{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UD3SREWHTN5CVULUUWMYFALY4L","short_pith_number":"pith:UD3SREWH","canonical_record":{"source":{"id":"2501.10967","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-19T07:00:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"36368a004253de7bed3ef27d8aeb3855eb5992fb592b4af25e66beea36cf1514","abstract_canon_sha256":"4186f768f85aa325b7bbd8d9f64d7b118f5987b62dbe4ea800451d7668599762"},"schema_version":"1.0"},"canonical_sha256":"a0f72892c79b7a2ad174a599828178e2c11f2ccebb10a31923f5fc7868fc9065","source":{"kind":"arxiv","id":"2501.10967","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.10967","created_at":"2026-07-05T10:13:07Z"},{"alias_kind":"arxiv_version","alias_value":"2501.10967v2","created_at":"2026-07-05T10:13:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10967","created_at":"2026-07-05T10:13:07Z"},{"alias_kind":"pith_short_12","alias_value":"UD3SREWHTN5C","created_at":"2026-07-05T10:13:07Z"},{"alias_kind":"pith_short_16","alias_value":"UD3SREWHTN5CVULU","created_at":"2026-07-05T10:13:07Z"},{"alias_kind":"pith_short_8","alias_value":"UD3SREWH","created_at":"2026-07-05T10:13:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UD3SREWHTN5CVULUUWMYFALY4L","target":"record","payload":{"canonical_record":{"source":{"id":"2501.10967","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-19T07:00:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"36368a004253de7bed3ef27d8aeb3855eb5992fb592b4af25e66beea36cf1514","abstract_canon_sha256":"4186f768f85aa325b7bbd8d9f64d7b118f5987b62dbe4ea800451d7668599762"},"schema_version":"1.0"},"canonical_sha256":"a0f72892c79b7a2ad174a599828178e2c11f2ccebb10a31923f5fc7868fc9065","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:07.430014Z","signature_b64":"k0Sx3zbA/0zt+V9rA6JI52Z687nSoiTnMxHY3km+e+feeogoq+MzBPWGk5cyXPdTDDx7R8Qnrnz5Suju1OCPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0f72892c79b7a2ad174a599828178e2c11f2ccebb10a31923f5fc7868fc9065","last_reissued_at":"2026-07-05T10:13:07.429561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:07.429561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.10967","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":"2026-07-05T10:13:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6pHo/Ok/VeaGpU2C/eKIfhFEBtQU9gVfZToKpubYfwZf/odLCGyK9wkn0ueGkqTE4rkxTN1AmkOOMlvfTjxMAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T02:28:56.624453Z"},"content_sha256":"8f14b3f0bdadf39c2face2fc4a89e044a0c4d2b4ef6c3eedfd7b84515f66e529","schema_version":"1.0","event_id":"sha256:8f14b3f0bdadf39c2face2fc4a89e044a0c4d2b4ef6c3eedfd7b84515f66e529"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UD3SREWHTN5CVULUUWMYFALY4L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advancing General Multimodal Capability of Vision-language Models with Pyramid-descent Visual Position Encoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Mingxiao Li, Nan Du, Xiaolong Li, Yuexian Zou, Zhanpeng Chen, Ziyang Chen","submitted_at":"2025-01-19T07:00:46Z","abstract_excerpt":"Vision-language Models (VLMs) have shown remarkable capabilities in advancing general artificial intelligence, yet the irrational encoding of visual positions persists in inhibiting the models' comprehensive perception performance across different levels of granularity. In this work, we propose Pyramid-descent Visual Position Encoding (PyPE), a novel approach designed to enhance the perception of visual tokens within VLMs. By assigning visual position indexes from the periphery to the center and expanding the central receptive field incrementally, PyPE addresses the limitations of traditional "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10967","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/2501.10967/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":"2026-07-05T10:13:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EaomMquaR8FI58Y4BDqxlGTqrUgGGZPBgN/KHBwKT9A3Hay6y24lG/Ae5hniegJC1bxoo0JXaG4Yt41IFx0tDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T02:28:56.624960Z"},"content_sha256":"434d3015afae4ed68c01fecc5c845edf8d7786aabeac0e72334e33135825b91e","schema_version":"1.0","event_id":"sha256:434d3015afae4ed68c01fecc5c845edf8d7786aabeac0e72334e33135825b91e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UD3SREWHTN5CVULUUWMYFALY4L/bundle.json","state_url":"https