{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:BXTRLI5FOJLTTPBEEJ3ML37BAA","short_pith_number":"pith:BXTRLI5F","canonical_record":{"source":{"id":"2211.04188","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-08T12:01:31Z","cross_cats_sorted":[],"title_canon_sha256":"4341312c927cc1ef32dcaeb9d2c627bcd93b5099f48edfbabe5a7f3c54dc8232","abstract_canon_sha256":"815f875a694805c017045127abdb3f28473541cc035751f34650ac81c16632e6"},"schema_version":"1.0"},"canonical_sha256":"0de715a3a5725739bc242276c5efe10000a26609dee10780126c3fd111d0e16c","source":{"kind":"arxiv","id":"2211.04188","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.04188","created_at":"2026-07-05T05:54:55Z"},{"alias_kind":"arxiv_version","alias_value":"2211.04188v2","created_at":"2026-07-05T05:54:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04188","created_at":"2026-07-05T05:54:55Z"},{"alias_kind":"pith_short_12","alias_value":"BXTRLI5FOJLT","created_at":"2026-07-05T05:54:55Z"},{"alias_kind":"pith_short_16","alias_value":"BXTRLI5FOJLTTPBE","created_at":"2026-07-05T05:54:55Z"},{"alias_kind":"pith_short_8","alias_value":"BXTRLI5F","created_at":"2026-07-05T05:54:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:BXTRLI5FOJLTTPBEEJ3ML37BAA","target":"record","payload":{"canonical_record":{"source":{"id":"2211.04188","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-08T12:01:31Z","cross_cats_sorted":[],"title_canon_sha256":"4341312c927cc1ef32dcaeb9d2c627bcd93b5099f48edfbabe5a7f3c54dc8232","abstract_canon_sha256":"815f875a694805c017045127abdb3f28473541cc035751f34650ac81c16632e6"},"schema_version":"1.0"},"canonical_sha256":"0de715a3a5725739bc242276c5efe10000a26609dee10780126c3fd111d0e16c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:55.840385Z","signature_b64":"C4OhRgfSXfbBDpddZEb33XSsGXNkn1nuXh6GmSQGb3GIiiz7S1D1BRrreDZkcKwezBwpm05jt0tUKU7RQRvABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0de715a3a5725739bc242276c5efe10000a26609dee10780126c3fd111d0e16c","last_reissued_at":"2026-07-05T05:54:55.839976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:55.839976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.04188","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":"2026-07-05T05:54:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/pInDs3kUx+KoZZHbT4upjeTJTPkPDNXmQ06cQirIUMyWjcHlLAasX1oQ6SW+tuWE0SI8xzI44M94M8Hn/WXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T03:31:53.558008Z"},"content_sha256":"413e853b21312fa9d34ed735c0dd0450d929d3096fdbc22110fecb4093860277","schema_version":"1.0","event_id":"sha256:413e853b21312fa9d34ed735c0dd0450d929d3096fdbc22110fecb4093860277"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:BXTRLI5FOJLTTPBEEJ3ML37BAA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DepthFormer: Multimodal Positional Encodings and Cross-Input Attention for Transformer-Based Segmentation Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Francesco Barbato, Giulia Rizzoli, Pietro Zanuttigh","submitted_at":"2022-11-08T12:01:31Z","abstract_excerpt":"Most approaches for semantic segmentation use only information from color cameras to parse the scenes, yet recent advancements show that using depth data allows to further improve performances. In this work, we focus on transformer-based deep learning architectures, that have achieved state-of-the-art performances on the segmentation task, and we propose to employ depth information by embedding it in the positional encoding. Effectively, we extend the network to multimodal data without adding any parameters and in a natural way that makes use of the strength of transformers' self-attention mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04188","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/2211.04188/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":"2026-07-05T05:54:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YxPTzP5lWVPtZ7rPhneplxkbbCzcGlQizAkhIGa58JBvAaK6gQTnwk/n+CrqxnJXsP7tow6M43jXh2bwWO67BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T03:31:53.558454Z"},"content_sha256":"5505f9a64d68d2d8183bc2c09ba0806d8cd20ae63db4f029a80a5de0d6d0f1cb","schema_version":"1.0","event_id":"sha256:5505f9a64d68d2d8183bc2c09ba0806d8cd20ae63db4f029a80a5de0d6d0f1cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BXTRLI5FOJLTTPBEEJ3ML37BAA/bundle.json","state_url":"https://pith