{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IBB76LLPULFPNARDAH5ZYLAKGR","short_pith_number":"pith:IBB76LLP","canonical_record":{"source":{"id":"2605.20254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-18T12:00:24Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"7b225e94345db0822a6989c7efb374f88fc30fc8137ca7c58ba794574fec40aa","abstract_canon_sha256":"f9cedced579667ab98e278eb4a3e19123f6d562c19d617bf45b37ca9e8df45dd"},"schema_version":"1.0"},"canonical_sha256":"4043ff2d6fa2caf6822301fb9c2c0a346a4cfca267abd86f9b6213fe792d48f9","source":{"kind":"arxiv","id":"2605.20254","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20254","created_at":"2026-05-21T00:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20254v1","created_at":"2026-05-21T00:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20254","created_at":"2026-05-21T00:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"IBB76LLPULFP","created_at":"2026-05-21T00:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"IBB76LLPULFPNARD","created_at":"2026-05-21T00:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"IBB76LLP","created_at":"2026-05-21T00:04:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IBB76LLPULFPNARDAH5ZYLAKGR","target":"record","payload":{"canonical_record":{"source":{"id":"2605.20254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-18T12:00:24Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"7b225e94345db0822a6989c7efb374f88fc30fc8137ca7c58ba794574fec40aa","abstract_canon_sha256":"f9cedced579667ab98e278eb4a3e19123f6d562c19d617bf45b37ca9e8df45dd"},"schema_version":"1.0"},"canonical_sha256":"4043ff2d6fa2caf6822301fb9c2c0a346a4cfca267abd86f9b6213fe792d48f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T00:04:22.830380Z","signature_b64":"fqRpoR+sDZ8xtT/mWTf4yH23XapRszPA5l4hjbQbCHYQyw0f/+W8N9Jdrxj+kanfWhIKEUxS5hUWoRfe3k7SDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4043ff2d6fa2caf6822301fb9c2c0a346a4cfca267abd86f9b6213fe792d48f9","last_reissued_at":"2026-05-21T00:04:22.829856Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T00:04:22.829856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.20254","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":"2026-05-21T00:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kVhDMETsKq+mvRAq7MH26UQ26d/RgDhUptqhwNminvqe9/WfWP4hu2xUrcwSr4DSF2DRTokKY7V5FgP56WXgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T11:30:55.312651Z"},"content_sha256":"b7df4fe9f2fd53894238812661bc01de1814c09f5ca3eeabae891d076162ee23","schema_version":"1.0","event_id":"sha256:b7df4fe9f2fd53894238812661bc01de1814c09f5ca3eeabae891d076162ee23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IBB76LLPULFPNARDAH5ZYLAKGR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.IR","authors_text":"Amritansh Maurya, Mohammed Javed, Navjot Singh, Omar Moured","submitted_at":"2026-05-18T12:00:24Z","abstract_excerpt":"Large Language Models (LLMs) have shown promising results on NLP tasks, however, their performance on tabular data still needs research attention, because Table Question-Answering (TQA) requires precise cell retrieval and multi-step structured reasoning. Existing work improves TQA either by fine-tuning or training LLMs on task-specific tabular data, but often lacks verifiable control over how the model navigates tables and derives answers. In this work, we propose a training-free TQA approach with two structured prompting frameworks: TableGrid Navigation (TGN), which iteratively navigates rows"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20254","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/2605.20254/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":"2026-05-21T00:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3E4H45OnRzWNldYTKHu+d34qHbmAJugF6NaN0A284Yo54nYei9E37k4WlpMLUgg8JxK1b4Bs1SDrJbhgXiqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T11:30:55.313030Z"},"content_sha256":"33d129b5255b0ffc5571ff750c7da785016d53739da304eab584a587cd24872b","schema_version":"1.0","event_id":"sha256:33d129b5255b0ffc5571ff750c7da785016d53739da304eab584a587cd24872b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IBB76LLPULFPNARDAH5ZYLAKGR/bundle.json","state_url":"https://pith