{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XJ7MT7PZ73XF6UQX6SVYTUOEBQ","short_pith_number":"pith:XJ7MT7PZ","canonical_record":{"source":{"id":"2412.00949","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T19:48:57Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"b44c5eee463d0572e473bb828baf9b523cc56d633b718965d9a23ae5a88ce8dd","abstract_canon_sha256":"4d27b345e4bbff7b4aa2f7eee9fec3003981c4a2c96bf19f227a18dcb92b6f48"},"schema_version":"1.0"},"canonical_sha256":"ba7ec9fdf9feee5f5217f4ab89d1c40c20f8034a77cdaef9c70515a975a9ffa7","source":{"kind":"arxiv","id":"2412.00949","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00949","created_at":"2026-07-05T09:42:50Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00949v1","created_at":"2026-07-05T09:42:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00949","created_at":"2026-07-05T09:42:50Z"},{"alias_kind":"pith_short_12","alias_value":"XJ7MT7PZ73XF","created_at":"2026-07-05T09:42:50Z"},{"alias_kind":"pith_short_16","alias_value":"XJ7MT7PZ73XF6UQX","created_at":"2026-07-05T09:42:50Z"},{"alias_kind":"pith_short_8","alias_value":"XJ7MT7PZ","created_at":"2026-07-05T09:42:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XJ7MT7PZ73XF6UQX6SVYTUOEBQ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.00949","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T19:48:57Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"b44c5eee463d0572e473bb828baf9b523cc56d633b718965d9a23ae5a88ce8dd","abstract_canon_sha256":"4d27b345e4bbff7b4aa2f7eee9fec3003981c4a2c96bf19f227a18dcb92b6f48"},"schema_version":"1.0"},"canonical_sha256":"ba7ec9fdf9feee5f5217f4ab89d1c40c20f8034a77cdaef9c70515a975a9ffa7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:50.727184Z","signature_b64":"iCd0W+ig5AWIGtL5ZKE+9jfeWqZaxH/PBUub9wXCRjIRruLlRLd8zO3UoeQBhz1mdpQSNLinpdi+A7Fxj+MdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba7ec9fdf9feee5f5217f4ab89d1c40c20f8034a77cdaef9c70515a975a9ffa7","last_reissued_at":"2026-07-05T09:42:50.726647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:50.726647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.00949","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":"2026-07-05T09:42:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+ZqaE6wHUcIExK1+C/TON8YHVqVljp4qaqCZQ9LdPcH2XO/bRt0HTL3nwMDw61BEXiKdb3KaAUk0Pgves5kMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T06:04:46.302649Z"},"content_sha256":"770d8486e9821fd51ff6118159f4c67a580e482c6df58ac8371b9d5b9eb5b839","schema_version":"1.0","event_id":"sha256:770d8486e9821fd51ff6118159f4c67a580e482c6df58ac8371b9d5b9eb5b839"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XJ7MT7PZ73XF6UQX6SVYTUOEBQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"STEVE-Audio: Expanding the Goal Conditioning Modalities of Embodied Agents in Minecraft","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Amogh Raut, Andrew Melnik, Nicholas Lenzen","submitted_at":"2024-12-01T19:48:57Z","abstract_excerpt":"Recently, the STEVE-1 approach has been introduced as a method for training generative agents to follow instructions in the form of latent CLIP embeddings. In this work, we present a methodology to extend the control modalities by learning a mapping from new input modalities to the latent goal space of the agent. We apply our approach to the challenging Minecraft domain, and extend the goal conditioning to include the audio modality. The resulting audio-conditioned agent is able to perform on a comparable level to the original text-conditioned and visual-conditioned agents. Specifically, we cr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00949","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/2412.00949/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":"2026-07-05T09:42:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DoBTXIOgoNP/TyL/HFps7mmE01p6gYhmtbCbs3qUCp61xcg9QLV8cGGTFJHeUUYRdaDzSu+TRKQnYMFmklpTBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T06:04:46.303477Z"},"content_sha256":"3ef7cbc321db52715aeb3086081c06cdf32052433deaedb0c442151d2a579755","schema_version":"1.0","event_id":"sha256:3ef7cbc321db52715aeb3086081c06cdf32052433deaedb0c442151d2a579755"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XJ7MT7PZ73XF6UQX6SVYTUOEBQ/bundle.json","state_url":"https://pith