{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EXE2PPMNWBA4TXGYFJJRL7DZZA","short_pith_number":"pith:EXE2PPMN","canonical_record":{"source":{"id":"2603.10863","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-11T15:15:12Z","cross_cats_sorted":[],"title_canon_sha256":"9b73f452912fb7544805da47a6da3c5714f90c120acac8d1432f755546776434","abstract_canon_sha256":"80955a462a8bfb9db485d1efe927f857ed1986c3f32dd46199ea406ded6a6b31"},"schema_version":"1.0"},"canonical_sha256":"25c9a7bd8db041c9dcd82a5315fc79c819487197bb6165c88f63909d929da1f9","source":{"kind":"arxiv","id":"2603.10863","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.10863","created_at":"2026-06-29T01:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2603.10863v2","created_at":"2026-06-29T01:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10863","created_at":"2026-06-29T01:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"EXE2PPMNWBA4","created_at":"2026-06-29T01:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"EXE2PPMNWBA4TXGY","created_at":"2026-06-29T01:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"EXE2PPMN","created_at":"2026-06-29T01:15:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EXE2PPMNWBA4TXGYFJJRL7DZZA","target":"record","payload":{"canonical_record":{"source":{"id":"2603.10863","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-11T15:15:12Z","cross_cats_sorted":[],"title_canon_sha256":"9b73f452912fb7544805da47a6da3c5714f90c120acac8d1432f755546776434","abstract_canon_sha256":"80955a462a8bfb9db485d1efe927f857ed1986c3f32dd46199ea406ded6a6b31"},"schema_version":"1.0"},"canonical_sha256":"25c9a7bd8db041c9dcd82a5315fc79c819487197bb6165c88f63909d929da1f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:15:04.466366Z","signature_b64":"r5Q+KuUhuuqcffM/6c5U22vYLQtN8baDljBBAYO/q9SKGlabu+DIIw/iY7MTyhvH/Yw+fmDJUuYm15+VuDRpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25c9a7bd8db041c9dcd82a5315fc79c819487197bb6165c88f63909d929da1f9","last_reissued_at":"2026-06-29T01:15:04.465852Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:15:04.465852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.10863","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":"2026-06-29T01:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aC2d4jcC0WissLAS/68AtI9vkkFeY2C3NX1O9fePDC1hjYSBghuARwb7jDzND20HGUuzVGR4zSrIzANwQH+JBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T16:17:45.909951Z"},"content_sha256":"26aa635ebaa824d5c8461ff71c492b1a831eec7f4b0d58775a3f0340f7b634bd","schema_version":"1.0","event_id":"sha256:26aa635ebaa824d5c8461ff71c492b1a831eec7f4b0d58775a3f0340f7b634bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EXE2PPMNWBA4TXGYFJJRL7DZZA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bolin Ni, Houwen Peng, Kun Ding, Lin Chen, Qi Yang, Shiming Xiang, Ying Wang, Zili Wang","submitted_at":"2026-03-11T15:15:12Z","abstract_excerpt":"Despite the remarkable capabilities of Multimodal Large Language Models (MLLMs), they still suffer from visual fading in long-context scenarios. Specifically, the attention to visual tokens diminishes as the text sequence lengthens, leading to text generation detached from visual constraints. We attribute this degradation to the inherent inductive bias of Multimodal RoPE, which penalizes inter-modal attention as the distance between visual and text tokens increases. To address this, we propose inter-modal Distance Invariant Position Encoding (DIPE), a simple but effective mechanism that disent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.10863","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/2603.10863/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":"2026-06-29T01:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TEDZMNRgk6Kstp7yayMz1idnyHB6qFgRSPWKRbadyOfe8iT2pI8nF8Kau/PNBGwzLkqVnNWPlmc7/SKvvJH4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T16:17:45.910335Z"},"content_sha256":"d14635bab24499a056d5493dde0a8f3dd50afcce0739b68bf48d448aabdebac5","schema_version":"1.0","event_id":"sha256:d14635bab24499a056d5493dde0a8f3dd50afcce0739b68bf48d448aabdebac5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EXE2PPMNWBA4TXGYFJJRL7DZZA/bundle.json","state_url":"https://pith.science/pith/EXE2PPMNWBA4TXGYFJJRL7DZZA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EXE2PPMNWBA4TXGYFJJRL7DZZA/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":"2026-07-03T16:17:45Z","links":{"resolver":"https://pith.science/pith/EXE2PPMNWBA4TXGYFJJRL7DZZA","bundle":"https://pith.science/pith/EXE2PPMNWBA4TXGYFJJRL7DZZA/bundle.json","state":"https://pith.science/pith/EXE2PPMNWBA4TXGYFJJRL7DZZA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EXE2PPMNWBA4TXGYFJJRL7DZZA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EXE2PPMNWBA4TXGYFJJRL7DZZA","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":"80955a462a8bfb9db485d1efe927f857ed1986c3f32dd46199ea406ded6a6b31","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-11T15:15:12Z","title_canon_sha256":"9b73f452912fb7544805da47a6da3c5714f90c120acac8d1432f755546776434"},"schema_version":"1.0","source":{"id":"2603.10863","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.10863","created_at":"2026-06-29T01:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2603.10863v2","created_at":"2026-06-29T01:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10863","created_at":"2026-06-29T01:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"EXE2PPMNWBA4","created_at":"2026-06-29T01:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"EXE2PPMNWBA4TXGY","created_at":"2026-06-29T01:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"EXE2PPMN","created_at":"2026-06-29T01:15:04Z"}],"graph_snapshots":[{"event_id":"sha256:d14635bab24499a056d5493dde0a8f3dd50afcce0739b68bf48d448aabdebac5","target":"graph","created_at":"2026-06-29T01:15:04Z","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/2603.10863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the remarkable capabilities of Multimodal Large Language Models (MLLMs), they still suffer from visual fading in long-context scenarios. Specifically, the attention to visual tokens diminishes as the text sequence lengthens, leading to text generation detached from visual constraints. We attribute this degradation to the inherent inductive bias of Multimodal RoPE, which penalizes inter-modal attention as the distance between visual and text tokens increases. To address this, we propose inter-modal Distance Invariant Position Encoding (DIPE), a simple but effective mechanism that disent","authors_text":"Bolin Ni, Houwen Peng, Kun Ding, Lin Chen, Qi Yang, Shiming Xiang, Ying Wang, Zili Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-11T15:15:12Z","title":"Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.10863","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":"sha256:26aa635ebaa824d5c8461ff71c492b1a831eec7f4b0d58775a3f0340f7b634bd","target":"record","created_at":"2026-06-29T01:15:04Z","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":"80955a462a8bfb9db485d1efe927f857ed1986c3f32dd46199ea406ded6a6b31","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-11T15:15:12Z","title_canon_sha256":"9b73f452912fb7544805da47a6da3c5714f90c120acac8d1432f755546776434"},"schema_version":"1.0","source":{"id":"2603.10863","kind":"arxiv","version":2}},"canonical_sha256":"25c9a7bd8db041c9dcd82a5315fc79c819487197bb6165c88f63909d929da1f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25c9a7bd8db041c9dcd82a5315fc79c819487197bb6165c88f63909d929da1f9","first_computed_at":"2026-06-29T01:15:04.465852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:15:04.465852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r5Q+KuUhuuqcffM/6c5U22vYLQtN8baDljBBAYO/q9SKGlabu+DIIw/iY7MTyhvH/Yw+fmDJUuYm15+VuDRpAQ==","signature_status":"signed_v1","signed_at":"2026-06-29T01:15:04.466366Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.10863","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26aa635ebaa824d5c8461ff71c492b1a831eec7f4b0d58775a3f0340f7b634bd","sha256:d14635bab24499a056d5493dde0a8f3dd50afcce0739b68bf48d448aabdebac5"],"state_sha256":"cbf7a6641555bd0f29b262f2100cfa6a10905d6bccb6925d586729ea32539d8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H6+5f8zuw/ojy1OkO8wXzntDlfiQ6H/l4EU2blEaxYPBLESKn6sawXf3pjwAIRVE8T7Esa+zEUPN/hS5a9rQCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T16:17:45.912352Z","bundle_sha256":"ac2e22ef613d66d485a52f11c29503ffd5d3019cb5ab536ce053aecefcaae98f"}}