{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y2E7Q5ZSTW7JU7LRI5YRSJYMFS","short_pith_number":"pith:Y2E7Q5ZS","canonical_record":{"source":{"id":"2410.03450","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T14:10:39Z","cross_cats_sorted":[],"title_canon_sha256":"e6d13dc120d9f8a5357bfcad4f88d49fd77ab5657fda47ff1ff16ebf470b464d","abstract_canon_sha256":"97742730f90199c2f92301a371ee66f377b24448c8d4eb495d8a0d0a25d1dbc2"},"schema_version":"1.0"},"canonical_sha256":"c689f877329dbe9a7d71477119270c2cab52d1a4e964352851c2b40573cbda4c","source":{"kind":"arxiv","id":"2410.03450","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03450","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03450v2","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03450","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"pith_short_12","alias_value":"Y2E7Q5ZSTW7J","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y2E7Q5ZSTW7JU7LR","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y2E7Q5ZS","created_at":"2026-07-05T11:07:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y2E7Q5ZSTW7JU7LRI5YRSJYMFS","target":"record","payload":{"canonical_record":{"source":{"id":"2410.03450","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T14:10:39Z","cross_cats_sorted":[],"title_canon_sha256":"e6d13dc120d9f8a5357bfcad4f88d49fd77ab5657fda47ff1ff16ebf470b464d","abstract_canon_sha256":"97742730f90199c2f92301a371ee66f377b24448c8d4eb495d8a0d0a25d1dbc2"},"schema_version":"1.0"},"canonical_sha256":"c689f877329dbe9a7d71477119270c2cab52d1a4e964352851c2b40573cbda4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:04.948633Z","signature_b64":"U2DMaPCNmed9qNkp5pBhWov7gKoDv7ZW+zHInKpNB+pnWm96g+PQ4uuF/pl37R8hsFVol44QI5pLxnM+XTINAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c689f877329dbe9a7d71477119270c2cab52d1a4e964352851c2b40573cbda4c","last_reissued_at":"2026-07-05T11:07:04.948150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:04.948150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.03450","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":"2026-07-05T11:07:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Ysvu2edvtF//vdjdhR0QfjcceE8OmFrIBAMfCbzlZQAGXG9QJ7gRIbC86ypT12REeBu0hvtBveiwoEXNVnbDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:09:57.819276Z"},"content_sha256":"2d42dfa1c57862f0514420cd7784d333c0dee59c49aad88fe36996c463095f01","schema_version":"1.0","event_id":"sha256:2d42dfa1c57862f0514420cd7784d333c0dee59c49aad88fe36996c463095f01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y2E7Q5ZSTW7JU7LRI5YRSJYMFS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"B\\\"orje F. Karlsson, Junpeng Yue, Xinrun Xu, Zongqing Lu","submitted_at":"2024-10-04T14:10:39Z","abstract_excerpt":"MLLM agents demonstrate potential for complex embodied tasks by retrieving multimodal task-relevant trajectory data. However, current retrieval methods primarily focus on surface-level similarities of textual or visual cues in trajectories, neglecting their effectiveness for the specific task at hand. To address this issue, we propose a novel method, MLLM As ReTriever (MART), which enhances the performance of embodied agents by utilizing interaction data to fine-tune an MLLM retriever based on preference learning, such that the retriever fully considers the effectiveness of trajectories and pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03450","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/2410.03450/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":"2026-07-05T11:07:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MB0VkcjFjbjovGQ3xLt+rO9TS/fyhDbl1TRVsHOGalG5WtX4kx8gBKVVxQcnqUk1iQvqxEN6lx19tRpZv1VWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:09:57.828512Z"},"content_sha256":"3eee7c381198ffab92efb5e91e0340d3d35a3dcaa9c8a3ec903023311494d334","schema_version":"1.0","event_id":"sha256:3eee7c381198ffab92efb5e91e0340d3d35a3dcaa9c8a3ec903023311494d334"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y2E7Q5ZSTW7JU7LRI5YRSJYMFS/bundle.json","state_url":"https://pith.science/pith/Y2E7Q5ZSTW7JU7