: (i) Process-reward misalignment. Sparse, terminal rewards are indiscriminately assigned to all intermediate steps of the generation process, failing to provide discriminative credit assignment. (ii) State-trajectory misalignment. Policy updates are often diverted toward artificial, out-of-trajectory states, squandering g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08501","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/2606.08501/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":"2026-06-09T01:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zvUyT4WrBhoAtx5lSxUVmv1eZ3C1YILyUSZuEuPA8wPN7+ZCGYhJAdtv+2xh12sVviocF/RimVYXO3IkShyaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T12:55:38.106728Z"},"content_sha256":"5087f6f2369fd3cddb3ca7f449d1afab202b75ba404d48049d67c074e0a890a7","schema_version":"1.0","event_id":"sha256:5087f6f2369fd3cddb3ca7f449d1afab202b75ba404d48049d67c074e0a890a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XS67K5ZENM3CIRB42YHJKN6PQA/bundle.json","state_url":"https://pith.science/pith/XS67K5ZENM3CIRB42YHJKN6PQA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XS67K5ZENM3CIRB42YHJKN6PQA/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":"2026-06-10T12:55:38Z","links":{"resolver":"https://pith.science/pith/XS67K5ZENM3CIRB42YHJKN6PQA","bundle":"https://pith.science/pith/XS67K5ZENM3CIRB42YHJKN6PQA/bundle.json","state":"https://pith.science/pith/XS67K5ZENM3CIRB42YHJKN6PQA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XS67K5ZENM3CIRB42YHJKN6PQA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XS67K5ZENM3CIRB42YHJKN6PQA","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":"bb831f2ec09f51108d373f3bdc119b6bbe14e9e1f79f74720c3981a94ed6fe1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T07:59:55Z","title_canon_sha256":"233f8c8448d641f4a7727d67a09e53c3470bb42e913d27ec8ceec0c04aae1d17"},"schema_version":"1.0","source":{"id":"2606.08501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08501","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08501v1","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08501","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"XS67K5ZENM3C","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"XS67K5ZENM3CIRB4","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"XS67K5ZE","created_at":"2026-06-09T01:05:38Z"}],"graph_snapshots":[{"event_id":"sha256:5087f6f2369fd3cddb3ca7f449d1afab202b75ba404d48049d67c074e0a890a7","target":"graph","created_at":"2026-06-09T01:05:38Z","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/2606.08501/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) holds immense promise for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, progress is fundamentally constrained by a dual misalignment between authentic generation trajectory and the gradient update process: (i) Process-reward misalignment. Sparse, terminal rewards are indiscriminately assigned to all intermediate steps of the generation process, failing to provide discriminative credit assignment. (ii) State-trajectory misalignment. Policy updates are often diverted toward artificial, out-of-trajectory states, squandering g","authors_text":"Hongchen Luo, Jie Xiao, Kai Zhu, Wei Zhai, Xueyang Fu, Yang Cao, Yawen Shao, Yu Liu, Zheng-Jun Zha","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T07:59:55Z","title":"Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08501","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":"sha256:96402674df84e97cc55f92668ebb12d9aa65337cb25b7fea0080fb775e83e8bd","target":"record","created_at":"2026-06-09T01:05:38Z","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":"bb831f2ec09f51108d373f3bdc119b6bbe14e9e1f79f74720c3981a94ed6fe1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T07:59:55Z","title_canon_sha256":"233f8c8448d641f4a7727d67a09e53c3470bb42e913d27ec8ceec0c04aae1d17"},"schema_version":"1.0","source":{"id":"2606.08501","kind":"arxiv","version":1}},"canonical_sha256":"bcbdf577246b3624443cd60e9537cf8025eedbac465b1ccd3a48ab03b5271d9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcbdf577246b3624443cd60e9537cf8025eedbac465b1ccd3a48ab03b5271d9d","first_computed_at":"2026-06-09T01:05:38.451957Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:38.451957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AZ3i7ziX0gom8vWQy1dkYvnGFv6yuI7RSQVMzatTIPMj9o0mlkNLC4dXWAHZQ+jJzFFYVTpthnMBqHqIE/bKAw==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:38.452419Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96402674df84e97cc55f92668ebb12d9aa65337cb25b7fea0080fb775e83e8bd","sha256:5087f6f2369fd3cddb3ca7f449d1afab202b75ba404d48049d67c074e0a890a7"],"state_sha256":"ea0414b91c80a5eb7e6aee979fdfb284d37fcff290b41959b688641383153a5d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K5wiozyplW7prT2R5T0AWF163dmJfPSnAuGqgBygkeqYw0RgEjLq/x+gPd8NJMZc4+4YQHkN0F/XW/xyF4oqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T12:55:38.110758Z","bundle_sha256":"c84b14ee1d94bc9a002dcd44971aca37dcb237f31e0cc3ccee301a636e850173"}}