.science/pith/IBB76LLPULFPNARDAH5ZYLAKGR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IBB76LLPULFPNARDAH5ZYLAKGR/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":"2026-05-28T11:30:55Z","links":{"resolver":"https://pith.science/pith/IBB76LLPULFPNARDAH5ZYLAKGR","bundle":"https://pith.science/pith/IBB76LLPULFPNARDAH5ZYLAKGR/bundle.json","state":"https://pith.science/pith/IBB76LLPULFPNARDAH5ZYLAKGR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IBB76LLPULFPNARDAH5ZYLAKGR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IBB76LLPULFPNARDAH5ZYLAKGR","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":"f9cedced579667ab98e278eb4a3e19123f6d562c19d617bf45b37ca9e8df45dd","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-18T12:00:24Z","title_canon_sha256":"7b225e94345db0822a6989c7efb374f88fc30fc8137ca7c58ba794574fec40aa"},"schema_version":"1.0","source":{"id":"2605.20254","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20254","created_at":"2026-05-21T00:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20254v1","created_at":"2026-05-21T00:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20254","created_at":"2026-05-21T00:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"IBB76LLPULFP","created_at":"2026-05-21T00:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"IBB76LLPULFPNARD","created_at":"2026-05-21T00:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"IBB76LLP","created_at":"2026-05-21T00:04:22Z"}],"graph_snapshots":[{"event_id":"sha256:33d129b5255b0ffc5571ff750c7da785016d53739da304eab584a587cd24872b","target":"graph","created_at":"2026-05-21T00:04:22Z","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/2605.20254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown promising results on NLP tasks, however, their performance on tabular data still needs research attention, because Table Question-Answering (TQA) requires precise cell retrieval and multi-step structured reasoning. Existing work improves TQA either by fine-tuning or training LLMs on task-specific tabular data, but often lacks verifiable control over how the model navigates tables and derives answers. In this work, we propose a training-free TQA approach with two structured prompting frameworks: TableGrid Navigation (TGN), which iteratively navigates rows","authors_text":"Amritansh Maurya, Mohammed Javed, Navjot Singh, Omar Moured","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-18T12:00:24Z","title":"Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20254","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:b7df4fe9f2fd53894238812661bc01de1814c09f5ca3eeabae891d076162ee23","target":"record","created_at":"2026-05-21T00:04:22Z","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":"f9cedced579667ab98e278eb4a3e19123f6d562c19d617bf45b37ca9e8df45dd","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-18T12:00:24Z","title_canon_sha256":"7b225e94345db0822a6989c7efb374f88fc30fc8137ca7c58ba794574fec40aa"},"schema_version":"1.0","source":{"id":"2605.20254","kind":"arxiv","version":1}},"canonical_sha256":"4043ff2d6fa2caf6822301fb9c2c0a346a4cfca267abd86f9b6213fe792d48f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4043ff2d6fa2caf6822301fb9c2c0a346a4cfca267abd86f9b6213fe792d48f9","first_computed_at":"2026-05-21T00:04:22.829856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T00:04:22.829856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fqRpoR+sDZ8xtT/mWTf4yH23XapRszPA5l4hjbQbCHYQyw0f/+W8N9Jdrxj+kanfWhIKEUxS5hUWoRfe3k7SDg==","signature_status":"signed_v1","signed_at":"2026-05-21T00:04:22.830380Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20254","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7df4fe9f2fd53894238812661bc01de1814c09f5ca3eeabae891d076162ee23","sha256:33d129b5255b0ffc5571ff750c7da785016d53739da304eab584a587cd24872b"],"state_sha256":"0223711681e06a1c7e8ff70ce5ebcda264410ef16637d89ebbb9b5674e7c610c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J+uctjitZr2eYqAvypmcd7hNwDkvpr2N0OcSsDLRVCVnULfws5ngpWJydwO8phvtL2zy0GggyI4iXJQ1Pp/ZAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T11:30:55.315111Z","bundle_sha256":"ea6f41ae3c7fe407bfb3dc2ab1967cc7a682fc308d58596c9965dee1ab793071"}}