LRI5YRSJYMFS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y2E7Q5ZSTW7JU7LRI5YRSJYMFS/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":"2026-08-14T09:09:57Z","links":{"resolver":"https://pith.science/pith/Y2E7Q5ZSTW7JU7LRI5YRSJYMFS","bundle":"https://pith.science/pith/Y2E7Q5ZSTW7JU7LRI5YRSJYMFS/bundle.json","state":"https://pith.science/pith/Y2E7Q5ZSTW7JU7LRI5YRSJYMFS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y2E7Q5ZSTW7JU7LRI5YRSJYMFS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y2E7Q5ZSTW7JU7LRI5YRSJYMFS","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":"97742730f90199c2f92301a371ee66f377b24448c8d4eb495d8a0d0a25d1dbc2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T14:10:39Z","title_canon_sha256":"e6d13dc120d9f8a5357bfcad4f88d49fd77ab5657fda47ff1ff16ebf470b464d"},"schema_version":"1.0","source":{"id":"2410.03450","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03450","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03450v2","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03450","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"pith_short_12","alias_value":"Y2E7Q5ZSTW7J","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y2E7Q5ZSTW7JU7LR","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y2E7Q5ZS","created_at":"2026-07-05T11:07:04Z"}],"graph_snapshots":[{"event_id":"sha256:3eee7c381198ffab92efb5e91e0340d3d35a3dcaa9c8a3ec903023311494d334","target":"graph","created_at":"2026-07-05T11:07:04Z","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/2410.03450/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"MLLM agents demonstrate potential for complex embodied tasks by retrieving multimodal task-relevant trajectory data. However, current retrieval methods primarily focus on surface-level similarities of textual or visual cues in trajectories, neglecting their effectiveness for the specific task at hand. To address this issue, we propose a novel method, MLLM As ReTriever (MART), which enhances the performance of embodied agents by utilizing interaction data to fine-tune an MLLM retriever based on preference learning, such that the retriever fully considers the effectiveness of trajectories and pr","authors_text":"B\\\"orje F. Karlsson, Junpeng Yue, Xinrun Xu, Zongqing Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T14:10:39Z","title":"MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03450","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":"sha256:2d42dfa1c57862f0514420cd7784d333c0dee59c49aad88fe36996c463095f01","target":"record","created_at":"2026-07-05T11:07:04Z","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":"97742730f90199c2f92301a371ee66f377b24448c8d4eb495d8a0d0a25d1dbc2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T14:10:39Z","title_canon_sha256":"e6d13dc120d9f8a5357bfcad4f88d49fd77ab5657fda47ff1ff16ebf470b464d"},"schema_version":"1.0","source":{"id":"2410.03450","kind":"arxiv","version":2}},"canonical_sha256":"c689f877329dbe9a7d71477119270c2cab52d1a4e964352851c2b40573cbda4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c689f877329dbe9a7d71477119270c2cab52d1a4e964352851c2b40573cbda4c","first_computed_at":"2026-07-05T11:07:04.948150Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:04.948150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U2DMaPCNmed9qNkp5pBhWov7gKoDv7ZW+zHInKpNB+pnWm96g+PQ4uuF/pl37R8hsFVol44QI5pLxnM+XTINAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:04.948633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03450","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d42dfa1c57862f0514420cd7784d333c0dee59c49aad88fe36996c463095f01","sha256:3eee7c381198ffab92efb5e91e0340d3d35a3dcaa9c8a3ec903023311494d334"],"state_sha256":"5170ddd87acec3049132dab77ca79c727dc856b026b615677d5ab3c2fe997424"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4hBMjiEtX5tBmTHeIqJNxW/W1ZX3tOTZ9zmVczeiYme+KrhFP0uMY14Wa+1zb9K3GwXmkC4BPMYiLOOuv4hiAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T09:09:57.841052Z","bundle_sha256":"30121ca2f01209681d03e2765e749534d1c4e8d29016554b71a37b2b49885fd8"}}