{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OKA42BU4AJJNVCLO7AZPXKQG2Y","short_pith_number":"pith:OKA42BU4","canonical_record":{"source":{"id":"2402.19469","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-29T18:57:37Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"2a86c4205454ce6eef83c957278f5030afd63be81eded081d452575831ca7c36","abstract_canon_sha256":"9a82735cde2c5136c7deedc4a32580852ae7a802f870be07f309a2bf10459299"},"schema_version":"1.0"},"canonical_sha256":"7281cd069c0252da896ef832fbaa06d616a15d6bd0d1d27afb4a48377f58c71f","source":{"kind":"arxiv","id":"2402.19469","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19469","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19469v1","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19469","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"pith_short_12","alias_value":"OKA42BU4AJJN","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"pith_short_16","alias_value":"OKA42BU4AJJNVCLO","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"pith_short_8","alias_value":"OKA42BU4","created_at":"2026-07-05T07:50:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OKA42BU4AJJNVCLO7AZPXKQG2Y","target":"record","payload":{"canonical_record":{"source":{"id":"2402.19469","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-29T18:57:37Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"2a86c4205454ce6eef83c957278f5030afd63be81eded081d452575831ca7c36","abstract_canon_sha256":"9a82735cde2c5136c7deedc4a32580852ae7a802f870be07f309a2bf10459299"},"schema_version":"1.0"},"canonical_sha256":"7281cd069c0252da896ef832fbaa06d616a15d6bd0d1d27afb4a48377f58c71f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:45.700150Z","signature_b64":"dkG6OD0ZPi3jFKRwJK/vCYQ8YJKC44T/j9ugjOtmZuobqVi/eeySorI6EMeDwIdWy2goBnvRdsXa+fPSKN0xDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7281cd069c0252da896ef832fbaa06d616a15d6bd0d1d27afb4a48377f58c71f","last_reissued_at":"2026-07-05T07:50:45.699642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:45.699642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.19469","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":"2026-07-05T07:50:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/laoTk7JIw4Mt3ToV/vWVOTIzvykgii2/SlRXZ1N8nLUWKmuGJ+kDKM3Xeo+RE7ZsLdgvF2lgGV1V3doBGOUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T01:21:06.519169Z"},"content_sha256":"854b199fcba860bf184f9869ec9f6e83fd0270782a08ef6fe3b26252ce60cd4d","schema_version":"1.0","event_id":"sha256:854b199fcba860bf184f9869ec9f6e83fd0270782a08ef6fe3b26252ce60cd4d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OKA42BU4AJJNVCLO7AZPXKQG2Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Humanoid Locomotion as Next Token Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Baifeng Shi, Bike Zhang, Ilija Radosavovic, Jathushan Rajasegaran, Jitendra Malik, Koushil Sreenath, Sarthak Kamat, Trevor Darrell","submitted_at":"2024-02-29T18:57:37Z","abstract_excerpt":"We cast real-world humanoid control as a next token prediction problem, akin to predicting the next word in language. Our model is a causal transformer trained via autoregressive prediction of sensorimotor trajectories. To account for the multi-modal nature of the data, we perform prediction in a modality-aligned way, and for each input token predict the next token from the same modality. This general formulation enables us to leverage data with missing modalities, like video trajectories without actions. We train our model on a collection of simulated trajectories coming from prior neural net"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19469","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/2402.19469/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":"2026-07-05T07:50:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vJ10aXx13V5ORvCdTG17iLerAFn5crjBHhG/yAN6ZfdaHYyNE85c71yjmOuGREoWBClBU0ZjPcoX8qnJZD0JDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T01:21:06.519674Z"},"content_sha256":"b81216ee523fd4eb1868b9cdb1ac543199dcb736c72e3eb728e871fe2cf27d2d","schema_version":"1.0","event_id":"sha256:b81216ee523fd4eb1868b9cdb1ac543199dcb736c72e3eb728e871fe2cf27d2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OKA42BU4AJJNVCLO7AZPXKQG2Y/bundle.json","state_url":"https://pith