{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KPASI7VIC6IYHQLPWCAXGHSEUC","short_pith_number":"pith:KPASI7VI","canonical_record":{"source":{"id":"2404.07965","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T17:52:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"15f9dc3caa54332cbfc969384b9d38a01b43a7cd0328e61c83faf603131880aa","abstract_canon_sha256":"48a4f594aa828e140f6546f91ed888b292f938a96a61be2a787ceec2d2046676"},"schema_version":"1.0"},"canonical_sha256":"53c1247ea8179183c16fb081731e44a0a19c9adc8a47da9dccf78fc37a6aee80","source":{"kind":"arxiv","id":"2404.07965","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07965","created_at":"2026-07-05T09:58:19Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07965v4","created_at":"2026-07-05T09:58:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07965","created_at":"2026-07-05T09:58:19Z"},{"alias_kind":"pith_short_12","alias_value":"KPASI7VIC6IY","created_at":"2026-07-05T09:58:19Z"},{"alias_kind":"pith_short_16","alias_value":"KPASI7VIC6IYHQLP","created_at":"2026-07-05T09:58:19Z"},{"alias_kind":"pith_short_8","alias_value":"KPASI7VI","created_at":"2026-07-05T09:58:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KPASI7VIC6IYHQLPWCAXGHSEUC","target":"record","payload":{"canonical_record":{"source":{"id":"2404.07965","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T17:52:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"15f9dc3caa54332cbfc969384b9d38a01b43a7cd0328e61c83faf603131880aa","abstract_canon_sha256":"48a4f594aa828e140f6546f91ed888b292f938a96a61be2a787ceec2d2046676"},"schema_version":"1.0"},"canonical_sha256":"53c1247ea8179183c16fb081731e44a0a19c9adc8a47da9dccf78fc37a6aee80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:19.860801Z","signature_b64":"CZOpJVMTUwoqTqeqMMVLA05iws5WCrqFjN2UvouKWfyUGG2DjnvlQMrykW3y7Nw2Opn6y7GLQ5M89TxsnQv9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53c1247ea8179183c16fb081731e44a0a19c9adc8a47da9dccf78fc37a6aee80","last_reissued_at":"2026-07-05T09:58:19.860228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:19.860228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.07965","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:58:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dC+3UzfgpngI1LWnTPaQvI1+8Aa8UsYcRx628OCERT0iJoLJ2moKvOPelLV7URDHzorMQzhAJkOhWvuXTj7oDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:38:24.178019Z"},"content_sha256":"e2335ea2b6dc1145d9280df286324732ea90684bd195dbeffb61e03ca31170da","schema_version":"1.0","event_id":"sha256:e2335ea2b6dc1145d9280df286324732ea90684bd195dbeffb61e03ca31170da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KPASI7VIC6IYHQLPWCAXGHSEUC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rho-1: Not All Tokens Are What You Need","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Lin, Jian Jiao, Nan Duan, Ruochen Xu, Weizhu Chen, Xiao Liu, Yelong Shen, Yeyun Gong, Yujiu Yang, Zhenghao Lin, Zhibin Gou","submitted_at":"2024-04-11T17:52:01Z","abstract_excerpt":"Previous language model pre-training methods have uniformly applied a next-token prediction loss to all training tokens. Challenging this norm, we posit that \"9l training\". Our initial analysis examines token-level training dynamics of language model, revealing distinct loss patterns for different tokens. Leveraging these insights, we introduce a new language model called Rho-1. Unlike traditional LMs that learn to predict every next token in a corpus, Rho-1 employs Selective Language Modeling (SLM), which selectively trains on useful tokens that aligned with the desired distribution. This app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07965","kind":"arxiv","version":4},"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/2404.07965/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":"2026-07-05T09:58:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"COs9oEtRtjiimyYH1BXXs/L5d/ZUJVGIBbi4Y8s5/Z4cTIxw9zIZvtBJKO9CLM0ViBBp5Pa8QTXyvFNSPKwqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:38:24.179047Z"},"content_sha256":"88cc26aeb8cfbe0ff16df7846e59f7c454df854f85696997228b8f754b8f0cdb","schema_version":"1.0","event_id":"sha256:88cc26aeb8cfbe0ff16df7846e59f7c454df854f85696997228b8f754b8f0cdb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPASI7VIC6IYHQLPWCAXGHSEUC/bundle.json","state_url":"https://pith