.science/pith/BXTRLI5FOJLTTPBEEJ3ML37BAA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BXTRLI5FOJLTTPBEEJ3ML37BAA/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":"2026-07-13T03:31:53Z","links":{"resolver":"https://pith.science/pith/BXTRLI5FOJLTTPBEEJ3ML37BAA","bundle":"https://pith.science/pith/BXTRLI5FOJLTTPBEEJ3ML37BAA/bundle.json","state":"https://pith.science/pith/BXTRLI5FOJLTTPBEEJ3ML37BAA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BXTRLI5FOJLTTPBEEJ3ML37BAA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BXTRLI5FOJLTTPBEEJ3ML37BAA","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":"815f875a694805c017045127abdb3f28473541cc035751f34650ac81c16632e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-08T12:01:31Z","title_canon_sha256":"4341312c927cc1ef32dcaeb9d2c627bcd93b5099f48edfbabe5a7f3c54dc8232"},"schema_version":"1.0","source":{"id":"2211.04188","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.04188","created_at":"2026-07-05T05:54:55Z"},{"alias_kind":"arxiv_version","alias_value":"2211.04188v2","created_at":"2026-07-05T05:54:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04188","created_at":"2026-07-05T05:54:55Z"},{"alias_kind":"pith_short_12","alias_value":"BXTRLI5FOJLT","created_at":"2026-07-05T05:54:55Z"},{"alias_kind":"pith_short_16","alias_value":"BXTRLI5FOJLTTPBE","created_at":"2026-07-05T05:54:55Z"},{"alias_kind":"pith_short_8","alias_value":"BXTRLI5F","created_at":"2026-07-05T05:54:55Z"}],"graph_snapshots":[{"event_id":"sha256:5505f9a64d68d2d8183bc2c09ba0806d8cd20ae63db4f029a80a5de0d6d0f1cb","target":"graph","created_at":"2026-07-05T05:54:55Z","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/2211.04188/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most approaches for semantic segmentation use only information from color cameras to parse the scenes, yet recent advancements show that using depth data allows to further improve performances. In this work, we focus on transformer-based deep learning architectures, that have achieved state-of-the-art performances on the segmentation task, and we propose to employ depth information by embedding it in the positional encoding. Effectively, we extend the network to multimodal data without adding any parameters and in a natural way that makes use of the strength of transformers' self-attention mod","authors_text":"Francesco Barbato, Giulia Rizzoli, Pietro Zanuttigh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-08T12:01:31Z","title":"DepthFormer: Multimodal Positional Encodings and Cross-Input Attention for Transformer-Based Segmentation Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04188","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":"sha256:413e853b21312fa9d34ed735c0dd0450d929d3096fdbc22110fecb4093860277","target":"record","created_at":"2026-07-05T05:54:55Z","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":"815f875a694805c017045127abdb3f28473541cc035751f34650ac81c16632e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-08T12:01:31Z","title_canon_sha256":"4341312c927cc1ef32dcaeb9d2c627bcd93b5099f48edfbabe5a7f3c54dc8232"},"schema_version":"1.0","source":{"id":"2211.04188","kind":"arxiv","version":2}},"canonical_sha256":"0de715a3a5725739bc242276c5efe10000a26609dee10780126c3fd111d0e16c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0de715a3a5725739bc242276c5efe10000a26609dee10780126c3fd111d0e16c","first_computed_at":"2026-07-05T05:54:55.839976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:55.839976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C4OhRgfSXfbBDpddZEb33XSsGXNkn1nuXh6GmSQGb3GIiiz7S1D1BRrreDZkcKwezBwpm05jt0tUKU7RQRvABw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:55.840385Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.04188","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:413e853b21312fa9d34ed735c0dd0450d929d3096fdbc22110fecb4093860277","sha256:5505f9a64d68d2d8183bc2c09ba0806d8cd20ae63db4f029a80a5de0d6d0f1cb"],"state_sha256":"85a58d3cfad2ddee754c9414cdac7f3833e6adadb50380382d21c89f51bc09d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4kIxscoROe5RTmUQ3NGJg7z4h8fg1miMyGgV5L/3l1Kae0+0Ss3BPZ81TrIUnjV3W6EdOgyHZRc7xlHYrceWDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T03:31:53.561714Z","bundle_sha256":"e40e25bbed3da08b5c77f303187cefb8d99dd189dc3eac3f72090214edffa375"}}