{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MXR65Z453C7VPOLT7HP7KFJ6L7","short_pith_number":"pith:MXR65Z45","canonical_record":{"source":{"id":"2501.01470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-01T06:19:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3ea7f5f2ee51cd67e8c62c82c7389ad76bea1a9fff6e48d3b0e7d3a889452bb5","abstract_canon_sha256":"62ad7ce7a3353a9ae371d21b28c2dad666ac36802561097a155619b0758f3bd3"},"schema_version":"1.0"},"canonical_sha256":"65e3eee79dd8bf57b973f9dff5153e5fc18f1fd62621dac6609a1d9fe63cde5e","source":{"kind":"arxiv","id":"2501.01470","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01470","created_at":"2026-07-05T09:56:25Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01470v1","created_at":"2026-07-05T09:56:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01470","created_at":"2026-07-05T09:56:25Z"},{"alias_kind":"pith_short_12","alias_value":"MXR65Z453C7V","created_at":"2026-07-05T09:56:25Z"},{"alias_kind":"pith_short_16","alias_value":"MXR65Z453C7VPOLT","created_at":"2026-07-05T09:56:25Z"},{"alias_kind":"pith_short_8","alias_value":"MXR65Z45","created_at":"2026-07-05T09:56:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MXR65Z453C7VPOLT7HP7KFJ6L7","target":"record","payload":{"canonical_record":{"source":{"id":"2501.01470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-01T06:19:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3ea7f5f2ee51cd67e8c62c82c7389ad76bea1a9fff6e48d3b0e7d3a889452bb5","abstract_canon_sha256":"62ad7ce7a3353a9ae371d21b28c2dad666ac36802561097a155619b0758f3bd3"},"schema_version":"1.0"},"canonical_sha256":"65e3eee79dd8bf57b973f9dff5153e5fc18f1fd62621dac6609a1d9fe63cde5e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:25.235538Z","signature_b64":"yerhgg4J4XHY86B3/LbfOyauOZ40OkBBkc7kpsp4fKKpfBqZ9W2j8nU364bYjfpWjdz+FAflvs396N17+XCSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65e3eee79dd8bf57b973f9dff5153e5fc18f1fd62621dac6609a1d9fe63cde5e","last_reissued_at":"2026-07-05T09:56:25.235118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:25.235118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.01470","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":"2026-07-05T09:56:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yW0jsHnFj4QXc64KWnLWG66jlGyzbnKw5TZgUU/Go/kPrPfiMtCpiyCw3l4CnN6jcvZtQzaaWyuuzCuVeRaFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:08:25.583296Z"},"content_sha256":"744aa545b4fda686c63019e42245702fb57f5a67d268fbaabaccc39a6c22ddb3","schema_version":"1.0","event_id":"sha256:744aa545b4fda686c63019e42245702fb57f5a67d268fbaabaccc39a6c22ddb3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MXR65Z453C7VPOLT7HP7KFJ6L7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Balance-aware Sequence Sampling Makes Multi-modal Learning Better","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Zhi-Hao Guan","submitted_at":"2025-01-01T06:19:55Z","abstract_excerpt":"To address the modality imbalance caused by data heterogeneity, existing multi-modal learning (MML) approaches primarily focus on balancing this difference from the perspective of optimization objectives. However, almost all existing methods ignore the impact of sample sequences, i.e., an inappropriate training order tends to trigger learning bias in the model, further exacerbating modality imbalance. In this paper, we propose Balance-aware Sequence Sampling (BSS) to enhance the robustness of MML. Specifically, we first define a multi-perspective measurer to evaluate the balance degree of each"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01470","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/2501.01470/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":"2026-07-05T09:56:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EMji1S97roFW/ouAxUiNa1puu0biVRbtJoC/XgJXz9G9CluZUVJyjL3UQa7oYo29mRr6r+HCbFR4w7ZH94jlCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:08:25.583803Z"},"content_sha256":"26706d75deb82d2694f67499ee054295d19c41e2070b0262d05c91f7561dce3c","schema_version":"1.0","event_id":"sha256:26706d75deb82d2694f67499ee054295d19c41e2070b0262d05c91f7561dce3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MXR65Z453C7VPOLT7HP7KFJ6L7/bundle.json","state_url":"https://pith.science