.science/pith/KPASI7VIC6IYHQLPWCAXGHSEUC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPASI7VIC6IYHQLPWCAXGHSEUC/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":"2026-08-05T07:38:24Z","links":{"resolver":"https://pith.science/pith/KPASI7VIC6IYHQLPWCAXGHSEUC","bundle":"https://pith.science/pith/KPASI7VIC6IYHQLPWCAXGHSEUC/bundle.json","state":"https://pith.science/pith/KPASI7VIC6IYHQLPWCAXGHSEUC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPASI7VIC6IYHQLPWCAXGHSEUC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KPASI7VIC6IYHQLPWCAXGHSEUC","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":"48a4f594aa828e140f6546f91ed888b292f938a96a61be2a787ceec2d2046676","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T17:52:01Z","title_canon_sha256":"15f9dc3caa54332cbfc969384b9d38a01b43a7cd0328e61c83faf603131880aa"},"schema_version":"1.0","source":{"id":"2404.07965","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07965","created_at":"2026-07-05T09:58:19Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07965v4","created_at":"2026-07-05T09:58:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07965","created_at":"2026-07-05T09:58:19Z"},{"alias_kind":"pith_short_12","alias_value":"KPASI7VIC6IY","created_at":"2026-07-05T09:58:19Z"},{"alias_kind":"pith_short_16","alias_value":"KPASI7VIC6IYHQLP","created_at":"2026-07-05T09:58:19Z"},{"alias_kind":"pith_short_8","alias_value":"KPASI7VI","created_at":"2026-07-05T09:58:19Z"}],"graph_snapshots":[{"event_id":"sha256:88cc26aeb8cfbe0ff16df7846e59f7c454df854f85696997228b8f754b8f0cdb","target":"graph","created_at":"2026-07-05T09:58:19Z","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/2404.07965/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous language model pre-training methods have uniformly applied a next-token prediction loss to all training tokens. Challenging this norm, we posit that \"9l training\". Our initial analysis examines token-level training dynamics of language model, revealing distinct loss patterns for different tokens. Leveraging these insights, we introduce a new language model called Rho-1. Unlike traditional LMs that learn to predict every next token in a corpus, Rho-1 employs Selective Language Modeling (SLM), which selectively trains on useful tokens that aligned with the desired distribution. This app","authors_text":"Chen Lin, Jian Jiao, Nan Duan, Ruochen Xu, Weizhu Chen, Xiao Liu, Yelong Shen, Yeyun Gong, Yujiu Yang, Zhenghao Lin, Zhibin Gou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T17:52:01Z","title":"Rho-1: Not All Tokens Are What You Need"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07965","kind":"arxiv","version":4},"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:e2335ea2b6dc1145d9280df286324732ea90684bd195dbeffb61e03ca31170da","target":"record","created_at":"2026-07-05T09:58:19Z","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":"48a4f594aa828e140f6546f91ed888b292f938a96a61be2a787ceec2d2046676","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T17:52:01Z","title_canon_sha256":"15f9dc3caa54332cbfc969384b9d38a01b43a7cd0328e61c83faf603131880aa"},"schema_version":"1.0","source":{"id":"2404.07965","kind":"arxiv","version":4}},"canonical_sha256":"53c1247ea8179183c16fb081731e44a0a19c9adc8a47da9dccf78fc37a6aee80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53c1247ea8179183c16fb081731e44a0a19c9adc8a47da9dccf78fc37a6aee80","first_computed_at":"2026-07-05T09:58:19.860228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:19.860228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CZOpJVMTUwoqTqeqMMVLA05iws5WCrqFjN2UvouKWfyUGG2DjnvlQMrykW3y7Nw2Opn6y7GLQ5M89TxsnQv9DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:19.860801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.07965","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2335ea2b6dc1145d9280df286324732ea90684bd195dbeffb61e03ca31170da","sha256:88cc26aeb8cfbe0ff16df7846e59f7c454df854f85696997228b8f754b8f0cdb"],"state_sha256":"f66b89159b0fc2ebcd893dea050fe28edb074eb1f5d5c01f1129ccf819c888ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KC5+Ind8tpGLwsrpbCqNA+fVK6dBTbYEvLD6O0JZrAsecqH2TmQG3kopl7Kk00GCgvbaA4ZDiLuyNggFcS+BDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:38:24.188018Z","bundle_sha256":"70a2c9a9ef26c4fde8a48640d1aa474e7f01f45a45d957c0f3b3cf908b8c6f2d"}}