{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NXGCTTBAAOGPXR6BW5B4CYMXOZ","short_pith_number":"pith:NXGCTTBA","canonical_record":{"source":{"id":"2404.00614","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T09:04:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2041331d292010f78ff9acd5909b2c62fab133eee13ed4470bbed871ab903026","abstract_canon_sha256":"453a44cecf35af996fe774af2eafa46a9265ef3af3e4ca61edb7076e8cc5055c"},"schema_version":"1.0"},"canonical_sha256":"6dcc29cc20038cfbc7c1b743c1619776541995a218ad6efbce9c25002e3d76bf","source":{"kind":"arxiv","id":"2404.00614","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00614","created_at":"2026-07-05T08:50:28Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00614v2","created_at":"2026-07-05T08:50:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00614","created_at":"2026-07-05T08:50:28Z"},{"alias_kind":"pith_short_12","alias_value":"NXGCTTBAAOGP","created_at":"2026-07-05T08:50:28Z"},{"alias_kind":"pith_short_16","alias_value":"NXGCTTBAAOGPXR6B","created_at":"2026-07-05T08:50:28Z"},{"alias_kind":"pith_short_8","alias_value":"NXGCTTBA","created_at":"2026-07-05T08:50:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NXGCTTBAAOGPXR6BW5B4CYMXOZ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.00614","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T09:04:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2041331d292010f78ff9acd5909b2c62fab133eee13ed4470bbed871ab903026","abstract_canon_sha256":"453a44cecf35af996fe774af2eafa46a9265ef3af3e4ca61edb7076e8cc5055c"},"schema_version":"1.0"},"canonical_sha256":"6dcc29cc20038cfbc7c1b743c1619776541995a218ad6efbce9c25002e3d76bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:28.509402Z","signature_b64":"qnM8zqao55RwhkftXxOaFkaQJnFrcAkJPKFeHwBGZC1yAHDQfkm9XRakjkljD+iVGYfipLNVPsbKiuBacZn+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dcc29cc20038cfbc7c1b743c1619776541995a218ad6efbce9c25002e3d76bf","last_reissued_at":"2026-07-05T08:50:28.508951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:28.508951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.00614","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:50:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G+lAW8kOZEZ11168ImKhDViXo5As2M0vCsf5qMp/Dlmx227ZyVRQLfYT9HcDAJ3tAF232Veun+5LDBFUhL3SCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:54:22.380748Z"},"content_sha256":"b8a3d1f1da3b572fb7b39bf060643f21a9288b9e31b34037d8297e47388fe3d5","schema_version":"1.0","event_id":"sha256:b8a3d1f1da3b572fb7b39bf060643f21a9288b9e31b34037d8297e47388fe3d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NXGCTTBAAOGPXR6BW5B4CYMXOZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Plan for Language Modeling from Unlabeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Florian Mai, Marie-Francine Moens, Nathan Cornille","submitted_at":"2024-03-31T09:04:01Z","abstract_excerpt":"By training to predict the next token in an unlabeled corpus, large language models learn to perform many tasks without any labeled data. However, their next-token-prediction objective arguably limits their performance in scenarios that require planning, such as writing a coherent article. In this paper, we train a module for planning the future writing process via a self-supervised learning objective. Given the textual context, this planning module learns to predict future abstract writing actions, which correspond to centroids in a clustered text embedding space. By conditioning on these act"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00614","kind":"arxiv","version":2},"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/2404.00614/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":"2026-07-05T08:50:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ujVSl68Goby04V4BPZ3BiEwTbfQhWIo1GM0Kb206gs1k4WiSsnNYXConLyEaMmjew6ctvTwwXJPxWnHEXNe8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:54:22.381329Z"},"content_sha256":"39741107a985cdaeed604ee0da777db2327629863594538f29c62705539c88d9","schema_version":"1.0","event_id":"sha256:39741107a985cdaeed604ee0da777db2327629863594538f29c62705539c88d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NXGCTTBAAOGPXR6BW5B4CYMXOZ/bundle.json","state_url":"https://pith.science/pith/NXGCTTBAAOGPXR6BW5B4CYMXOZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NXGCTTBAAOGPXR6BW5B4CYMXOZ/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":"2026-08-15T11:54:22Z","links":{"resolver":"https://pith.science/pith/NXGCTTBAAOGPXR6BW5B4CYMXOZ","bundle":"https://pith.science/pith/NXGCTTBAAOGPXR6BW5B4CYMXOZ/bundle.json","state":"https://pith.science/pith/NXGCTTBAAOGPXR6BW5B4CYMXOZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NXGCTTBAAOGPXR6BW5B4CYMXOZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NXGCTTBAAOGPXR6BW5B4CYMXOZ","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":"453a44cecf35af996fe774af2eafa46a9265ef3af3e4ca61edb7076e8cc5055c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T09:04:01Z","title_canon_sha256":"2041331d292010f78ff9acd5909b2c62fab133eee13ed4470bbed871ab903026"},"schema_version":"1.0","source":{"id":"2404.00614","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00614","created_at":"2026-07-05T08:50:28Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00614v2","created_at":"2026-07-05T08:50:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00614","created_at":"2026-07-05T08:50:28Z"},{"alias_kind":"pith_short_12","alias_value":"NXGCTTBAAOGP","created_at":"2026-07-05T08:50:28Z"},{"alias_kind":"pith_short_16","alias_value":"NXGCTTBAAOGPXR6B","created_at":"2026-07-05T08:50:28Z"},{"alias_kind":"pith_short_8","alias_value":"NXGCTTBA","created_at":"2026-07-05T08:50:28Z"}],"graph_snapshots":[{"event_id":"sha256:39741107a985cdaeed604ee0da777db2327629863594538f29c62705539c88d9","target":"graph","created_at":"2026-07-05T08:50:28Z","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/2404.00614/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"By training to predict the next token in an unlabeled corpus, large language models learn to perform many tasks without any labeled data. However, their next-token-prediction objective arguably limits their performance in scenarios that require planning, such as writing a coherent article. In this paper, we train a module for planning the future writing process via a self-supervised learning objective. Given the textual context, this planning module learns to predict future abstract writing actions, which correspond to centroids in a clustered text embedding space. By conditioning on these act","authors_text":"Florian Mai, Marie-Francine Moens, Nathan Cornille","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T09:04:01Z","title":"Learning to Plan for Language Modeling from Unlabeled Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00614","kind":"arxiv","version":2},"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:b8a3d1f1da3b572fb7b39bf060643f21a9288b9e31b34037d8297e47388fe3d5","target":"record","created_at":"2026-07-05T08:50:28Z","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":"453a44cecf35af996fe774af2eafa46a9265ef3af3e4ca61edb7076e8cc5055c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T09:04:01Z","title_canon_sha256":"2041331d292010f78ff9acd5909b2c62fab133eee13ed4470bbed871ab903026"},"schema_version":"1.0","source":{"id":"2404.00614","kind":"arxiv","version":2}},"canonical_sha256":"6dcc29cc20038cfbc7c1b743c1619776541995a218ad6efbce9c25002e3d76bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6dcc29cc20038cfbc7c1b743c1619776541995a218ad6efbce9c25002e3d76bf","first_computed_at":"2026-07-05T08:50:28.508951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:28.508951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qnM8zqao55RwhkftXxOaFkaQJnFrcAkJPKFeHwBGZC1yAHDQfkm9XRakjkljD+iVGYfipLNVPsbKiuBacZn+Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:28.509402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.00614","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8a3d1f1da3b572fb7b39bf060643f21a9288b9e31b34037d8297e47388fe3d5","sha256:39741107a985cdaeed604ee0da777db2327629863594538f29c62705539c88d9"],"state_sha256":"aa2fd5ba35fd41174616e22ff3a79937cf51e9ccca4516b33f4be272aa4077c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eLLA1yh2H6MfeAYgNlzvdAbm9Wq9l8HNdIl589ahyIqSOjONWpWoJG+S5ZefQpR5eQAKQ3bwZqubSrKVUyOHDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T11:54:22.386712Z","bundle_sha256":"e1ee93153e22ef63500dd7e33b7bec73147ca97093778bbb9de4cb959b72404e"}}