/pith/MXR65Z453C7VPOLT7HP7KFJ6L7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MXR65Z453C7VPOLT7HP7KFJ6L7/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":"2026-08-11T13:08:25Z","links":{"resolver":"https://pith.science/pith/MXR65Z453C7VPOLT7HP7KFJ6L7","bundle":"https://pith.science/pith/MXR65Z453C7VPOLT7HP7KFJ6L7/bundle.json","state":"https://pith.science/pith/MXR65Z453C7VPOLT7HP7KFJ6L7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MXR65Z453C7VPOLT7HP7KFJ6L7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MXR65Z453C7VPOLT7HP7KFJ6L7","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":"62ad7ce7a3353a9ae371d21b28c2dad666ac36802561097a155619b0758f3bd3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-01T06:19:55Z","title_canon_sha256":"3ea7f5f2ee51cd67e8c62c82c7389ad76bea1a9fff6e48d3b0e7d3a889452bb5"},"schema_version":"1.0","source":{"id":"2501.01470","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01470","created_at":"2026-07-05T09:56:25Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01470v1","created_at":"2026-07-05T09:56:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01470","created_at":"2026-07-05T09:56:25Z"},{"alias_kind":"pith_short_12","alias_value":"MXR65Z453C7V","created_at":"2026-07-05T09:56:25Z"},{"alias_kind":"pith_short_16","alias_value":"MXR65Z453C7VPOLT","created_at":"2026-07-05T09:56:25Z"},{"alias_kind":"pith_short_8","alias_value":"MXR65Z45","created_at":"2026-07-05T09:56:25Z"}],"graph_snapshots":[{"event_id":"sha256:26706d75deb82d2694f67499ee054295d19c41e2070b0262d05c91f7561dce3c","target":"graph","created_at":"2026-07-05T09:56:25Z","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/2501.01470/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To address the modality imbalance caused by data heterogeneity, existing multi-modal learning (MML) approaches primarily focus on balancing this difference from the perspective of optimization objectives. However, almost all existing methods ignore the impact of sample sequences, i.e., an inappropriate training order tends to trigger learning bias in the model, further exacerbating modality imbalance. In this paper, we propose Balance-aware Sequence Sampling (BSS) to enhance the robustness of MML. Specifically, we first define a multi-perspective measurer to evaluate the balance degree of each","authors_text":"Zhi-Hao Guan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-01T06:19:55Z","title":"Balance-aware Sequence Sampling Makes Multi-modal Learning Better"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01470","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":"sha256:744aa545b4fda686c63019e42245702fb57f5a67d268fbaabaccc39a6c22ddb3","target":"record","created_at":"2026-07-05T09:56:25Z","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":"62ad7ce7a3353a9ae371d21b28c2dad666ac36802561097a155619b0758f3bd3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-01T06:19:55Z","title_canon_sha256":"3ea7f5f2ee51cd67e8c62c82c7389ad76bea1a9fff6e48d3b0e7d3a889452bb5"},"schema_version":"1.0","source":{"id":"2501.01470","kind":"arxiv","version":1}},"canonical_sha256":"65e3eee79dd8bf57b973f9dff5153e5fc18f1fd62621dac6609a1d9fe63cde5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65e3eee79dd8bf57b973f9dff5153e5fc18f1fd62621dac6609a1d9fe63cde5e","first_computed_at":"2026-07-05T09:56:25.235118Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:25.235118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yerhgg4J4XHY86B3/LbfOyauOZ40OkBBkc7kpsp4fKKpfBqZ9W2j8nU364bYjfpWjdz+FAflvs396N17+XCSCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:25.235538Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01470","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:744aa545b4fda686c63019e42245702fb57f5a67d268fbaabaccc39a6c22ddb3","sha256:26706d75deb82d2694f67499ee054295d19c41e2070b0262d05c91f7561dce3c"],"state_sha256":"71bc0194e17776e00c77e6ac5beb12bac8a5020ecc7179f00ec0a454d6787342"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MVueL7Cp9FsqhzlxpnO3y4p8D3D6Od/7TGZeDtjaNqDRQg1Hm2AAsNTCz3ioq7cY5q2e/8FVs7SxND85VR8DBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T13:08:25.587518Z","bundle_sha256":"08aac523b30f5662343d185dcaf8d27662b0b90928b5da0352993d97c5ba76fd"}}