://pith.science/pith/UD3SREWHTN5CVULUUWMYFALY4L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UD3SREWHTN5CVULUUWMYFALY4L/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":"2026-08-07T02:28:56Z","links":{"resolver":"https://pith.science/pith/UD3SREWHTN5CVULUUWMYFALY4L","bundle":"https://pith.science/pith/UD3SREWHTN5CVULUUWMYFALY4L/bundle.json","state":"https://pith.science/pith/UD3SREWHTN5CVULUUWMYFALY4L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UD3SREWHTN5CVULUUWMYFALY4L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UD3SREWHTN5CVULUUWMYFALY4L","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":"4186f768f85aa325b7bbd8d9f64d7b118f5987b62dbe4ea800451d7668599762","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-19T07:00:46Z","title_canon_sha256":"36368a004253de7bed3ef27d8aeb3855eb5992fb592b4af25e66beea36cf1514"},"schema_version":"1.0","source":{"id":"2501.10967","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.10967","created_at":"2026-07-05T10:13:07Z"},{"alias_kind":"arxiv_version","alias_value":"2501.10967v2","created_at":"2026-07-05T10:13:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10967","created_at":"2026-07-05T10:13:07Z"},{"alias_kind":"pith_short_12","alias_value":"UD3SREWHTN5C","created_at":"2026-07-05T10:13:07Z"},{"alias_kind":"pith_short_16","alias_value":"UD3SREWHTN5CVULU","created_at":"2026-07-05T10:13:07Z"},{"alias_kind":"pith_short_8","alias_value":"UD3SREWH","created_at":"2026-07-05T10:13:07Z"}],"graph_snapshots":[{"event_id":"sha256:434d3015afae4ed68c01fecc5c845edf8d7786aabeac0e72334e33135825b91e","target":"graph","created_at":"2026-07-05T10:13:07Z","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/2501.10967/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language Models (VLMs) have shown remarkable capabilities in advancing general artificial intelligence, yet the irrational encoding of visual positions persists in inhibiting the models' comprehensive perception performance across different levels of granularity. In this work, we propose Pyramid-descent Visual Position Encoding (PyPE), a novel approach designed to enhance the perception of visual tokens within VLMs. By assigning visual position indexes from the periphery to the center and expanding the central receptive field incrementally, PyPE addresses the limitations of traditional ","authors_text":"Mingxiao Li, Nan Du, Xiaolong Li, Yuexian Zou, Zhanpeng Chen, Ziyang Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-19T07:00:46Z","title":"Advancing General Multimodal Capability of Vision-language Models with Pyramid-descent Visual Position Encoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10967","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":"sha256:8f14b3f0bdadf39c2face2fc4a89e044a0c4d2b4ef6c3eedfd7b84515f66e529","target":"record","created_at":"2026-07-05T10:13:07Z","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":"4186f768f85aa325b7bbd8d9f64d7b118f5987b62dbe4ea800451d7668599762","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-19T07:00:46Z","title_canon_sha256":"36368a004253de7bed3ef27d8aeb3855eb5992fb592b4af25e66beea36cf1514"},"schema_version":"1.0","source":{"id":"2501.10967","kind":"arxiv","version":2}},"canonical_sha256":"a0f72892c79b7a2ad174a599828178e2c11f2ccebb10a31923f5fc7868fc9065","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0f72892c79b7a2ad174a599828178e2c11f2ccebb10a31923f5fc7868fc9065","first_computed_at":"2026-07-05T10:13:07.429561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:07.429561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k0Sx3zbA/0zt+V9rA6JI52Z687nSoiTnMxHY3km+e+feeogoq+MzBPWGk5cyXPdTDDx7R8Qnrnz5Suju1OCPBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:07.430014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.10967","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f14b3f0bdadf39c2face2fc4a89e044a0c4d2b4ef6c3eedfd7b84515f66e529","sha256:434d3015afae4ed68c01fecc5c845edf8d7786aabeac0e72334e33135825b91e"],"state_sha256":"4ffc097bcd3dd8c997a9feb2cb9bab559cb467a5cac5ea00c3a8c053e341369c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VdKIYtd8btIdrzlvx4FJJPHkj/0lCz3isMG5QhcPSS9mCozjpIwGIXSgkQB2tGg4ws23nL+disIUyTofJ+3NCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T02:28:56.629003Z","bundle_sha256":"a26c119406647d85b650f7bb0af642e159570199c67f444c924104caab67e749"}}