.science/pith/XJ7MT7PZ73XF6UQX6SVYTUOEBQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XJ7MT7PZ73XF6UQX6SVYTUOEBQ/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":"2026-08-15T06:04:46Z","links":{"resolver":"https://pith.science/pith/XJ7MT7PZ73XF6UQX6SVYTUOEBQ","bundle":"https://pith.science/pith/XJ7MT7PZ73XF6UQX6SVYTUOEBQ/bundle.json","state":"https://pith.science/pith/XJ7MT7PZ73XF6UQX6SVYTUOEBQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XJ7MT7PZ73XF6UQX6SVYTUOEBQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XJ7MT7PZ73XF6UQX6SVYTUOEBQ","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":"4d27b345e4bbff7b4aa2f7eee9fec3003981c4a2c96bf19f227a18dcb92b6f48","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T19:48:57Z","title_canon_sha256":"b44c5eee463d0572e473bb828baf9b523cc56d633b718965d9a23ae5a88ce8dd"},"schema_version":"1.0","source":{"id":"2412.00949","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00949","created_at":"2026-07-05T09:42:50Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00949v1","created_at":"2026-07-05T09:42:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00949","created_at":"2026-07-05T09:42:50Z"},{"alias_kind":"pith_short_12","alias_value":"XJ7MT7PZ73XF","created_at":"2026-07-05T09:42:50Z"},{"alias_kind":"pith_short_16","alias_value":"XJ7MT7PZ73XF6UQX","created_at":"2026-07-05T09:42:50Z"},{"alias_kind":"pith_short_8","alias_value":"XJ7MT7PZ","created_at":"2026-07-05T09:42:50Z"}],"graph_snapshots":[{"event_id":"sha256:3ef7cbc321db52715aeb3086081c06cdf32052433deaedb0c442151d2a579755","target":"graph","created_at":"2026-07-05T09:42:50Z","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/2412.00949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, the STEVE-1 approach has been introduced as a method for training generative agents to follow instructions in the form of latent CLIP embeddings. In this work, we present a methodology to extend the control modalities by learning a mapping from new input modalities to the latent goal space of the agent. We apply our approach to the challenging Minecraft domain, and extend the goal conditioning to include the audio modality. The resulting audio-conditioned agent is able to perform on a comparable level to the original text-conditioned and visual-conditioned agents. Specifically, we cr","authors_text":"Amogh Raut, Andrew Melnik, Nicholas Lenzen","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T19:48:57Z","title":"STEVE-Audio: Expanding the Goal Conditioning Modalities of Embodied Agents in Minecraft"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00949","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":"sha256:770d8486e9821fd51ff6118159f4c67a580e482c6df58ac8371b9d5b9eb5b839","target":"record","created_at":"2026-07-05T09:42:50Z","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":"4d27b345e4bbff7b4aa2f7eee9fec3003981c4a2c96bf19f227a18dcb92b6f48","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T19:48:57Z","title_canon_sha256":"b44c5eee463d0572e473bb828baf9b523cc56d633b718965d9a23ae5a88ce8dd"},"schema_version":"1.0","source":{"id":"2412.00949","kind":"arxiv","version":1}},"canonical_sha256":"ba7ec9fdf9feee5f5217f4ab89d1c40c20f8034a77cdaef9c70515a975a9ffa7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba7ec9fdf9feee5f5217f4ab89d1c40c20f8034a77cdaef9c70515a975a9ffa7","first_computed_at":"2026-07-05T09:42:50.726647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:50.726647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iCd0W+ig5AWIGtL5ZKE+9jfeWqZaxH/PBUub9wXCRjIRruLlRLd8zO3UoeQBhz1mdpQSNLinpdi+A7Fxj+MdBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:50.727184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00949","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:770d8486e9821fd51ff6118159f4c67a580e482c6df58ac8371b9d5b9eb5b839","sha256:3ef7cbc321db52715aeb3086081c06cdf32052433deaedb0c442151d2a579755"],"state_sha256":"49f283c1ab54bf8c3a457452e3f7ccdf4a6004a2736de9484552089b982d5444"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kWsgx0Eg8VOa16sO2A4cP/GvmsADWR88VHIbdV1Vo3P1nSxP3URDZqjbulFe6Wm4ZnRqBwmy0dpR/dosteFwDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T06:04:46.309058Z","bundle_sha256":"5a39aec25c6dfaf7bb032de648df9576d3bef38adc3741ceab5cae94e61a46b3"}}