{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JJCLIWZUGMXCLRQADIUF3KMX3C","short_pith_number":"pith:JJCLIWZU","canonical_record":{"source":{"id":"2503.11576","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T16:44:14Z","cross_cats_sorted":[],"title_canon_sha256":"09132cfca068dd682b4a99ff14333631a45d44b529c8afa3354ced5e991856dc","abstract_canon_sha256":"ecd4e10d8d28590037259a6fdd93c674000cb8669ee17fa0d78332ca0b732abe"},"schema_version":"1.0"},"canonical_sha256":"4a44b45b34332e25c6001a285da997d88926d93e8002d02bd06791d89d088a00","source":{"kind":"arxiv","id":"2503.11576","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.11576","created_at":"2026-07-05T10:31:35Z"},{"alias_kind":"arxiv_version","alias_value":"2503.11576v1","created_at":"2026-07-05T10:31:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11576","created_at":"2026-07-05T10:31:35Z"},{"alias_kind":"pith_short_12","alias_value":"JJCLIWZUGMXC","created_at":"2026-07-05T10:31:35Z"},{"alias_kind":"pith_short_16","alias_value":"JJCLIWZUGMXCLRQA","created_at":"2026-07-05T10:31:35Z"},{"alias_kind":"pith_short_8","alias_value":"JJCLIWZU","created_at":"2026-07-05T10:31:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JJCLIWZUGMXCLRQADIUF3KMX3C","target":"record","payload":{"canonical_record":{"source":{"id":"2503.11576","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T16:44:14Z","cross_cats_sorted":[],"title_canon_sha256":"09132cfca068dd682b4a99ff14333631a45d44b529c8afa3354ced5e991856dc","abstract_canon_sha256":"ecd4e10d8d28590037259a6fdd93c674000cb8669ee17fa0d78332ca0b732abe"},"schema_version":"1.0"},"canonical_sha256":"4a44b45b34332e25c6001a285da997d88926d93e8002d02bd06791d89d088a00","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:35.131240Z","signature_b64":"iUK7F2AlckAtjynMtTGpEr9N9ina4hD8NEaV/ouwOJBtynLdWsEaBDYvB45KSVW+ERITznNw+H/86tx8tOb9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a44b45b34332e25c6001a285da997d88926d93e8002d02bd06791d89d088a00","last_reissued_at":"2026-07-05T10:31:35.130518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:35.130518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.11576","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":"2026-07-05T10:31:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jZmdqsbEZ9Wqcs52m/vrJi6JUInfDdTMXErc7GXb43uznRwLjwRcJEjCUbB+Xj1TfLk5Wyja0sitn3lf7HcAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:00:52.839668Z"},"content_sha256":"63aeeabf503bfac9f28937ae16fcc32f7672f23c60de110814affadd87f5eefe","schema_version":"1.0","event_id":"sha256:63aeeabf503bfac9f28937ae16fcc32f7672f23c60de110814affadd87f5eefe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JJCLIWZUGMXCLRQADIUF3KMX3C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmed Nassar, Andres Marafioti, A. Said Gurbuz, Christoph Auer, Lucas Morin, Maksym Lysak, Matteo Omenetti, Michele Dolfi, Miquel Farr\\'e, Nikolaos Livathinos, Peter W. J. Staar, Rafael Teixeira de Lima, Yusik Kim","submitted_at":"2025-03-14T16:44:14Z","abstract_excerpt":"We introduce SmolDocling, an ultra-compact vision-language model targeting end-to-end document conversion. Our model comprehensively processes entire pages by generating DocTags, a new universal markup format that captures all page elements in their full context with location. Unlike existing approaches that rely on large foundational models, or ensemble solutions that rely on handcrafted pipelines of multiple specialized models, SmolDocling offers an end-to-end conversion for accurately capturing content, structure and spatial location of document elements in a 256M parameters vision-language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11576","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/2503.11576/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":"2026-07-05T10:31:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/lGy3jLNPluoujH3wz2P8DtC/sU5FGe+2TzXNSk+OdAO2Vz37ZOI0tdf89O7lRIolgN1tpP55xzVL7p8O4rDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:00:52.840287Z"},"content_sha256":"aaefbadb0db65656207873077fb183b9dde337e053e1af1fe187e2370bdb2139","schema_version":"1.0","event_id":"sha256:aaefbadb0db65656207873077fb183b9dde337e053e1af1fe187e2370bdb2139"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JJCLIWZUGMXCLRQADIUF3KMX3C/bundle.json","state_url":"https://pith.science/pith/JJCLIWZUGMXCLRQADIUF3KMX3C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JJCLIWZUGMXCLRQADIUF3KMX3C/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":"2026-08-01T07:00:52Z","links":{"resolver":"https://pith.science/pith/JJCLIWZUGMXCLRQADIUF3KMX3C","bundle":"https://pith.science/pith/JJCLIWZUGMXCLRQADIUF3KMX3C/bundle.json","state":"https://pith.science/pith/JJCLIWZUGMXCLRQADIUF3KMX3C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JJCLIWZUGMXCLRQADIUF3KMX3C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JJCLIWZUGMXCLRQADIUF3KMX3C","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":"ecd4e10d8d28590037259a6fdd93c674000cb8669ee17fa0d78332ca0b732abe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T16:44:14Z","title_canon_sha256":"09132cfca068dd682b4a99ff14333631a45d44b529c8afa3354ced5e991856dc"},"schema_version":"1.0","source":{"id":"2503.11576","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.11576","created_at":"2026-07-05T10:31:35Z"},{"alias_kind":"arxiv_version","alias_value":"2503.11576v1","created_at":"2026-07-05T10:31:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11576","created_at":"2026-07-05T10:31:35Z"},{"alias_kind":"pith_short_12","alias_value":"JJCLIWZUGMXC","created_at":"2026-07-05T10:31:35Z"},{"alias_kind":"pith_short_16","alias_value":"JJCLIWZUGMXCLRQA","created_at":"2026-07-05T10:31:35Z"},{"alias_kind":"pith_short_8","alias_value":"JJCLIWZU","created_at":"2026-07-05T10:31:35Z"}],"graph_snapshots":[{"event_id":"sha256:aaefbadb0db65656207873077fb183b9dde337e053e1af1fe187e2370bdb2139","target":"graph","created_at":"2026-07-05T10:31:35Z","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/2503.11576/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce SmolDocling, an ultra-compact vision-language model targeting end-to-end document conversion. Our model comprehensively processes entire pages by generating DocTags, a new universal markup format that captures all page elements in their full context with location. Unlike existing approaches that rely on large foundational models, or ensemble solutions that rely on handcrafted pipelines of multiple specialized models, SmolDocling offers an end-to-end conversion for accurately capturing content, structure and spatial location of document elements in a 256M parameters vision-language","authors_text":"Ahmed Nassar, Andres Marafioti, A. Said Gurbuz, Christoph Auer, Lucas Morin, Maksym Lysak, Matteo Omenetti, Michele Dolfi, Miquel Farr\\'e, Nikolaos Livathinos, Peter W. J. Staar, Rafael Teixeira de Lima, Yusik Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T16:44:14Z","title":"SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11576","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":"sha256:63aeeabf503bfac9f28937ae16fcc32f7672f23c60de110814affadd87f5eefe","target":"record","created_at":"2026-07-05T10:31:35Z","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":"ecd4e10d8d28590037259a6fdd93c674000cb8669ee17fa0d78332ca0b732abe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T16:44:14Z","title_canon_sha256":"09132cfca068dd682b4a99ff14333631a45d44b529c8afa3354ced5e991856dc"},"schema_version":"1.0","source":{"id":"2503.11576","kind":"arxiv","version":1}},"canonical_sha256":"4a44b45b34332e25c6001a285da997d88926d93e8002d02bd06791d89d088a00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a44b45b34332e25c6001a285da997d88926d93e8002d02bd06791d89d088a00","first_computed_at":"2026-07-05T10:31:35.130518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:35.130518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iUK7F2AlckAtjynMtTGpEr9N9ina4hD8NEaV/ouwOJBtynLdWsEaBDYvB45KSVW+ERITznNw+H/86tx8tOb9AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:35.131240Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.11576","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63aeeabf503bfac9f28937ae16fcc32f7672f23c60de110814affadd87f5eefe","sha256:aaefbadb0db65656207873077fb183b9dde337e053e1af1fe187e2370bdb2139"],"state_sha256":"96474a5f1958a172018b701de09336ac45eed113df006812a9801722a0e8d766"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rbpckaq5Km58bvFQBrh54HPyyqzYfTkQ6o/p1b7TUHVZvQ6KvAgLoPorZedsLVhB3y21Up278TMOvHIuxFd6DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T07:00:52.844256Z","bundle_sha256":"3320ed5dcd5eef5f292307b9ac98f0ab7093bd3a4de0b577fc2e13a413d4c355"}}