.science/pith/OKA42BU4AJJNVCLO7AZPXKQG2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OKA42BU4AJJNVCLO7AZPXKQG2Y/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":"2026-08-21T01:21:06Z","links":{"resolver":"https://pith.science/pith/OKA42BU4AJJNVCLO7AZPXKQG2Y","bundle":"https://pith.science/pith/OKA42BU4AJJNVCLO7AZPXKQG2Y/bundle.json","state":"https://pith.science/pith/OKA42BU4AJJNVCLO7AZPXKQG2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OKA42BU4AJJNVCLO7AZPXKQG2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OKA42BU4AJJNVCLO7AZPXKQG2Y","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":"9a82735cde2c5136c7deedc4a32580852ae7a802f870be07f309a2bf10459299","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-29T18:57:37Z","title_canon_sha256":"2a86c4205454ce6eef83c957278f5030afd63be81eded081d452575831ca7c36"},"schema_version":"1.0","source":{"id":"2402.19469","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19469","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19469v1","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19469","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"pith_short_12","alias_value":"OKA42BU4AJJN","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"pith_short_16","alias_value":"OKA42BU4AJJNVCLO","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"pith_short_8","alias_value":"OKA42BU4","created_at":"2026-07-05T07:50:45Z"}],"graph_snapshots":[{"event_id":"sha256:b81216ee523fd4eb1868b9cdb1ac543199dcb736c72e3eb728e871fe2cf27d2d","target":"graph","created_at":"2026-07-05T07:50:45Z","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/2402.19469/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We cast real-world humanoid control as a next token prediction problem, akin to predicting the next word in language. Our model is a causal transformer trained via autoregressive prediction of sensorimotor trajectories. To account for the multi-modal nature of the data, we perform prediction in a modality-aligned way, and for each input token predict the next token from the same modality. This general formulation enables us to leverage data with missing modalities, like video trajectories without actions. We train our model on a collection of simulated trajectories coming from prior neural net","authors_text":"Baifeng Shi, Bike Zhang, Ilija Radosavovic, Jathushan Rajasegaran, Jitendra Malik, Koushil Sreenath, Sarthak Kamat, Trevor Darrell","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-29T18:57:37Z","title":"Humanoid Locomotion as Next Token Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19469","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":"sha256:854b199fcba860bf184f9869ec9f6e83fd0270782a08ef6fe3b26252ce60cd4d","target":"record","created_at":"2026-07-05T07:50:45Z","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":"9a82735cde2c5136c7deedc4a32580852ae7a802f870be07f309a2bf10459299","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-29T18:57:37Z","title_canon_sha256":"2a86c4205454ce6eef83c957278f5030afd63be81eded081d452575831ca7c36"},"schema_version":"1.0","source":{"id":"2402.19469","kind":"arxiv","version":1}},"canonical_sha256":"7281cd069c0252da896ef832fbaa06d616a15d6bd0d1d27afb4a48377f58c71f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7281cd069c0252da896ef832fbaa06d616a15d6bd0d1d27afb4a48377f58c71f","first_computed_at":"2026-07-05T07:50:45.699642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:45.699642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dkG6OD0ZPi3jFKRwJK/vCYQ8YJKC44T/j9ugjOtmZuobqVi/eeySorI6EMeDwIdWy2goBnvRdsXa+fPSKN0xDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:45.700150Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.19469","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:854b199fcba860bf184f9869ec9f6e83fd0270782a08ef6fe3b26252ce60cd4d","sha256:b81216ee523fd4eb1868b9cdb1ac543199dcb736c72e3eb728e871fe2cf27d2d"],"state_sha256":"54a1f149864a3e8d293fd14572aa7fea846047993c65fce2a3e2ea94a244d934"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2HEh/8yAqyfT0TEKNPnWN7RhvJC6Ks9XezutUQOGW+ZsQIewJbzsSNI2C6R/qz6DC/DcWUfE7iT+xsjMhm3JBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T01:21:06.524524Z","bundle_sha256":"e98f50ba12b7af2162c7afd4824e0254031fe8cf1345657349322303278286b0"}}