{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YGP6Y46HL5B3453ZTT662BBEPO","short_pith_number":"pith:YGP6Y46H","canonical_record":{"source":{"id":"2607.26515","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T06:28:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e8373ab8700811d044ae38efc4b053f35af4f79792ec1340d436c750e8148c6f","abstract_canon_sha256":"4dcd486300e68e063676fbfb399d47d6ae57f43c3d06e600ba08ae56f575be10"},"schema_version":"1.0"},"canonical_sha256":"c19fec73c75f43be77799cfded04247ba0f8330bfeccd6ab39e0987b6d25e1f0","source":{"kind":"arxiv","id":"2607.26515","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26515","created_at":"2026-07-30T01:20:45Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26515v1","created_at":"2026-07-30T01:20:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26515","created_at":"2026-07-30T01:20:45Z"},{"alias_kind":"pith_short_12","alias_value":"YGP6Y46HL5B3","created_at":"2026-07-30T01:20:45Z"},{"alias_kind":"pith_short_16","alias_value":"YGP6Y46HL5B3453Z","created_at":"2026-07-30T01:20:45Z"},{"alias_kind":"pith_short_8","alias_value":"YGP6Y46H","created_at":"2026-07-30T01:20:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YGP6Y46HL5B3453ZTT662BBEPO","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26515","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T06:28:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e8373ab8700811d044ae38efc4b053f35af4f79792ec1340d436c750e8148c6f","abstract_canon_sha256":"4dcd486300e68e063676fbfb399d47d6ae57f43c3d06e600ba08ae56f575be10"},"schema_version":"1.0"},"canonical_sha256":"c19fec73c75f43be77799cfded04247ba0f8330bfeccd6ab39e0987b6d25e1f0","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c19fec73c75f43be77799cfded04247ba0f8330bfeccd6ab39e0987b6d25e1f0","last_reissued_at":"2026-07-30T01:20:45.406518Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:20:45.406518Z"},"source_kind":"arxiv","source_id":"2607.26515","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":"2026-07-30T01:20:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lWy7erj9O4hq18rCwY0gqwuPB4j+owZyUUJNWtGKbwQ6WtG5ooj+eHy28SiDVgnzVLiTwXZdEUtluSTFjb4nBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:25:00.649499Z"},"content_sha256":"6652ff37af28e51a3bd8998bdfd7efd40c3ef6fb7c950da8e367acee0b96c9a8","schema_version":"1.0","event_id":"sha256:6652ff37af28e51a3bd8998bdfd7efd40c3ef6fb7c950da8e367acee0b96c9a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YGP6Y46HL5B3453ZTT662BBEPO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anandharaju Durai Raju, Fengchen He, Guipeng Hu, Hei Yi Mak, Hoang Le, Junsong Wang, Mehran Taghian Jazi, Shadan Golestan, Tanzila Rahman, Tianchi Hu, Yao Wang, Yaoyuan Wang, Yunke Peng","submitted_at":"2026-07-29T06:28:26Z","abstract_excerpt":"We present, to our knowledge, the first end-to-end FP4 RL post-training, in which both the rollout and training policies, including their forward and backward passes, operate at 4-bit precision. A systematic study reveals that the dominant source of degradation in FP4 RL is not training-side quantization error but rollout activation quantization: outliers stretch the dynamic range so far that a large number of activation values underflow to zero under FP4. Counterintuitively, restoring the training policy to higher precision while keeping the rollout in FP4 makes accuracy worse than full FP4 b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26515","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/2607.26515/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":"2026-07-30T01:20:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UiTWu6+BlIHSQw2t+6GDTw8e/OZh11DjDPh9pb6fX6u+PUp724V2GpQlCqTDk57sZkguV97cDuljTrWToRakCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:25:00.650417Z"},"content_sha256":"622dba0ab753ad102ab24b72acbdc2e90ddaea3837d1f05385b37181b5249652","schema_version":"1.0","event_id":"sha256:622dba0ab753ad102ab24b72acbdc2e90ddaea3837d1f05385b37181b5249652"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YGP6Y46HL5B3453ZTT662BBEPO/bundle.json","state_url":"https://pith.science/pith/YGP6Y46HL5B3453ZTT662BBEPO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YGP6Y46HL5B3453ZTT662BBEPO/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":"2026-08-05T03:25:00Z","links":{"resolver":"https://pith.science/pith/YGP6Y46HL5B3453ZTT662BBEPO","bundle":"https://pith.science/pith/YGP6Y46HL5B3453ZTT662BBEPO/bundle.json","state":"https://pith.science/pith/YGP6Y46HL5B3453ZTT662BBEPO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YGP6Y46HL5B3453ZTT662BBEPO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YGP6Y46HL5B3453ZTT662BBEPO","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":"4dcd486300e68e063676fbfb399d47d6ae57f43c3d06e600ba08ae56f575be10","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T06:28:26Z","title_canon_sha256":"e8373ab8700811d044ae38efc4b053f35af4f79792ec1340d436c750e8148c6f"},"schema_version":"1.0","source":{"id":"2607.26515","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26515","created_at":"2026-07-30T01:20:45Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26515v1","created_at":"2026-07-30T01:20:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26515","created_at":"2026-07-30T01:20:45Z"},{"alias_kind":"pith_short_12","alias_value":"YGP6Y46HL5B3","created_at":"2026-07-30T01:20:45Z"},{"alias_kind":"pith_short_16","alias_value":"YGP6Y46HL5B3453Z","created_at":"2026-07-30T01:20:45Z"},{"alias_kind":"pith_short_8","alias_value":"YGP6Y46H","created_at":"2026-07-30T01:20:45Z"}],"graph_snapshots":[{"event_id":"sha256:622dba0ab753ad102ab24b72acbdc2e90ddaea3837d1f05385b37181b5249652","target":"graph","created_at":"2026-07-30T01:20:45Z","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/2607.26515/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present, to our knowledge, the first end-to-end FP4 RL post-training, in which both the rollout and training policies, including their forward and backward passes, operate at 4-bit precision. A systematic study reveals that the dominant source of degradation in FP4 RL is not training-side quantization error but rollout activation quantization: outliers stretch the dynamic range so far that a large number of activation values underflow to zero under FP4. Counterintuitively, restoring the training policy to higher precision while keeping the rollout in FP4 makes accuracy worse than full FP4 b","authors_text":"Anandharaju Durai Raju, Fengchen He, Guipeng Hu, Hei Yi Mak, Hoang Le, Junsong Wang, Mehran Taghian Jazi, Shadan Golestan, Tanzila Rahman, Tianchi Hu, Yao Wang, Yaoyuan Wang, Yunke Peng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T06:28:26Z","title":"HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26515","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":"sha256:6652ff37af28e51a3bd8998bdfd7efd40c3ef6fb7c950da8e367acee0b96c9a8","target":"record","created_at":"2026-07-30T01:20:45Z","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":"4dcd486300e68e063676fbfb399d47d6ae57f43c3d06e600ba08ae56f575be10","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T06:28:26Z","title_canon_sha256":"e8373ab8700811d044ae38efc4b053f35af4f79792ec1340d436c750e8148c6f"},"schema_version":"1.0","source":{"id":"2607.26515","kind":"arxiv","version":1}},"canonical_sha256":"c19fec73c75f43be77799cfded04247ba0f8330bfeccd6ab39e0987b6d25e1f0","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c19fec73c75f43be77799cfded04247ba0f8330bfeccd6ab39e0987b6d25e1f0","first_computed_at":"2026-07-30T01:20:45.406518Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:20:45.406518Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26515","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6652ff37af28e51a3bd8998bdfd7efd40c3ef6fb7c950da8e367acee0b96c9a8","sha256:622dba0ab753ad102ab24b72acbdc2e90ddaea3837d1f05385b37181b5249652"],"state_sha256":"9d07c6a648cca4cddcf539d49c1b7f088040bfc61832f103092daab0ba796662"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GCL5O8J/WBLinOBS8dMBFPb5IbEgUJgLEeE0mg/yBfW8XAXqDQ9mAmYvwojnkTMgpIe4QF1E3jUSvWg++gFFAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:25:00.657482Z","bundle_sha256":"0d26e42827f7dfb781a3322bc20e5629f4fc23992ac8d99040433c9e5adc5ddc"}}